Deep Residual Learning for Image Recognition

2015/12/10 by Kaiming He, He, Kaiming, Xiangyu Zhang +5 · 3 voices · 4214 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Advanced Image and Video Retrieval Techniques

paper · pdf · doi:10.48550/arxiv.1512.03385

Abstract

A curated reading list of foundational machine-learning papers, blog posts, and course notes. Compiled from a Hacker News comment by user cute_boi (news.ycombinator.com/item?id=48822131). This record is a bibliographic list only (titles and links); it does not redistribute the referenced works.

Citations

• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Backpropagation Applied to Handwritten Zip Code Recognition
• ImageNet classification with deep convolutional neural networks

Cited by

• PYPM-GGD: Pitman-Yor Process Mixture with Generalized Gaussian Density using ADAM
• HYCO: Hybrid-Cooperative Learning for Data-Driven PDE Modeling
• Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization
• Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction
• Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
• Automatic Stability and Recovery for Neural Network Training
• PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Framework
• FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection
• Low-Altitude Channel Multipath Prediction via Panoramic Perception and Vision-Language Model
• From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning
• Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation
• Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection
• Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement
• On the Convergence of Stochastic Low-Rank Adaptation
• InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting
• LLM-Based Visual Explanation Evaluation Framework for Assessing the Explainability of Facial Skin Disease Classification Models
• Projection Pursuit CPCANet for Domain Generalization
• Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation
• ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors
• Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning
• JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision
• Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet
• Improving Large Vision-Language Models' Understanding for Flow Field Data
• Exact Neural-Network Representations of the Motzkin States
• Pretraining Recurrent Networks without Recurrence
• Deep Convolutional Large-Margin ℓ_p-SVDD for Visual Anomaly Detection
• A Statistical Multi-Objective Framework for Assessing Sensitivity of Radiomic AI Models to Acquisition Parameters
• Quality-Aware Multimodal Fusion Reveals Implicit Identity in Valence-Arousal Features
• Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition
• SocialPulse: On-Device Detection of Social Interactions in Naturalistic Settings Using Smartwatch Sensing
• Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models
• DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV
• DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross-Domain Few-Shot Semantic Segmentation
• Traceback Translators Against Forgetting in Continual Fake Speech Detection
• Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architecture-Agnostic Brain Tumor MRI Triage
• SLT: Robust Quantum Neural Networks for Noisy-Label Medical Image Classification via Supermartingale-based Label Transition
• AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
• PILD: Physics-Informed Learning via Diffusion
• Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
• Auto-adaptive Resonance Equalization using Dilated Residual Networks
• Differentially Private Neural Network Training Under the Hidden State Assumption
• Online Variance Reduction for Domain Adaptation on Streaming Data
• A convergence result of a continuous model of deep learning via a Łojasiewicz--Simon inequality
• Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
• Back to Back with a Copy: A Computational Analysis of AI-Generated Visual Contemporary Art Pastiches
• WiFi Sensing via Reservoir Computing
• Test Case Prioritization for DNNs via Neural Collapse Instability
• Ambiguity-Resolved Micro-Doppler Construction for Asynchronous Bistatic Sensing
• Conjugate Gradient Unrolled Network with PSF Conditioning for Non-Diagonal Data Fidelity in CASSI Reconstruction
• AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
• IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
• Variance-reduced Domain Adaptation using Paired Sampling
• Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation
• Variational Learning of Physical Intuition from a Few Observations: Charting Manifolds of Variational Physics
• Label-Noise Resistant Learning via Optimal Brain Damage Masking
• Weather Estimation for Integrated Sensing and Communication
• ReRAM-aware Model Finetuning addressing I-V Non-linearity and Retention Errors
• The Well-Tempered Likelihood: Honest Confidence Intervals for Misspecified Models
• End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers
• Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness
• PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis
• One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification
• Pipelined Gradient Coding
• Detecting Neural Network Failures through Spectral Analysis of Internal Activations
• Glyce: Glyph-vectors for Chinese Character Representations
• HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
• Great X: A Unified Multi-Modal Simulator Bridging the Sim2Real Gap for 6G
• From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
• TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning
• Hierarchy-Aware and Anatomy-Guided Learning for Lung Ultrasound Video Classification
• Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification
• LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
• Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning
• MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion
• ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning
• End-to-End Differential Privacy in Training Deep Neural Network Classifiers
• A Deep Learning Framework for Predicting Solar EUV Irradiance During Significant Flares
• MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Species
• Occlusion-Aware Panoptic Segmentation with Joint Position Embedding and Occlusion-Level Attention
• Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
• TaskTok: Delving into Task Tokens for Task-driven Image Restoration
• In-Context Learning for Wound Classification with Small Multimodal Language Models
• Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
• Decafs: Disentangled Conditional adversarial Flows
• Posterior Samplings are Missing Modalities Generators for Medical Image Translation
• Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models
• Dual Attention Residuals
• Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making
• Visual Semantic Decoding of Electrocorticography from Video Stimuli using End-to-End Deep Learning
• Advancing Multimodal Fusion on Heterogeneous Medical Data with Hybrid Geometry Attention
• GATE-3D: Geometry-Aware Test-time Adaptive Reranking for Open-Set 3D Shape Retrieval
• AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models
• SynGallery: A Synthetic Gallery of Real Paintings for Instance-Level Artwork Recognition
• Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures
• Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction
• An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers
• LieBN: Batch Normalization over Lie Groups
• InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation
• DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
• DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition
• Scalable Model-Assisted Multi-Target Estimation in Large Image Collections
• Benchmarking NACTI Species Recognition in Long-Tailed Regimes
• SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift
• Program Synthesis for Simulation-Based Inference: Joint Model Selection and Parameter Estimation
• (A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
• Early Yield Prediction for Sugar Beet Fields using Satellite Data -- Learnings from Specialized Vision Transformers
• Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator
• COVAriance-Induced Fairness Gap Penalty for Subgroup-Fair Clustering
• Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models
• mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
• The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric
• Patch Policy: Efficient Embodied Control via Dense Visual Representations
• ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation
• Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning
• The Calibration Channel Determines the Bayes-Error Proxy: An Exact Law for Temperature-Induced Distortion
• EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database
• Dice Loss for Data-imbalanced NLP Tasks
• Rethinking Feature Reliance Evaluation with Semantically Matched Suppression
• Provably Lossless Acceleration of DNN Mutation Testing via Memoization
• Sequential Attention-based Sampling for Histopathological Analysis
• Three-Body Scattering for Generative Modeling
• PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption
• Artificially intelligent agents in the social and behavioral sciences: A history and outlook
• CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification
• The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture
• History-Aware Transformation of ReID Features for Multiple Object Tracking
• AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels
• Cross-Coordinate Correspondence Pruning for Image-to-Point Cloud Registration
• HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
• Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures
• ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators
• The Information Content of Krylov Observables: A Machine Learning Approach
• TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection
• A Research Prototype for Closed-Loop Generative Design of Customized Foot Orthoses via Semantic-Physics Alignment
• Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
• Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
• When Generative Replay Meets Evolving Deepfakes: Dual Confusion-Aware Regularization for Incremental Face Forgery Detection
• Do Value Vectors in Deep Layers Need Context from the Residual Stream?
• REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
• Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
• PI-H2T: Enhancing Long-Tailed Visual Recognition with Permutation-Invariant and Head-to-Tail Feature Fusion
• Robust Losses from Univariate Base Functions for Noisy-Label Learning
• Prompt-Guided Foundation Model Tuning for Pathology Image Classification
• MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
• Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances
• Foundation Model-Driven Semantic Change Detection in Remote Sensing Imagery
• Scalable Open-Source Visuotactile Sensor for 6-Axis Contact Wrench Estimation in Tensegrity Robots
• Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning
• STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
• Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets
• Hybrid Machine Learning for Articulation Angle Estimation of Truck-Semitrailer Combinations
• Online-Score-Aided Federated Learning for Resource-Constrained Wireless Clients with Continual Data Arrival
• Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
• Backpropagation-Free Trunk Training via the Split Forward Gradients
• Task-Oriented Communication with Hybrid-Precision Models
• Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training
• GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking
• Dataset Distillation by Influence Matching
• Code-Poisoning Property Inference Attacks
• DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
• A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
• HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection
• From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data
• Toward a mechanistic understanding of inference in visual cortex and diffusion models
• Disentangling Model and Human Data Uncertainty in Apparent Facial Age Estimation
• Measurement of the branching ratio of the K⁺→π⁺νν decay
• In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention
• Improving Backward Conformal Prediction via Non-Conformity Score Transformation
• Conformal Graph Prediction with Z-Gromov-Wasserstein Distances
• Structure-Induced Information for Rerooting Levin Tree Search
• Pretraining Multiple Instance Learning Networks with Multi-Teacher Distillation from Pathology Slide Foundation Models
• Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
• CoDi -- an exemplar-conditioned diffusion model for low-shot counting
• VTLoc: Learning-based Tactile Contact Localization in Visual Point Clouds
• ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
• Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging
• An LLM-Based Automatic Sportscast Solution for Robot Soccer Matches
• Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
• MuxGel: Simultaneous Dual-Modal Visuo-Tactile Sensing via Spatially Multiplexing and Deep Reconstruction
• Diffusion models recover accurate mixture weights despite score function insensitivity
• xHC: Expanded Hyper-Connections
• The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers
• Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization
• Parameter-efficient Prompt Tuning of Vision Foundation Model With Adaptive Focal Loss for Interpretable MCI Screening
• When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
• Factorized Neural Operators Decompose Dynamic and Persistent Responses
• EdgeFaaS: A Function-based Framework for Edge Computing
• Intentional Electromagnetic Interference Attacks on Facial Recognition
• Knowing You at First Glance: Inferring Apparent Personality from Faces
• From hyperplanes to hyperellipsoids: characterizing the inherent interpretability of linear and single-qubit mixed-state binary classification models
• Estimating Time-Dependent COVID-19 Parameters Using Kolmogorov-Arnold Network and Fourier Series
• GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
• A Step Forward Towards Trustworthy Risk-Aware Facial Retrieval (RA-FR)
• 3D Lane Detection with Odometry for High-Speed Vehicle Racing
• Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
• Predicting Groundwater Arsenic Concentrations Using Graph Neural Networks
• An Empirical Study of Handcrafted Feature Learning and Convolutional Neural Networks for Facial Expression Recognition
• Representation recycling for streaming video analysis
• CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
• AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis
• Reducing Per-Sample Harm in Stochastic Optimization
• Prediction of the Hubbard <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>U</mml:mi> </mml:math> parameter from scanning tunneling microscopy images of moiré systems using image recognition
• Do Transformers Need Three Projections? Systematic Study of QKV Variants
• FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs
• Random network structure stabilizes neural manifolds
• What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?
• Training-Free Bayesian Filtering with Generative Emulators
• 123D: Unifying Multi-Modal Autonomous Driving Data at Scale
• Deep learning reveals genomic regions introgressed between two recurrently hybridizing lynx species
• The illusory simplicity of the feedforward pass: evidence for the dynamical nature of stimulus encoding along the primate ventral stream
• CURE: Privacy-Preserving Split Learning Done Right
• Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data
• Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning
• Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
• Introducing TropiCam‐AI: A taxonomically flexible automated classifier of Neotropical arboreal mammals and birds from camera‐trap data
• Li-ViP3D++: Query-Gated Deformable Camera–LiDAR Fusion for End-to-End Perception and Trajectory Prediction
• Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
• Benchmarking for practice: Few-shot time-series crop-type classification on the EuroCropsML dataset
• FSL-HDnn: A 40-nm Few-Shot On-Device Learning Accelerator With Integrated Feature Extraction and Hyperdimensional Computing
• Learnable Quantum Efficiency Filters for Urban Hyperspectral Segmentation
• mHC: Manifold-Constrained Hyper-Connections
• SomnoNet: A Lightweight and Interpretable Framework for Sleep Staging Using Single-Channel EEG
• MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding
• Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
• A Primer on Quantum Machine Learning
• ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures
• Simulating Automotive Radar with Lidar and Camera Inputs
• StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction
• A Distributed Emulation Environment for In-Memory Computing Systems
• Model-Guided Microstimulation Steers Primate Visual Behavior
• FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking Systems
• ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
• Mouse vs. AI: A Neuroethological Benchmark for Visual Robustness and Neural Alignment
• From basic affordances to symbolic thought: A computational phylogenesis of biological intelligence.
• Fast weight programming and linear transformers: from machine learning to neurobiology
• What Neuroscience Can Teach AI About Learning in Continuously Changing Environments
• What does really matter in image goal navigation?
• Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
• HRRRCast: A Data-Driven Emulator for Regional Weather Forecasting at Convection-Allowing Scales
• Adopting a human developmental visual diet yields robust, shape-based AI vision
• Hierarchical Reasoning Model
• WorldVLA: Towards Autoregressive Action World Model
• ShapeEmbed: a self-supervised learning framework for 2D contour quantification
• FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping
• NeXtBrain: Combining local and global feature learning for brain tumor classification
• Facial albedo generation for 3D face reconstruction from a single image via a coarse-to-fine approach
• Transformers are Graph Neural Networks
• Are Statistical Methods Obsolete in the Era of Deep Learning? A Study of ODE Inverse Problems
• Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis
• Perception Encoder: The best visual embeddings are not at the output of the network
• In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?
• AssistanceZero: Scalably Solving Assistance Games
• NNN: Next-Generation Neural Networks for Marketing Measurement
• Accurate phenotyping of luminal A breast cancer in magnetic resonance imaging: A new 3D CNN approach
• RANa: Retrieval-Augmented Navigation
• NeuRaLaTeX: A machine learning library written in pure LaTeX
• Transformers without Normalization
• Shared Global and Local Geometry of Language Model Embeddings
• Advancements in automated nuclei segmentation for histopathology using you only look once-driven approaches: A systematic review
• Representational Similarity via Interpretable Visual Concepts
• ILIAS: Instance-Level Image retrieval At Scale
• Traveling Waves Integrate Spatial Information Through Time
• Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
• Distributional Diffusion Models with Scoring Rules
• The functional role of oscillatory dynamics in neocortical circuits: A computational perspective
• Rethinking Early Stopping: Refine, Then Calibrate
• The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
• TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
• An AI-Powered Autonomous Underwater System for Sea Exploration and Scientific Research
• LC4-DViT: Land-cover Creation for Land-cover Classification with Deformable Vision Transformer
• Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
• Distribution Matching Variational AutoEncoder
• The SpiNNaker2 chip: a many-core platform for flexible and scalable brain-inspired computing
• Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception
• Image Denoising Using Global and Local Circulant Representation
• Deep learning reveals cross-platform consistency in street view imagery for urban perception mapping
• Multi-label Classification with Panoptic Context Aggregation Networks
• SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context
• World Engine: Towards the Era of Post-Training for Autonomous Driving
• Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
• VGGT-Ω
• Rethinking Intrinsic Dimension Estimation in Neural Representations
• Glacier shrinkage in the Peruvian and Bolivian Andes from a deep learning-based multi-temporal inventory (2016–2024)
• Directly Constructing Low-Dimensional Solution Subspaces in Deep Neural Networks
• Diffusion priors enhanced velocity model building from time-lag images using a neural operator
• A new adaptive two-layer model for opinion spread in hypergraphs: parameter sensitivity and estimation
• Explainable Neural Inverse Kinematics for Obstacle-Aware Robotic Manipulation: A Comparative Analysis of IKNet Variants
• Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information
• LIMO: Low-Power In-Memory-Annealer and Matrix-Multiplication Primitive for Edge Computing
• Exploring Syn-to-Real Domain Adaptation for Military Target Detection
• Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing
• EIR: Enhanced Image Representations for Medical Report Generation
• Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning
• With Great Context Comes Great Prediction Power: Classifying Objects via Geo-Semantic Scene Graphs
• JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference
• Fusion or Confusion? Multimodal Complexity Is Not All You Need
• Learning Where to Focus: Density-Driven Guidance for Detecting Dense Tiny Objects
• Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
• Chessformer: A Unified Architecture for Chess Modeling
• ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
• Galaxy Zoo Evo: 1 million human-annotated images of galaxies
• Spatial Interpolation of Room Impulse Responses based on Deeper Physics-Informed Neural Networks with Residual Connections
• Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples
• Plug In, Grade Right: Psychology-Inspired AGIQA
• Investigating Deep Learning Models for Ejection Fraction Estimation from Echocardiography Videos
• EmoCtrl: Controllable Emotional Image Content Generation
• Bright 4B: Scaling Hyperspherical Learning for Segmentation in 3D Brightfield Microscopy
• DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization
• CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks
• A CNN-Based Malaria Diagnosis from Blood Cell Images with SHAP and LIME Explainability
• Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks
• iOS as Acceleration
• Joint Flow Matching for Generator-Consistent Classification
• Attention Residuals
• Greedy dynamical meta-learning
• Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
• Statistics of natural scenes shape contextual modulation in the visual cortex
• To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion
• AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
• When Rates Are Geometric: Rate-Certificate Transfer for Contact Splittings in Optimization
• Multi‐angle, cross‐domain fusion strategy enhances automated insect identification and hierarchical categorization: a case study on assassin bugs (Hemiptera: Reduviidae)
• Identifying Dolphin Whistle Producers With Deep Learning: Moving Beyond Signature Whistles
• Adaptive Acoustic Monitoring for Endangered Cook Inlet Beluga Whales in Complex Soundscapes
• End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration
• SE-MLP Model for Predicting Prior Acceleration Features in Penetration Signals
• PINNs for Electromagnetic Wave Propagation
• Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
• Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations
• 6G-Enabled Smart Railways
• How Does a Deep Neural Network Look at Lexical Stress?
• A Closer Look into Transformer-Based Code Intelligence Through Code Transformation: Challenges and Opportunities
• A Scoping Review of Machine Learning Applications in Power System Protection and Disturbance Management
• Advancing Marine Bioacoustics with Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection
• Adaptive Data Admission and Retention for Streaming Federated Learning
• The Semantic Least-Energy Principle: A Hypothesis for Intelligence
• Codebook Capacity Governs Perceptual Quality Across Resolutions in Hierarchical Discrete Video Compression
• Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging
• SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation
• EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability
• LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection
• DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing
• QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment
• Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning
• DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding
• The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation
• AI Empowered Communication and Radar Modulation Recognition: A Survey
• Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation
• Self-Supervised Learning from Noisy and Incomplete Data
• Automated Numerical Stability Analysis of Deep Learning Operators
• ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID
• MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks
• Room-Mediated Co-occurrence for Zero-Shot Object-Centric Semantic Navigation via Frontier Scoring
• AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition
• Balanced Soft mixture-of-expert model for Glaucoma Detection
• Raven: High-Recall Sequence Modeling with Sparse Memory Routing
• Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?
• Anti-Backdoor Coreset Selection via Cumulative Entropy
• Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors
• ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization
• Multiclass Classification without Labels via Posterior Simplex Geometry
• OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis
• PLATO: Pointer Learner for Agent and Task Openness
• Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension
• Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix
• Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting
• Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations
• Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs
• Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence
• Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
• Structural Preservation Governs Data Augmentation in Deep Learning-Based Laser Speckle Material Classification
• A Diagnostic Gap Framework for Evaluating Reconstruction Fidelity in Weakly Supervised Mammography
• CrossSpine: Multi-scale Cross-sequence Attention with Anatomical Priors for Automated Pfirrmann Grading
• Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment
• Benchmarking the Domain Gap: Model Selection Instability Under Domain Shift in Video Capsule Endoscopy
• Real-Time Semantic Segmentation with Optimized RetinaNet Architectures for Embedded Automotive Systems
• Explainable Multimodal Regression via Information Decomposition
• Histopathological Spectrum-Guided Prostate Stratification via Segmentation-Assisted Diagnostic Transformer
• Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model
• DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis
• T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
• DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification
• Quotient Tree Arithmetic: Deferred-Division Computation with Bounded Symbolic Depth and Cross-Subtree Cancellation
• Lexical discovery in unknown environments orchestrated by Large Language Models
• Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
• Toric code under antiferromagnetic isotropic Heisenberg interactions
• Latent Space Probing for Adult Content Detection in Video Generative Models
• Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation
• Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers
• Deep Delta Learning
• WiFo-M²: Empower Wireless Communications With Plug-and-Play Environment Sensing via Foundation Model
• Benchmarking deep learning models for Raman spectroscopy across open-source datasets
• AI for Mycetoma Diagnosis in Histopathological Images: The MICCAI 2024 Challenge
• LVLM-Aided Alignment of Task-Specific Vision Models
• Data relativistic uncertainty framework for low-illumination anime scenery image enhancement
• Am I Confused or Is This Confusing?: Deep Ensembles for ENSO Uncertainty Quantification
• LibContinual: A Comprehensive Library towards Realistic Continual Learning
• A Model of Causal Explanation on Neural Networks for Tabular Data
• Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective
• Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentation
• ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
• Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models
• First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
• Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
• Fixed-Budget Parameter-Efficient Training with Frozen Encoders Improves Multimodal Chest X-Ray Classification
• GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
• animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
• A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding
• GraviBERT: Transformer-based inference for gravitational-wave time series
• Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
• Neural Network-Assisted RIS Weight Optimization for Spatial Nulling in Distorted Reflector Antenna Systems
• UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
• A Learning Stability Profile for Finite-Dimensional Learning Dynamics
• Hierarchical Modeling Approach to Fast and Accurate Table Recognition
• Understanding Scaling Laws in Deep Neural Networks via Feature Learning Dynamics
• Language-Guided Grasp Detection with Coarse-to-Fine Learning for Robotic Manipulation
• Granular-ball Guided Masking: Structure-aware Data Augmentation
• X-ray Insights Unleashed: Pioneering the Enhancement of Multi-Label Long-Tail Data
• SLIDE: Simultaneous Model Downloading and Inference at the Wireless Network Edge
• ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
• Defending against adversarial attacks using mixture of experts
• NULLBUS: Multimodal Mixed-Supervision for Breast Ultrasound Segmentation via Nullable Global-Local Prompts
• Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
• TrashDet: Iterative Neural Architecture Search for Efficient Waste Detection
• Programmable Optical Spectrum Shapers as Computing Primitives for Accelerating Convolutional Neural Networks
• Multi-Grained Text-Guided Image Fusion for Multi-Exposure and Multi-Focus Scenarios
• Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow
• Neural Scaling Laws for Learning-based Identification of Nonlinear Systems
• CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images
• FedDPC : Handling Data Heterogeneity and Partial Client Participation in Federated Learning
• UbiQVision: Quantifying Uncertainty in XAI for Image Recognition
• Item Region-based Style Classification Network (IRSN): A Fashion Style Classifier Based on Domain Knowledge of Fashion Experts
• Progressive Learned Image Compression for Machine Perception
• Self-motion as a structural prior for coherent and robust formation of cognitive maps
• FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs
• WSD-MIL: Window Scale Decay Multiple Instance Learning for Whole Slide Image Classification
• TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation
• Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
• Target Classification for Integrated Sensing and Communication in Industrial Deployments
• LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• Vehicle-centric Perception via Multimodal Structured Pre-training
• Non-Contrast CT Esophageal Varices Grading through Clinical Prior-Enhanced Multi-Organ Analysis
• DK-STN: A Domain Knowledge Embedded Spatio-Temporal Network Model for MJO Forecast
• Deep Legendre Transform
• No Data? No Problem: Robust Vision-Tabular Learning with Missing Values
• Event Extraction in Large Language Model
• Multi-Modal Soccer Scene Analysis with Masked Pre-Training
• Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration
• DSTED: Decoupling Temporal Stabilization and Discriminative Enhancement for Surgical Workflow Recognition
• ReasonCD: A Multimodal Reasoning Large Model for Implicit Change-of-Interest Semantic Mining
• From Pixels to Predicates Structuring urban perception with scene graphs
• PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
• AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction
• D²Stream: Decoupled Dual-Stream Temporal-Speaker Interaction for Audio-Visual Speaker Detection
• Timely Parameter Updating in Over-the-Air Federated Learning
• AI-Driven Subcarrier-Level CQI Feedback
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
• DeepQuantum: A PyTorch-based Software Platform for Quantum Machine Learning and Photonic Quantum Computing
• DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis
• HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction
• VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion
• Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
• VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference
• Misbehavior Forecasting for Focused Autonomous Driving Systems Testing
• Decentralized GNSS at Global Scale via Graph-Aware Diffusion Adaptation
• ML Inference Scheduling with Predictable Latency
• Generating Risky Samples with Conformity Constraints via Diffusion Models
• Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts
• The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation
• Context-Aware Network Based on Multi-scale Spatio-temporal Attention for Action Recognition in Videos
• WoundNet-Ensemble: A Novel IoMT System Integrating Self-Supervised Deep Learning and Multi-Model Fusion for Automated, High-Accuracy Wound Classification and Healing Progression Monitoring
• NASTaR: NovaSAR Automated Ship Target Recognition Dataset
• PlantDiseaseNet-RT50: A Fine-tuned ResNet50 Architecture for High-Accuracy Plant Disease Detection Beyond Standard CNNs
• MeniMV: A Multi-view Benchmark for Meniscus Injury Severity Grading
• UniMPR: A Unified Framework for Multimodal Place Recognition with Heterogeneous Sensor Configurations
• On the Convergence Rate of LoRA Gradient Descent
• Towards Ancient Plant Seed Classification: A Benchmark Dataset and Baseline Model
• Spectral Discrepancy and Cross-modal Semantic Consistency Learning for Object Detection in Hyperspectral Image
• When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
• FedWiLoc: Federated Learning for Privacy-Preserving WiFi Indoor Localization
• SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusion
• ALIGN: Advanced Query Initialization with LiDAR-Image Guidance for Occlusion-Robust 3D Object Detection
• Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism
• A two-stream network with global-local feature fusion for bone age assessment
• FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability
• Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
• A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients
• InfinityEBSD : Metrics-Guided Infinite-Size EBSD Map Generation With Diffusion Models
• AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning
• AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
• MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image
• Learning Spatio-Temporal Feature Representations for Video-Based Gaze Estimation
• Self-Supervised Weighted Image Guided Quantitative MRI Super-Resolution
• A Unified Representation of Neural Networks Architectures
• Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
• Validation of Diagnostic Artificial Intelligence Models for Prostate Pathology in a Middle Eastern Cohort
• A Systematic Reproducibility Study of BSARec for Sequential Recommendation
• Domain-Aware Quantum Circuit for QML
• Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
• Cryptanalysis of Pseudorandom Error-Correcting Codes
• Towards Pixel-Wise Anomaly Location for High-Resolution PCBA via Self-Supervised Image Reconstruction
• WDFFU-Mamba: A Wavelet-guided Dual-attention Feature Fusion Mamba for Breast Tumor Segmentation in Ultrasound Images
• A Search for Binary Black Hole Mergers in LIGO O1-O3 Data with Convolutional Neural Networks
• Can Synthetic Images Serve as Effective and Efficient Class Prototypes?
• Enhancing AIGC Service Efficiency with Adaptive Multi-Edge Collaboration in A Distributed System
• Interpretable Similarity of Synthetic Image Utility
• Training Together, Diagnosing Better: Federated Learning for Collagen VI-Related Dystrophies
• Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
• FlowDet: Unifying Object Detection and Generative Transport Flows
• Few-Shot Fingerprinting Subject Re-Identification in 3D-MRI and 2D-X-Ray
• Exploiting Radio Frequency Fingerprints for Device Identification: Tackling Cross-receiver Challenges in the Source-data-free Scenario
• SARMAE: Masked Autoencoder for SAR Representation Learning
• Yuan-TecSwin: A text conditioned Diffusion model with Swin-transformer blocks
• Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation
• Continuized Nesterov Acceleration for Non-Convex Optimization
• XTC, A Research Platform for Optimizing AI Workload Operators
• Smile on the Face, Sadness in the Eyes: Bridging the Emotion Gap with a Multimodal Dataset of Eye and Facial Behaviors
• Hypernetworks That Evolve Themselves
• Graph Neural Networks for Source Detection: A Review and Benchmark Study
• Learning High-Quality Initial Noise for Single-View Synthesis with Diffusion Models
• A Multimodal Approach to Alzheimer's Diagnosis: Geometric Insights from Cube Copying and Cognitive Assessments
• Towards Closing the Domain Gap with Event Cameras
• Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
• GenAI-enabled Residual Motion Estimation for Energy-Efficient Semantic Video Communication
• Evaluation of deep learning architectures for wildlife object detection: A comparative study of ResNet and Inception
• Privacy Blur: Quantifying Privacy and Utility for Image Data Release
• Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
• Open Ad-hoc Categorization with Contextualized Feature Learning
• Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivatives
• See It Before You Grab It: Deep Learning-based Action Anticipation in Basketball
• MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging
• SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
• In Pursuit of Pixel Supervision for Visual Pre-training
• Artism: AI-Driven Dual-Engine System for Art Generation and Critique
• From Camera to World: A Plug-and-Play Module for Human Mesh Transformation
• Reducing Pilots in Channel Estimation with Predictive Foundation Models
• SCS-SupCon: Sigmoid-based Common and Style Supervised Contrastive Learning with Adaptive Decision Boundaries
• S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation
• From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning
• Packed Malware Detection Using Grayscale Binary-to-Image Representations
• Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models
• SemanticBridge - A Dataset for 3D Semantic Segmentation of Bridges and Domain Gap Analysis
• Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
• Automated Motion Artifact Check for MRI (AutoMAC-MRI): An Interpretable Framework for Motion Artifact Detection and Severity Assessment
• BBNet: accurate neural network emulator for primordial light element abundances
• Enhancing Alzheimer's Detection through Late Fusion of Multi-Modal EEG Features
• Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
• An updated efficient galaxy morphology classification model based on ConvNeXt encoding with UMAP dimensionality reduction
• EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting
• LADY: Linear Attention for Autonomous Driving Efficiency without Transformers
• Which Coauthor Should I Nominate in My 99 ICLR Submissions? A Mathematical Analysis of the ICLR 2026 Reciprocal Reviewer Nomination Policy
• ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architectures
• Cross-modal ultra-scale learning with tri-modalities of renal biopsy images for glomerular multi-disease auxiliary diagnosis
• Physics-driven human-like working memory outperforms digital networks in dynamic vision
• Borrowing from anything: A generalizable framework for reference-guided instance editing
• BEV-Patch-PF: Particle Filtering with BEV-Aerial Feature Matching for Off-Road Geo-Localization
• GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection
• Isolated Sign Language Recognition with Segmentation and Pose Estimation
• A Roadmap for Applying Graph Neural Networks to Numerical Data: Insights from Cementitious Materials
• Enhancing Visual Sentiment Analysis via Semiotic Isotopy-Guided Dataset Construction
• A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images
• AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation
• PruneX: A Hierarchical Communication-Efficient System for Distributed CNN Training with Structured Pruning
• FoodLogAthl-218: Constructing a Real-World Food Image Dataset Using Dietary Management Applications
• Relaying Signal When Monitoring Traffic: Double Use of Aerial Vehicles Towards Intelligent Low-Altitude Networking
• Enhancing Interpretability for Vision Models via Shapley Value Optimization
• Decoding Orbital Angular Momentum in Turbid Tissue-like Scattering Medium via Fourier-Domain Deep Learning
• Attention-Based Foundation Model for Quantum States
• Transfer learning reveals large discrepancies between air and land surface temperatures in cities
• Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation
• TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision Models
• SELECT: Detecting Label Errors in Real-world Scene Text Data
• Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers
• A Single Architecture for Representing Invariance Under Any Space Group
• Ensemble-Guided Distillation for Compact and Robust Acoustic Scene Classification on Edge Devices
• How Does Fourier Analysis Network Work? A Mechanism Analysis and a New Dual-Activation Layer Proposal
• SignIT: A Comprehensive Dataset and Multimodal Analysis for Italian Sign Language Recognition
• Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
• LitePT: Lighter Yet Stronger Point Transformer
• Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
• CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks
• DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
• Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
• The Renaissance of Expert Systems: Optical Recognition of Printed Chinese Jianpu Musical Scores with Lyrics
• Face Identity Unlearning for Retrieval via Embedding Dispersion
• Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• LeafTrackNet: A Deep Learning Framework for Robust Leaf Tracking in Top-Down Plant Phenotyping
• OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
• Time-aware UNet and super-resolution deep residual networks for spatial downscaling
• Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches
• TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading
• Leveraging Compression to Construct Transferable Bitrate Ladders
• Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery
• Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification
• Test-Time Modification: Inverse Domain Transformation for Robust Perception
• Robust Motion Generation using Part-level Reliable Data from Videos
• Selective Conformal Risk Control
• PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
• GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
• Federated Learning with Feedback Alignment
• FuXi-γ: Efficient Sequential Recommendation with Exponential-Power Temporal Encoder and Diagonal-Sparse Positional Mechanism
• Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
• Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
• TF-MCL: Time-frequency Fusion and Multi-domain Cross-Loss for Self-supervised Depression Detection
• StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
• GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
• Generative Spatiotemporal Data Augmentation
• DL³M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models
• Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots
• Optimized Architectures for Kolmogorov-Arnold Networks
• Hybrid algorithm combining matched filtering and convolutional neural networks for searching gravitational waves from binary black hole mergers
• Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
• Active learning potentials for first-principles phase diagrams using replica-exchange nested sampling
• WeDetect: Fast Open-Vocabulary Object Detection as Retrieval
• Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework
• A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction
• ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB
• Open Horizons: Evaluating Deep Models in the Wild
• A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
• SPDMark: Selective Parameter Displacement for Robust Video Watermarking
• Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model
• Non-Convex Federated Optimization under Cost-Aware Client Selection
• Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis
• Fully Inductive Node Representation Learning via Graph View Transformation
• ACCOR: Attention-Enhanced Complex-Valued Contrastive Learning for Occluded Object Classification Using mmWave Radar IQ Signals
• RadarFuseNet: Complex-Valued Attention-Based Fusion of IQ Time- and Frequency-Domain Radar Features for Classification Tasks
• Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using LiDAR HD Reference Data across Metropolitan France
• DREAM-B3P: Dual-Stream Transformer Network Enhanced by Feedback Diffusion Model for Blood-Brain Barrier Penetrating Peptide Prediction
• On the Dangers of Bootstrapping Generation for Continual Learning and Beyond
• ARC-AGI Without Pretraining
• Type II and Type III Solar Radio Burst Classification Using Transfer Learning
• On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
• Vision-Based Learning for Cyberattack Detection in Blockchain Smart Contracts and Transactions
• An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
• Back to the Baseline: Examining Baseline Effects on Explainability Metrics
• Weak-to-Strong Generalization Enables Fully Automated De Novo Training of Multi-head Mask-RCNN Model for Segmenting Densely Overlapping Cell Nuclei in Multiplex Whole-slice Brain Images
• Bhargava Cube--Inspired Quadratic Regularization for Structured Neural Embeddings
• SATMapTR: Satellite Image Enhanced Online HD Map Construction
• Surveillance Video-Based Traffic Accident Detection Using Transformer Architecture
• Task-Specific Distance Correlation Matching for Few-Shot Action Recognition
• CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks
• Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference
• Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
• Reliable Detection of Minute Targets in High-Resolution Aerial Imagery across Temporal Shifts
• AMBER: An Adaptive Multimodal Mask Transformer for Beam Prediction with Missing Modalities
• Weakly Supervised Tuberculosis Localization in Chest X-rays through Knowledge Distillation
• Bidirectional Normalizing Flow: From Data to Noise and Back
• PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction
• Graph Laplacian Transformer with Progressive Sampling for Prostate Cancer Grading
• Physics-Informed Learning of Microvascular Flow Models using Graph Neural Networks
• Blood Pressure Prediction for Coronary Artery Disease Diagnosis using Coronary Computed Tomography Angiography
• Neural personal sound zones with flexible bright zone control
• Learning to Split: A Reinforcement-Learning-Guided Splitting Heuristic for Neural Network Verification
• Thermal and Size Effects in Ferroelastic Domains by Machine Learning
• Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
• Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network
• Clustered Federated Learning with Hierarchical Knowledge Distillation
• Neural Collapse in Test-Time Adaptation
• Infusing Experimental Reality into Complex Many-Body Hamiltonians: The Observable-Constrained Variational Framework (OCVF)
• Independent Density Estimation
• Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
• Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
• Federated Domain Generalization with Latent Space Inversion
• Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis
• Self-Ensemble Post Learning for Noisy Domain Generalization
• Optimal transport unlocks end-to-end learning for single-molecule localization
• StainNet: Scaling Self-Supervised Foundation Models on Immunohistochemistry and Special Stains for Computational Pathology
• Sequence-to-Image Transformation for Sequence Classification Using Rips Complex Construction and Chaos Game Representation
• Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information
• Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
• ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects
• Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries
• Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers
• Straggler Tolerant and Resilient DL Training on Homogeneous GPUs
• CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
• Hands-on Evaluation of Visual Transformers for Object Recognition and Detection
• Masked Registration and Autoencoding of CT Images for Predictive Tibia Reconstruction
• NeuroSketch: An Effective Framework for Neural Decoding via Systematic Architectural Optimization
• QuanvNeXt: An end-to-end quanvolutional neural network for EEG-based detection of major depressive disorder
• Visual Categorization Across Minds and Models: Cognitive Analysis of Human Labeling and Neuro-Symbolic Integration
• Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook
• Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance
• SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
• GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model
• Contrastive Learning for Semi-Supervised Deep Regression with Generalized Ordinal Rankings from Spectral Seriation
• Accelerating high-order energy-stable discontinous Galerkin solver using auto-differentiation and neural networks
• Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks
• KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification
• Slow dynamics and magnon bound states in the 2D long-range quantum Ising model
• Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
• Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
• Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweighting
• Fully Decentralized Certified Unlearning
• The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
• When unlearning is free: leveraging low influence points to reduce computational costs
• Bi²MAC: Bimodal Bi-Adaptive Mask-Aware Convolution for Remote Sensing Pansharpening
• RLCNet: An end-to-end deep learning framework for simultaneous online calibration of LiDAR, RADAR, and Camera
• Fast-BEV++: Fast by Algorithm, Deployable by Design
• Spatially-extended Flow Phixer (SpeF-Phixer): A Spatially Extended φ-Mixing Framework for Gene Regulatory Causal Inference in Spatial Gene Field
• Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
• Instance-Aware Test-Time Segmentation for Continual Domain Shifts
• Identification of Deforestation Areas in the Amazon Rainforest Using Change Detection Models
• Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method
• HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
• CIP-Net: Continual Interpretable Prototype-based Network
• VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
• Relational Visual Similarity
• GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring
• Improving action classification with brain-inspired deep networks
• Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding
• Bandwidth-Aware Network Topology Optimization for Decentralized Learning
• Dictionary-Based Contrastive Learning for GNSS Jamming Detection
• Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
• GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring
• Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood
• How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline
• LogicCBMs: Logic-Enhanced Concept-Based Learning
• A Geometric Unification of Concept Learning with Concept Cones
• DeepAgent: A Dual Stream Multi Agent Fusion for Robust Multimodal Deepfake Detection
• Zero-Shot Textual Explanations via Translating Decision-Critical Features
• START: Spatial and Textual Learning for Chart Understanding
• Enhanced Chest Disease Classification Using an Improved CheXNet Framework with EfficientNetV2-M and Optimization-Driven Learning
• UnCageNet: Tracking and Pose Estimation of Caged Animal
• Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification
• R2MF-Net: A Recurrent Residual Multi-Path Fusion Network for Robust Multi-directional Spine X-ray Segmentation
• Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search
• Multi-view Pyramid Transformer: Look Coarser to See Broader
• DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
• Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology
• Balanced Learning for Domain Adaptive Semantic Segmentation
• SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification
• Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
• Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training
• Leveraging Pre-trained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-free Phase Holotomographic Microscopy
• Optimal and Diffusion Transports in Machine Learning
• ADAM Optimization with Adaptive Batch Selection
• JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms
• Rectifying Latent Space for Generative Single-Image Reflection Removal
• Selective Masking based Self-Supervised Learning for Image Semantic Segmentation
• XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association
• Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks
• Hierarchical Deep Learning for Diatom Image Classification: A Multi-Level Taxonomic Approach
• On Memory: A comparison of memory mechanisms in world models
• Embodied Referring Expression Comprehension in Human-Robot Interaction
• Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial Testbed
• Neural expressiveness for beyond importance model compression
• Automated Deep Learning Estimation of Anthropometric Measurements for Preparticipation Cardiovascular Screening
• When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition
• 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
• A Perception CNN for Facial Expression Recognition
• Phase-OTDR Event Detection Using Image-Based Data Transformation and Deep Learning
• CLUENet: Cluster Attention Makes Neural Networks Have Eyes
• Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
• Language-driven Fine-grained Retrieval
• Approximate Multiplier Induced Error Propagation in Deep Neural Networks
• Greedy Alignment Principle for Optimizer Selection
• SPOOF: Simple Pixel Operations for Out-of-Distribution Fooling
• DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classification
• AQUA-Net: Adaptive Frequency Fusion and Illumination Aware Network for Underwater Image Enhancement
• Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception
• Synset Signset Germany: a Synthetic Dataset for German Traffic Sign Recognition
• A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
• Variance Matters: Improving Domain Adaptation via Stratified Sampling
• LDLT L-Lipschitz Network: Generalized Deep End-To-End Lipschitz Network Construction
• Scaling and Transferability of Annealing Strategies in Large Language Model Training
• HSCP: A Two-Stage Spectral Clustering Framework for Resource-Constrained UAV Identification
• Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation
• Curvature-Regularized Variational Autoencoder for 3D Scene Reconstruction from Sparse Depth
• Learning High-Fidelity Cloth Animation via Skinning-Free Image Transfer
• Wasserstein distance based semi-supervised manifold learning and application to GNSS multi-path detection
• VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation
• DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
• Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation
• University Building Recognition Dataset in Thailand for the mission-oriented IoT sensor system
• Performance Evaluation of Deep Learning for Tree Branch Segmentation in Autonomous Forestry Systems
• RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design
• Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
• Rep Smarter, Not Harder: AI Hypertrophy Coaching with Wearable Sensors and Edge Neural Networks
• Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image
• CNN on `Top': In Search of Scalable &amp; Lightweight Image-based Jet Taggers
• DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation
• When Do Domain-Specific Foundation Models Justify Their Cost? A Systematic Evaluation Across Retinal Imaging Tasks
• Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks
• SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
• STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
• Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation
• Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
• Recurrent Neural Networks with Linear Structures for Electricity Price Forecasting
• Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
• Infrared UAV Target Tracking with Dynamic Feature Refinement and Global Contextual Attention Knowledge Distillation
• Research on Brain Tumor Classification Method Based on Improved ResNet34 Network
• MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
• FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring
• Searching for binary black hole mergers with deep learning in Advanced LIGO's third observing run
• Open Set Face Forgery Detection via Dual-Level Evidence Collection
• CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
• Generalized Event Partonomy Inference with Structured Hierarchical Predictive Learning
• Predicting parameters of a model cuprate superconductor using machine learning
• State Space Models for Bioacoustics: A comparative Evaluation with Transformers
• Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
• Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
• Comparison of neural network training strategies for the simulation of dynamical systems
• HieroGlyphTranslator: Automatic Recognition and Translation of Egyptian Hieroglyphs to English
• EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification
• LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
• Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustness
• Multi-Scale Visual Prompting for Lightweight Small-Image Classification
• MKSNet: Advanced Small Object Detection in Remote Sensing Imagery with Multi-Kernel and Dual Attention Mechanisms
• FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features
• SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
• HBFormer: A Hybrid-Bridge Transformer for Microtumor and Miniature Organ Segmentation
• DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions
• Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching
• Cross-Space Synergy: A Unified Framework for Multimodal Emotion Recognition in Conversation
• NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation
• Hierarchical Attention for Sparse Volumetric Anomaly Detection in Subclinical Keratoconus
• Network of Theseus (like the ship)
• Single-Round Scalable Analytic Federated Learning
• DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision
• Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?
• PyroFocus: A Deep Learning Approach to Real-Time Wildfire Detection in Multispectral Remote Sensing Imagery
• Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems
• Decision Tree Embedding by Leaf-Means
• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
• Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
• GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
• ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics
• BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection
• FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE
• Layout Anything: One Transformer for Universal Room Layout Estimation
• Defense That Attacks: How Robust Models Become Better Attackers
• A Framework for Causal Concept-based Model Explanations
• Conformal Correction for Efficiency May be at Odds with Entropy
• A Discrete Neural Operator with Adaptive Sampling for Surrogate Modeling of Parametric Transient Darcy Flows in Porous Media
• From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
• Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
• Leveraging generative adversarial networks with spatially adaptive denormalization for multivariate stochastic seismic data inversion
• Drainage: A Unifying Framework for Addressing Class Uncertainty
• TGDD: Trajectory Guided Dataset Distillation with Balanced Distribution
• Microbenchmarking NVIDIA's Blackwell Architecture: An in-depth Architectural Analysis
• Equilibrium Propagation Without Limits
• Context-Enriched Contrastive Loss: Enhancing Presentation of Inherent Sample Connections in Contrastive Learning Framework
• Data-Centric Visual Development for Self-Driving Labs
• Improved Mean Flows: On the Challenges of Fastforward Generative Models
• Physical ID-Transfer Attacks against Multi-Object Tracking via Adversarial Trajectory
• SARL: Spatially-Aware Self-Supervised Representation Learning for Visuo-Tactile Perception
• OpenREAD: Reinforced Open-Ended Reasoning for End-to-End Autonomous Driving with LLM-as-Critic
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch
• Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
• Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
• Learned Image Compression for Earth Observation: Implications for Downstream Segmentation Tasks
• Dual Randomized Smoothing: Beyond Global Noise Variance
• On the Unreasonable Effectiveness of Last-layer Retraining
• Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks
• A unified framework for geometry-independent operator learning in cardiac electrophysiology simulations
• DB-KAUNet: An Adaptive Dual Branch Kolmogorov-Arnold UNet for Retinal Vessel Segmentation
• ViT³: Unlocking Test-Time Training in Vision
• Toward Content-based Indexing and Retrieval of Head and Neck CT with Abscess Segmentation
• Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures
• Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks
• ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark
• Directed evolution algorithm drives neural prediction
• InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
• FishDetector-R1: Unified MLLM-Based Framework with Reinforcement Fine-Tuning for Weakly Supervised Fish Detection, Segmentation, and Counting
• FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection
• DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling
• Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
• OmniFD: A Unified Model for Versatile Face Forgery Detection
• Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysis
• Generalized Medical Phrase Grounding
• PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting
• Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
• PAGen: Phase-guided Amplitude Generation for Domain-adaptive Object Detection
• Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
• VFM-ISRefiner: Towards Better Adapting Vision Foundation Models for Interactive Segmentation of Remote Sensing Images
• Partially Shared Concept Bottleneck Models
• 3D Affordance Keypoint Detection for Robotic Manipulation
• ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices
• Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models
• Structured Context Learning for Generic Event Boundary Detection
• GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework
• SelfAI: Building a Self-Training AI System with LLM Agents
• Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement
• Vision Transformer for Classification of UAV and Helicopters Using Micro-Doppler Spectrograms in Surveillance Radar
• S²-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting
• An Interpretable Operator-Learning Model for Electric Field Profile Reconstruction in Discharges Based on the EFISH Method
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
• "Why the face?": Exploring Robot Error Detection Using Instrumented Bystander Reactions
• Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
• MANTA: Physics-Informed Generalized Underwater Object Tracking
• SimScale: Learning to Drive via Real-World Simulation at Scale
• PointCNN++: Performant Convolution on Native Points
• GAVINA: flexible aggressive undervolting for bit-serial mixed-precision DNN acceleration
• Communication-Computation Pipeline Parallel Split Learning over Wireless Edge Networks
• Estimating the Event-Related Potential from Few EEG Trials
• Evaluating the Clinical Impact of Generative Inpainting on Bone Age Estimation
• Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring
• Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognition
• Stable-Drift: A Patient-Aware Latent Drift Replay Method for Stabilizing Representations in Continual Learning
• ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
• CNN-Based Framework for Pedestrian Age and Gender Classification Using Far-View Surveillance in Mixed-Traffic Intersections
• Adaptive Dataset Quantization: A New Direction for Dataset Pruning
• SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
• A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees
• Bandit Guided Submodular Curriculum for Adaptive Subset Selection
• InstanceV: Instance-Level Video Generation
• Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records
• Leveraging Textual Compositional Reasoning for Robust Change Captioning
• Time Series Forecasting via Direct Per-Step Probability Distribution Modeling
• Closing the Generalization Gap in Parameter-efficient Federated Edge Learning
• U Net LSTM with incremental time-stepping for robust long-horizon unsteady flow prediction
• GazeTrack: High-Precision Eye Tracking Based on Regularization and Spatial Computing
• Hard Spatial Gating for Precision-Driven Brain Metastasis Segmentation: Addressing the Over-Segmentation Paradox in Deep Attention Networks
• AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection
• Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
• IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance
• SHIC-XE: Viewpoint-Invariant Explainability via Dense 2D-3D Correspondences: an Application to Equine Pain Recognition
• Combining Projected Uncertainty for Self-Supervised Visual Odometry: From Two-Frame to Multi-Frame
• A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral data
• Rethinking Cross-Generator Image Forgery Detection through DINOv3
• Angle-Optimized Partial Disentanglement for Multimodal Emotion Recognition in Conversation
• DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization
• Semi-Supervised Contrastive Learning with Orthonormal Prototypes
• AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices
• INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts
• FADiff: Fusion-Aware Differentiable Optimization for DNN Scheduling on Tensor Accelerators
• HandyLabel: Towards Post-Processing to Real-Time Annotation Using Skeleton Based Hand Gesture Recognition
• FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
• UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation
• ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopy
• Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation
• Stacked Ensemble of Fine-Tuned CNNs for Knee Osteoarthritis Severity Grading
• HyperST: Hierarchical Hyperbolic Learning for Spatial Transcriptomics Prediction
• MRI-Based Brain Age Estimation with Supervised Contrastive Learning of Continuous Representation
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving
• The Age-specific Alzheimer 's Disease Prediction with Characteristic Constraints in Nonuniform Time Span
• Self-Paced Learning for Images of Antinuclear Antibodies
• SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning
• Biomimetic Metamaterial-based Interface for Decoding Heterogeneous Mechanodermal Activity
• Uni-Hema: Unified Model for Digital Hematopathology
• CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation
• Lost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation
• Dynamical Implicit Neural Representations
• PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation
• Shift-Equivariant Complex-Valued Convolutional Neural Networks
• RISC-V Based TinyML Accelerator for Depthwise Separable Convolutions in Edge AI
• DeepRFTv2: Kernel-level Learning for Image Deblurring
• RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
• Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network
• MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection
• Beyond Realism: Learning the Art of Expressive Composition with StickerNet
• AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios
• Guaranteed Optimal Compositional Explanations for Neurons
• Open Vocabulary Compositional Explanations for Neuron Alignment
• Pre-train to Gain: Robust Learning Without Clean Labels
• Effects of Initialization Biases on Deep Neural Network Training Dynamics
• Intriguing Properties of Dynamic Sampling Networks
• Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification
• 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
• Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
• The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting
• Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection
• Automated Monitoring of Cultural Heritage Artifacts Using Semantic Segmentation
• Adam Simplified: Bias Correction Debunked
• Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations
• HVAdam: A Full-Dimension Adaptive Optimizer
• DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection
• Advancing Image Classification with Discrete Diffusion Classification Modeling
• Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization
• XiCAD: Camera Activation Detection in the Da Vinci Xi User Interface
• DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning
• Text-guided Controllable Diffusion for Realistic Camouflage Images Generation
• Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
• PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
• Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning
• RankOOD -- Class Ranking-based Out-of-Distribution Detection
• GazeProphetV2: Head-Movement-Based Gaze Prediction Enabling Efficient Foveated Rendering on Mobile VR
• Stragglers Can Contribute More: Uncertainty-Aware Distillation for Asynchronous Federated Learning
• MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
• Low-Resolution Editing is All You Need for High-Resolution Editing
• Intelligent Image Search Algorithms Fusing Visual Large Models
• LiMT: A Multi-task Liver Image Benchmark Dataset
• Distilling Cross-Modal Knowledge via Feature Disentanglement
• Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
• Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generation
• Learning to Clean: Reinforcement Learning for Noisy Label Correction
• Annotation-Free Class-Incremental Learning
• AdaCap: An Adaptive Contrastive Approach for Small-Data Neural Networks
• HybriDLA: Hybrid Generation for Document Layout Analysis
• On the Limits of Momentum in Decentralized and Federated Optimization
• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
• Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environments
• An Anatomy Aware Hybrid Deep Learning Framework for Lung Cancer Tumor Stage Classification
• Enhancing Conformal Prediction via Class Similarity
• CellFMCount: A Fluorescence Microscopy Dataset, Benchmark, and Methods for Cell Counting
• A CNN-Based Technique to Assist Layout-to-Generator Conversion for Analog Circuits
• DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling
• ModHiFi: Identifying High Fidelity predictive components for Model Modification
• Development of a fully deep learning model to improve the reproducibility of sector classification systems for predicting unerupted maxillary canine likelihood of impaction
• EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction
• Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation
• When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP
• DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection
• Graph-based 3D Human Pose Estimation using WiFi Signals
• Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling
• Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting
• MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design
• Cross-Domain Generalization of Multimodal LLMs for Global Photovoltaic Assessment
• AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
• Leveraging Adversarial Learning for Pathological Fidelity in Virtual Staining
• Scalable Vision-Guided Crop Yield Estimation
• Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection
• Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
• Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
• MapRF: Weakly Supervised Online HD Map Construction via NeRF-Guided Self-Training
• AutoMAS: A Generic Multi-Agent System for Algorithm Self-Adaptation in Wireless Networks
• Sampling Control for Imbalanced Calibration in Semi-Supervised Learning
• Re-Key-Free, Risky-Free: Adaptable Model Usage Control
• NI-Tex: Non-isometric Image-based Garment Texture Generation
• OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting
• Higgs Production Classifier using Weak Supervision
• Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
• Multimodal Real-Time Anomaly Detection and Industrial Applications
• Single Image to High-Quality 3D Object via Latent Features
• Exploring Surround-View Fisheye Camera 3D Object Detection
• Neural Geometry Image-Based Representations with Optimal Transport (OT)
• Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
• LMSeg: an end-to-end geometric message-passing network on barycentric dualgraphs for large-scale landscape mesh segmentation
• Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?
• Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
• LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space
• Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models
• CoD: A Diffusion Foundation Model for Image Compression
• Dendritic Convolution for Noise Image Recognition
• AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
• Bayesian-based Online Label Shift Estimation with Dynamic Dirichlet Priors
• CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning
• From Simulations to Surveys: Domain Adaptation for Galaxy Observations
• PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
• Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion
• Shape-Adapting Gated Experts: Dynamic Expert Routing for Colonoscopic Lesion Segmentation
• NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
• Exploring Weak-to-Strong Generalization for CLIP-based Classification
• AIA-UltraNeRF:Acoustic-Impedance-Aware Neural Radiance Field with Hash Encodings for Robotic Ultrasound Reconstruction and Localization
• Z-Space: A Multi-Agent Tool Orchestration Framework for Enterprise-Grade LLM Automation
• DE-KAN: A Kolmogorov Arnold Network with Dual Encoder for accurate 2D Teeth Segmentation
• UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
• Hyperspectral Variational Autoencoders for Joint Data Compression and Component Extraction
• Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection
• Stro-VIGRU: Defining the Vision Recurrent-Based Baseline Model for Brain Stroke Classification
• AFT: Appearance-Based Feature Tracking for Markerless and Training-Free Shape Reconstruction of Soft Robots
• Early Lung Cancer Diagnosis from Virtual Follow-up LDCT Generation via Correlational Autoencoder and Latent Flow Matching
• Nested Unfolding Network for Real-World Concealed Object Segmentation
• Compact neural networks for astronomy with optimal transport bias correction
• SFHand: A Streaming Framework for Language-guided 3D Hand Forecasting and Embodied Manipulation
• Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
• Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning
• VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection
• Learning Rate Scheduling with Matrix Factorization for Private Training
• Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning
• Comprehensive Design Space Exploration for Tensorized Neural Network Hardware Accelerators
• Understanding Private Learning From Feature Perspective
• Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation
• L1 Sample Flow for Efficient Visuomotor Learning
• Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds
• State and Scene Enhanced Prototypes for Weakly Supervised Open-Vocabulary Object Detection
• A multi-view contrastive learning framework for spatial embeddings in risk modelling
• Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
• REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion
• SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration
• An Artificial Intelligence Framework for Measuring Human Spine Aging Using MRI
• Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions
• Self-Supervised Learning by Curvature Alignment
• MemIntelli: A Generic End-to-End Simulation Framework for Memristive Intelligent Computing
• Quantum Masked Autoencoders for Vision Learning
• SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering
• ReBaPL: Repulsive Bayesian Prompt Learning
• QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
• Dual-Path Knowledge-Augmented Contrastive Alignment Network for Spatially Resolved Transcriptomics
• Layer-wise Weight Selection for Power-Efficient Neural Network Acceleration
• Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs
• RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
• Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels
• DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction
• A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection
• Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning
• Enhancing Adversarial Transferability through Block Stretch and Shrink
• Person Recognition in Aerial Surveillance: A Decade Survey
• MRI Super-Resolution with Deep Learning: A Comprehensive Survey
• Membership Inference Attacks Beyond Overfitting
• Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations
• Formal Abductive Latent Explanations for Prototype-Based Networks
• Broad stochastic configuration residual learning system for norm-convergent universal approximation
• Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin
• Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
• ODE-ViT: Plug &amp; Play Attention Layer from the Generalization of the ViT as an Ordinary Differential Equation
• Flow and Depth Assisted Video Prediction with Latent Transformer
• TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models
• MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features
• Memory-DD: A Low-Complexity Dendrite-Inspired Neuron for Temporal Prediction Tasks
• Green Distributed AI Training: Orchestrating Compute Across Renewable-Powered Micro Datacenters
• Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
• Descend or Rewind? Stochastic Gradient Descent Unlearning
• LLMs-based Augmentation for Domain Adaptation in Long-tailed Food Datasets
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
• Scenario-Aware Control of Segmented Ladder Bus: Design and FPGA Implementation
• GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving
• SpectralTrain: A Universal Framework for Hyperspectral Image Classification
• CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation
• An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs
• Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
• Real-Time 3D Object Detection with Inference-Aligned Learning
• A Spatial Semantics and Continuity Perception Attention for Remote Sensing Water Body Change Detection
• DiffuDepGrasp: Diffusion-based Depth Noise Modeling Empowers Sim2Real Robotic Grasping
• MambaIO: Global-Coordinate Inertial Odometry for Pedestrians via Multi-Scale Frequency-Decoupled Modeling
• Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
• What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity
• Instruction-Based Coordination of Heterogeneous Processing Units for Acceleration of DNN Inference
• A Review of Machine Learning for Cavitation Intensity Recognition in Complex Industrial Systems
• FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
• SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
• A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturing
• D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
• ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
• STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Detection
• What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
• Robust Bayesian Optimisation with Unbounded Corruptions
• Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs
• SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
• Enforcing hidden physics in physics-informed neural networks
• Eq.Bot: Enhance Robotic Manipulation Learning via Group Equivariant Canonicalization
• GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
• TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection
• Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval
• BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?
• Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans
• WiCo-MG: Wireless Channel Foundation Model for Multipath Generation via Synesthesia of Machines
• Non-Convex Self-Concordant Functions: Practical Algorithms and Complexity Analysis
• Latent space analysis and generalization to out-of-distribution data
• Toward Complete Merger Identification at Cosmic Noon with Deep Learning
• Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation
• Efficient Large-Scale Learning of Minimax Risk Classifiers
• Artificial intelligence approaches for energy-efficient laser cutting machines
• GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis
• B-Rep Distance Functions (BR-DF): How to Represent a B-Rep Model by Volumetric Distance Functions?
• M²OE²-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers
• SLAM-AGS: Slide-Label Aware Multi-Task Pretraining Using Adaptive Gradient Surgery in Computational Cytology
• Parameter Aware Mamba Model for Multi-task Dense Prediction
• Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
• Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals
• Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
• Sigil: Server-Enforced Watermarking in U-Shaped Split Federated Learning via Gradient Injection
• Cranio-ID: Graph-Based Craniofacial Identification via Automatic Landmark Annotation in 2D Multi-View X-rays
• Stage Aware Diagnosis of Diabetic Retinopathy via Ordinal Regression
• Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning
• HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation
• Weight Variance Amplifier Improves Accuracy in High-Sparsity One-Shot Pruning
• Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning
• ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
• Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision
• Unifying Convolution and Attention via Convolutional Nearest Neighbors
• Compute-in-Memory Implementation of State Space Models for Event Sequence Processing
• SAE-MCVT: A Real-Time and Scalable Multi-Camera Vehicle Tracking Framework Powered by Edge Computing
• Training-free Detection of AI-generated images via Cropping Robustness
• Robust Client-Server Watermarking for Split Federated Learning
• Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
• Alpha Divergence Losses for Biometric Verification
• Power Homotopy for Zeroth-Order Non-Convex Optimizations
• Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks
• Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problems
• Mapping the Vanishing and Transformation of Urban Villages in China
• Hardware optimization on Android for inference of AI models
• TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing
• InfoDecom: Decomposing Information for Defending against Privacy Leakage in Split Inference
• Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping
• Semi-Supervised Multi-Task Learning for Interpretable Quality As- sessment of Fundus Images
• Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges
• Hybrid-Domain Adaptative Representation Learning for Gaze Estimation
• End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer
• Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection
• Birth of a Painting: Differentiable Brushstroke Reconstruction
• Uncertainty-aware Physics-informed Neural Networks for Robust CARS-to-Raman Signal Reconstruction
• Region-Point Joint Representation for Effective Trajectory Similarity Learning
• Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning
• MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images
• ResAlignNet: A Data-Driven Approach for INS/DVL Alignment
• Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
• Decoupling Scene Perception and Ego Status: A Multi-Context Fusion Approach for Enhanced Generalization in End-to-End Autonomous Driving
• Monocular 3D Lane Detection via Structure Uncertainty-Aware Network with Curve-Point Queries
• H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
• Simple Lines, Big Ideas: Towards Interpretable Assessment of Human Creativity from Drawings
• Learned Adaptive Kernels for High-Fidelity Image Downscaling
• Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems
• HIT-ROCKET: Hadamard-vector Inner-product Transformer for ROCKET
• CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation
• MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers
• LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
• GeoPl@ntNet: A Platform for Exploring Essential Biodiversity Variables
• Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning
• Efficiently Training A Flat Neural Network Before It has been Quantizated
• Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation
• Attention-Enhanced Convolutional Autoencoder and Structured Delay Embeddings for Weather Prediction
• FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
• OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding
• Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
• CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
• DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
• Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion
• MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
• Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
• MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation
• VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving
• MSLoRA: Multi-Scale Low-Rank Adaptation via Attention Reweighting
• HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models
• Segmented Exponent Alignment and Dynamic Wordline Activation for Floating-Point Analog CIM Macros
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• Leveraging Quantum-Based Architectures for Robust Diagnostics
• AGGRNet: Selective Feature Extraction and Aggregation for Enhanced Medical Image Classification
• Model Inversion Attack Against Deep Hashing
• Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?
• Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering
• Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function
• Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis
• Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
• Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks
• Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning
• Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning
• Intelligent Collaborative Optimization for Rubber Tyre Film Production Based on Multi-path Differentiated Clipping Proximal Policy Optimization
• BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
• VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation
• Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis
• From Classification to Cross-Modal Understanding: Leveraging Vision-Language Models for Fine-Grained Renal Pathology
• Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs
• FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention
• A Deep Learning Framework for Thyroid Nodule Segmentation and Malignancy Classification from Ultrasound Images
• CVChess: A Deep Learning Framework for Converting Chessboard Images to Forsyth-Edwards Notation
• Quantifying and Improving Adaptivity in Conformal Prediction through Input Transformations
• Enhancing Photon Identification with Neural Network Methods
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net
• Coordinate Descent for Network Linearization
• D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
• Virtual Width Networks
• Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy
• Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays
• MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation
• Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
• LEMUR: Large scale End-to-end MUltimodal Recommendation
• Heterogeneous Complementary Distillation
• YOLO-Drone: An Efficient Object Detection Approach Using the GhostHead Network for Drone Images
• Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
• Dynamic Temperature Scheduler for Knowledge Distillation
• When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
• Dynamic LRP-Based Pruning for CNNs in Data-Scarce Transfer Learning: Suppressing Cascading Accuracy Degradation
• GFT: Graph Feature Tuning for Efficient Point Cloud Analysis
• Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
• Moirai 2.0: When Less Is More for Time Series Forecasting
• On the Detectability of Active Gradient Inversion Attacks in Federated Learning
• Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance
• Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
• Domain Adaptation for Camera-Specific Image Characteristics using Shallow Discriminators
• RoboBenchMart: Benchmarking Robots in Retail Environment
• TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
• Soiling detection for Advanced Driver Assistance Systems
• Fairness-Aware Deepfake Detection: Leveraging Dual-Mechanism Optimization
• Physics-informed Machine Learning for Static Friction Modeling in Robotic Manipulators Based on Kolmogorov-Arnold Networks
• 2.5D Transformer: An Efficient 3D Seismic Interpolation Method without Full 3D Training
• AdaptViG: Adaptive Vision GNN with Exponential Decay Gating
• EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services
• ConSurv: Multimodal Continual Learning for Survival Analysis
• CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage
• SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
• Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
• Continuum Dropout for Neural Differential Equations
• ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
• Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
• Data Heterogeneity and Forgotten Labels in Split Federated Learning
• Generalizing PDE Emulation with Equation-Aware Neural Operators
• SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation
• CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition
• Federated Learning for Pediatric Pneumonia Detection: Enabling Collaborative Diagnosis Without Sharing Patient Data
• SuperRivolution: Fine-Scale Rivers from Coarse Temporal Satellite Imagery
• AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events
• Deep Learning for Metabolic Rate Estimation from Biosignals: A Comparative Study of Architectures and Signal Selection
• Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues
• Iterated Population Based Training with Task-Agnostic Restarts
• PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh Recovery
• RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation
• Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding
• Blurred Encoding for Trajectory Representation Learning
• Free-Boundary Quasiconformal Maps via a Least-squares Operator in Diffeomorphism Optimization
• TransactionGPT
• Improving VisNet for Object Recognition
• Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting
• Improve Contrastive Clustering Performance by Multiple Fusing-Augmenting ViT Blocks
• Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
• FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
• Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression
• A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers
• Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
• Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification
• Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient
• SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology
• CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing
• Why Should the Server Do It All?: A Scalable, Versatile, and Model-Agnostic Framework for Server-Light DNN Inference over Massively Distributed Clients via Training-Free Intermediate Feature Compression
• RDTE-UNet: A Boundary and Detail Aware UNet for Precise Medical Image Segmentation
• A Generative Adversarial Approach to Adversarial Attacks Guided by Contrastive Language-Image Pre-trained Model
• Measuring the Intrinsic Dimension of Earth Representations
• REASON: Probability map-guided dual-branch fusion framework for gastric content assessment
• Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
• SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
• NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
• Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation
• RAPTR: Radar-based 3D Pose Estimation using Transformer
• Extreme Model Compression with Structured Sparsity at Low Precision
• Mitigating Negative Flips via Margin Preserving Training
• H-Model: Dynamic Neural Architectures for Adaptive Processing
• SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering
• Rethinking Explanation Evaluation under the Retraining Scheme
• X-IONet: Cross-Platform Inertial Odometry Network with Dual-Stage Attention
• Data-Driven Discovery of Feature Groups in Clinical Time Series
• Fill the gaps: continuous in time interpolation of fluid dynamical simulations
• Evaluating Gemini LLM in Food Image-Based Recipe and Nutrition Description with EfficientNet-B4 Visual Backbone
• Towards Provably Unlearnable Examples via Bayes Error Optimisation
• Pixel-level Quality Assessment for Oriented Object Detection
• GAMA: A Neural Neighborhood Search Method with Graph-aware Multi-modal Attention for Vehicle Routing Problem
• WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
• VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
• Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks
• ProbSelect: Stochastic Client Selection for GPU-Accelerated Compute Devices in the 3D Continuum
• BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services
• From Sequential to Recursive: Enhancing Decision-Focused Learning with Bidirectional Feedback
• High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
• Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving
• Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition
• Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation
• ReIDMamba: Learning Discriminative Features with Visual State Space Model for Person Re-Identification
• Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
• Multi-objective Hyperparameter Optimization in the Age of Deep Learning
• The Impact of Longitudinal Mammogram Alignment on Breast Cancer Risk Assessment
• Data Descriptions from Large Language Models with Influence Estimation
• Visual Bridge: Universal Visual Perception Representations Generating
• MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection
• A General Method for Proving Networks Universal Approximation Property
• VEDA: 3D Molecular Generation via Variance-Exploding Diffusion with Annealing
• Deep Learning Analysis of Prenatal Ultrasound for Identification of Ventriculomegaly
• DI3CL: Contrastive Learning With Dynamic Instances and Contour Consistency for SAR Land-Cover Classification Foundation Model
• Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
• Operational machine learning for remote spectroscopic detection of CH₄ point sources
• Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement
• CAVER: Curious Audiovisual Exploring Robot
• Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
• Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?
• Verifying rich robustness properties for neural networks
• CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video
• Revisiting the Neural Tangent Kernel: the role of large width and depth
• Integrating Epigenetic and Phenotypic Features for Biological Age Estimation in Cancer Patients via Multimodal Learning
• BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective
• HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving
• Pandar128 dataset for lane line detection
• GoCkpt: Gradient-Assisted Multi-Step overlapped Checkpointing for Efficient LLM Training
• Fair Bayesian Data Selection via Generalized Discrepancy Measures
• Performance Decay in Deepfake Detection: The Limitations of Training on Outdated Data
• From Attribution to Action: Jointly ALIGNing Predictions and Explanations
• Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers
• MI-to-Mid Distilled Compression (M2M-DC): An Hybrid-Information-Guided-Block Pruning with Progressive Inner Slicing Approach to Model Compression
• Minimum Width of Deep Narrow Networks for Universal Approximation
• PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks
• K-Stain: Keypoint-Driven Correspondence for H&amp;E-to-IHC Virtual Staining
• Probably Approximately Global Robustness Certification
• Flexible Concept Bottleneck Model
• REOcc: Camera-Radar Fusion with Radar Feature Enrichment for 3D Occupancy Prediction
• Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
• Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision
• Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search
• Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
• Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation
• FPGA-Accelerated RISC-V ISA Extensions for Efficient Neural Network Inference on Edge Devices
• Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models
• DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization
• SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection
• SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images
• LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation
• Achieving Fairness Without Harm via Selective Demographic Experts
• Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
• Temporal-Guided Visual Foundation Models for Event-Based Vision
• VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving
• One-Shot Knowledge Transfer for Scalable Person Re-Identification
• ReMoD: Rethinking Modality Contribution in Multimodal Stance Detection via Dual Reasoning
• Online Learning of Modular Bayesian Deep Receivers: Single-Step Adaptation with Streaming Data
• Radio AGN feedback sustains quiescence only in a minority of massive galaxies
• Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
• Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registration
• Global Multiple Extraction Network for Low-Resolution Facial Expression Recognition
• LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting
• EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion
• MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation
• Sign language recognition from skeletal data using graph and recurrent neural networks
• Environment-Aware MIMO Channel Estimation in Pilot-Constrained Upper Mid-Band Systems
• Towards Unified AI-Driven Fracture Mechanics: The Extended Deep Energy Method (XDEM)
• An Efficient Gradient-Aware Error-Bounded Lossy Compressor for Federated Learning
• SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning
• Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration
• Climate Downscaling of Tropical Cyclone Intensity using Deep Learning
• The Causal Round Trip: Generating Authentic Counterfactuals by Eliminating Information Loss
• NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling
• MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and Classification
• From Linear Probing to Joint-Weighted Token Hierarchy: A Foundation Model Bridging Global and Cellular Representations in Biomarker Detection
• NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
• MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
• Order-Level Attention Similarity Across Language Models: A Latent Commonality
• Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidance
• MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery
• Deep Progressive Training: scaling up depth capacity of zero/one-layer models
• Learning Fourier shapes to probe the geometric world of deep neural networks
• The Future of Fully Homomorphic Encryption System: from a Storage I/O Perspective
• Unveiling the Training Dynamics of ReLU Networks through a Linear Lens
• Beta Distribution Learning for Reliable Roadway Crash Risk Assessment
• What's on Your Plate? Inferring Chinese Cuisine Intake from Wearable IMUs
• Accelerating metamaterial topology optimization using deep super-resolution networks
• Environment Agnostic Goal-Conditioning, A Study of Reward-Free Autonomous Learning
• Automatic detection of CMEs using synthetically-trained Mask R-CNN
• Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers
• Saliency-Guided Domain Adaptation for Left-Hand Driving in Autonomous Steering
• Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
• DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale
• A MATLAB tutorial on deep feature extraction combined with chemometrics for analytical applications
• Comparative Study of CNN Architectures for Binary Classification of Horses and Motorcycles in the VOC 2008 Dataset
• AIM: Software and Hardware Co-design for Architecture-level IR-drop Mitigation in High-performance PIM
• MacroNav: Multi-Task Context Representation Learning Enables Efficient Navigation in Unknown Environments
• Probing the Probes: Methods and Metrics for Concept Alignment
• Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
• An Efficient Algorithm for Learning-Based Visual Localization
• Active Domain Adaptation for mmWave-based HAR via Renyi Entropy-based Uncertainty Estimation
• FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI
• Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment
• MedDChest: A Content-Aware Multimodal Foundational Vision Model for Thoracic Imaging
• SynQuE: Estimating Synthetic Dataset Quality Without Annotations
• Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
• Event Reconstruction for Radio-Based In-Ice Neutrino Detectors with Neural Posterior Estimation
• A Transferable Machine Learning Approach to Predict Quantum Circuit Parameters for Electronic Structure Problems
• Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection
• nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN
• MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs
• Efficient Neural Networks with Discrete Cosine Transform Activations
• Extended Physics Informed Neural Network for Hyperbolic Two-Phase Flow in Porous Media
• Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning
• Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
• Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
• Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels
• Decentralized Federated Learning with Distributed Aggregation Weight Optimization
• Decoupled Entropy Minimization
• Cross-Modal Alignment via Variational Copula Modelling
• SAAIPAA: Optimizing aspect-angles-invariant physical adversarial attacks on SAR target recognition models
• Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response
• An Augmentation Overlap Theory of Contrastive Learning
• Scalable Autoregressive Deep Surrogates for Dendritic Microstructure Dynamics
• Contextual Role Modulates Object Representational Geometry in the Human Brain
• Conditional Diffusion Model-Enabled Scenario-Specific Neural Receivers for Superimposed Pilot Schemes
• Archaeological Classification of Small Datasets Using Meta- and Transfer Learning Methods: A Case Study on Hittite Stele Fragments
• Learning with less: label-efficient land cover classification at very high spatial resolution using self-supervised deep learning
• Generative Hints
• UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs
• Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization
• Improving Unlearning with Model Updates Probably Aligned with Gradients
• Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
• MammoClean: Toward Reproducible and Bias-Aware AI in Mammography through Dataset Harmonization
• Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster
• GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection
• Differentiable Hierarchical Visual Tokenization
• Collaborative Attention and Consistent-Guided Fusion of MRI and PET for Alzheimer's Disease Diagnosis
• OmniField: Conditioned Neural Fields for Robust Multimodal Spatiotemporal Learning
• MM-UNet: Morph Mamba U-shaped Convolutional Networks for Retinal Vessel Segmentation
• PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks
• CFL: On the Use of Characteristic Function Loss for Domain Alignment in Machine Learning
• HAGI++: Head-Assisted Gaze Imputation and Generation
• A Proof of Learning Rate Transfer under μP
• TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
• Machine and Deep Learning for Indoor UWB Jammer Localization
• Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
• Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms
• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
• Motion-Robust Multimodal Fusion of PPG and Accelerometer Signals for Three-Class Heart Rhythm Classification
• Lightweight ResNet-Based Deep Learning for Photoplethysmography Signal Quality Assessment
• Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
• Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection
• Parameter Interpolation Adversarial Training for Robust Image Classification
• Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack
• Validating Deep Models for Alzheimer's 18F-FDG PET Diagnosis Across Populations: A Study with Latin American Data
• Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
• Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach
• EPARA: Parallelizing Categorized AI Inference in Edge Clouds
• Digital Twin of Aerosol Jet Printing
• Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
• Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction
• OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
• Weakly Supervised Pneumonia Localization from Chest X-Rays Using Deep Neural Network and Grad-CAM Explanations
• ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
• Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum
• Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection
• Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
• Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
• Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
• A Multimodal Framework for Depression Detection during Covid-19 via Harvesting Social Media: A Novel Dataset and Method
• Towards Automated Petrography
• TRISKELION-1: Unified Descriptive-Predictive-Generative AI
• STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology
• Enhancing Frequency Forgery Clues for Diffusion-Generated Image Detection
• Melanoma Classification Through Deep Ensemble Learning and Explainable AI
• Machine learning-based cloud resource allocation algorithms: a comprehensive comparative review
• Approximating Young Measures With Deep Neural Networks
• An Efficient and Generalizable Transfer Learning Method for Weather Condition Detection on Ground Terminals
• Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challenges
• Vision Transformer for Robust Occluded Person Reidentification in Complex Surveillance Scenes
• VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images
• Towards robust quantitative photoacoustic tomography via learned iterative methods
• FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
• MeisenMeister: A Simple Two Stage Pipeline for Breast Cancer Classification on MRI
• CASR-Net: An Image Processing-focused Deep Learning-based Coronary Artery Segmentation and Refinement Network for X-ray Coronary Angiogram
• Rethinking Robust Adversarial Concept Erasure in Diffusion Models
• ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction
• Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation
• FedSM: Robust Semantics-Guided Feature Mixup for Bias Reduction in Federated Learning with Long-Tail Data
• Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting
• Soft Task-Aware Routing of Experts for Equivariant Representation Learning
• SpecAware: A Spectral-Content Aware Foundation Model for Unifying Multi-Sensor Learning in Hyperspectral Remote Sensing Mapping
• SilhouetteTell: Practical Video Identification Leveraging Blurred Recordings of Video Subtitles
• AFM-Net: Advanced Fusing Hierarchical CNN Visual Priors with Global Sequence Modeling for Remote Sensing Image Scene Classification
• Exploring Landscapes for Better Minima along Valleys
• Exact Terminal Condition Neural Network for American Option Pricing Based on the Black-Scholes-Merton Equations
• Lightweight CNN Model Hashing with Higher-Order Statistics and Chaotic Mapping for Piracy Detection and Tamper Localization
• Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation
• A Retrospect to Multi-prompt Learning across Vision and Language
• Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition
• ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning
• DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
• FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
• End-to-End Framework Integrating Generative AI and Deep Reinforcement Learning for Autonomous Ultrasound Scanning
• Merlin L48 Spectrogram Dataset
• NOMAD -- Navigating Optimal Model Application to Datastreams
• Gaussian Combined Distance: A Generic Metric for Object Detection
• Calibration Across Layers: Understanding Calibration Evolution in LLMs
• AD-SAM: Fine-Tuning the Segment Anything Vision Foundation Model for Autonomous Driving Perception
• Incremental Human-Object Interaction Detection with Invariant Relation Representation Learning
• Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
• Semantic Frame Aggregation-based Transformer for Live Video Comment Generation
• An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning
• FlowQ-Net: A Generative Framework for Automated Quantum Circuit Design
• Improving Classification of Occluded Objects through Scene Context
• MSAD: A Deep Dive into Model Selection for Time series Anomaly Detection
• Hybrid Physical-Neural Simulator for Fast Cosmological Hydrodynamics
• SA²Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging
• On Measuring Localization of Shortcuts in Deep Networks
• MIREDO: MIP-Driven Resource-Efficient Dataflow Optimization for Computing-in-Memory Accelerator
• SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
• A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy Grading
• Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning
• Leveraging Large-Scale Face Datasets for Deep Periocular Recognition via Ocular Cropping
• Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances
• ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
• MV-MLM: Bridging Multi-View Mammography and Language for Breast Cancer Diagnosis and Risk Prediction
• Security Risk of Misalignment between Text and Image in Multi-modal Model
• Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
• Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomography
• Multi-Representation Attention Framework for Underwater Bioacoustic Denoising and Recognition
• Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry
• CHIPSIM: A Co-Simulation Framework for Deep Learning on Chiplet-Based Systems
• Reading Radio from Camera: Visually-Grounded, Lightweight, and Interpretable RSSI Prediction
• Active Learning with Task-Driven Representations for Messy Pools
• VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
• Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
• Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets
• Adaptive End-to-End Transceiver Design for NextG Pilot-Free and CP-Free Wireless Systems
• A Deep Learning Framework for Multi-Operator Learning: Architectures and Approximation Theory
• Lightweight Federated Learning in Mobile Edge Computing with Statistical and Device Heterogeneity Awareness
• MMEdge: Accelerating On-device Multimodal Inference via Pipelined Sensing and Encoding
• When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
• Image Quality Dependent Degradation for AI Systems
• PowerScale: Energy-Efficient Geo-Distributed Model Training with Federated Datacenter Power
• TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors
• Deep Stacked Networks with Residual Polishing for Image Inpainting
• Binary Stochastic Representations for Large Multi-class Classification
• Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
• Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations
• Interpretable Image-Level Acne Severity Grading via EfficientNet-B0 Transfer Learning and Grad-CAM
• HERMES: A Hybrid Ensemble for Head-and-Neck Tumor Segmentation, TN Staging, and Recurrence-Free Survival on PET/CT
• Calibrating the Digital Twin Channel: Statistics-Consistent Sim-to-Lab Adaptation for W-Band Industrial OFDM Links
• FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
• A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
• Decoupled Visual Processing: Efficient Multimodal Adaptation via Modality-Specific Transformer Substitution
• Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification
• Classification of Disease from Lungs X-ray Images using VGG16, VGG19 and ResNet50 Models
• StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation
• Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition
• A Hierarchical Framework for Graph Structure Learning in Histopathology Image Classification
• Lilith: Backdoor Generalization under Training-Inference Trigger Shift
• DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving
• HeteroPROPMT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
• Shape-Based Inductive Bias for Glioma Grading from Tumor Contours
• Gradually Updated Neural Networks for Large-Scale Image Recognition
• Mixture-of-Depths Attention
• Consistent Accelerated Inference via Confident Adaptive Transformers
• Achieving Human Parity on Automatic Chinese to English News Translation
• Automatic Liver Segmentation from CT Images Using Deep Learning Algorithms: A Comparative Study
• Open Source Face Recognition Performance Evaluation Package
• Fusion++: Volumetric Object-Level SLAM
• Analysing object detectors from the perspective of co-occurring object\n categories
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
• Distance-aware Soft Prompt Learning for Multimodal Valence-Arousal Estimation
• B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
• And the Bit Goes Down: Revisiting the Quantization of Neural Networks
• Stable Tensor Neural Networks for Rapid Deep Learning
• Efficient Sparse-Winograd Convolutional Neural Networks
• Learning Digital Camera Pipeline for Extreme Low-Light Imaging
• Unsupervised Single Image Deraining with Self-supervised Constraints
• Soft Calibration Objectives for Neural Networks
• Visual Data Augmentation through Learning
• AI and Image
• Dominant Controls on Preferential Flow and Their Implications for Future Soil Water Fluxes
• Understanding Infographics through Textual and Visual Tag Prediction
• Analyzing Image Encoder Choices and Graph Homophily in GCN Frameworks for Breast Ultrasound Classification
• First-Order Preconditioning via Hypergradient Descent
• Superposition disentanglement of neural representations reveals hidden alignment
• Calibrated Uncertainty Sampling for Active Learning
• Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
• GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis
• Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
• MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
• Reducing Noise in GAN Training with Variance Reduced Extragradient
• PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification
• FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
• Improve Unsupervised Pretraining for Few-label Transfer
• A one-armed CNN for exoplanet detection from light curves
• Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
• InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry
• SeGAN: Segmenting and Generating the Invisible
• Deep Feature Flow for Video Recognition
• Knowledge Adaptation for Efficient Semantic Segmentation
• Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
• Learnable Pooling Methods for Video Classification
• Granular Motor State Monitoring of Free Living Parkinson's Disease Patients via Deep Learning
• Mapping small reservoirs across Brazil from 1984 to 2025
• Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss
• Enforcing Reasoning in Visual Commonsense Reasoning
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
• Large-scale empirical tuning and comparison of default optimizers for variational inference
• Scene-Centric Unsupervised Video Panoptic Segmentation
• ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
• Optimality of Sub-network Laplace Approximations: New Results and Methods
• Convolutional neural networks in Vis–NIR chemometrics: From contradiction to conditional design
• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
• Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
• LR-to-HR Face Hallucination with an Adversarial Progressive\n Attribute-Induced Network
• Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
• MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space
• Generative Partition Networks for Multi-Person Pose Estimation
• Natural Adversarial Examples
• Hyperspectral image classification using CNN: Application to industrial food packaging
• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• OpenMAP-BrainAge: generalizable and interpretable brain age predictor from MRI
• A Theory of Generalization in Deep Learning
• Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
• Recurrent 3D Pose Sequence Machines
• GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
• Dynamic Few-Shot Visual Learning without Forgetting
• Motion-Appearance Co-Memory Networks for Video Question Answering
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
• Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
• Deep Gradient Projection Networks for Pan-sharpening
• Representation range needs for 16-bit neural network training
• SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing
• On Periodic Functions as Regularizers for Quantization of Neural Networks
• Deep Spatial Regression Model for Image Crowd Counting
• FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection
• BlockDrop: Dynamic Inference Paths in Residual Networks
• Detecting abnormal events in video using Narrowed Normality Clusters
• Zero-shot World Models Are Developmentally Efficient Learners
• SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision
• Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
• Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
• RaCo: Ranking and Covariance for Practical Learned Keypoints
• Diagnosing Error in Temporal Action Detectors
• Generative Modeling via Drifting
• Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition
• Fourier-Based GAN Fingerprint Detection using ResNet50
• Robust and Generalizable Atrial Fibrillation Detection from ECG Using Time-Frequency Fusion and Supervised Contrastive Learning
• Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance
• Generating metamers of human scene understanding
• High-throughput Verticillium wilt detection in cotton: A comparative study of faster R-CNN and YOLOv11
• Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models
• Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
• Generalizable and scalable protein stability prediction with rewired protein generative models
• Contrastive learning enhances fairness in pathology artificial intelligence systems
• Deep learning technique for plant disease classification and pest detection and model explainability elevating agricultural sustainability
• EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning
• BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
• GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Prediction
• IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
• Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
• Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision
• Classifier Enhancement Using Extended Context and Domain Experts for Semantic Segmentation
• Adversarially Robust Quantum Transfer Learning
• Cosmic Background Removal with Deep Neural Networks in SBND
• A Study on Inference Latency for Vision Transformers on Mobile Devices
• Selective Diabetic Retinopathy Screening with Accuracy-Weighted Deep Ensembles and Entropy-Guided Abstention
• NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies
• Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
• Breast Cancer VLMs: Clinically Practical Vision-Language Train-Inference Models
• A Quadratic Actor Network for Model-Free Reinforcement Learning
• Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
• SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving
• Pyramid Scene Parsing Network
• FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
• Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
• MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
• Eigenfunction Extraction for Ordered Representation Learning
• All in one timestep: Enhancing Sparsity and Energy efficiency in Multi-level Spiking Neural Networks
• Exploring Federated Learning for Thermal Urban Feature Segmentation -- A Comparison of Centralized and Decentralized Approaches
• Time-Embedded Algorithm Unrolling for Computational MRI
• SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
• Deep-Learning-Empowered Programmable Topolectrical Circuits
• HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series
• When are radiology reports useful for training medical image classifiers?
• A Domain Adaptive Position Reconstruction Method for Time Projection Chamber based on Deep Neural Network
• Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning
• UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
• Global Chlorophyll-a Retrieval algorithm from Sentinel 2 Using Residual Deep Learning and Novel Machine Learning Water Classification
• Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation
• CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image Segmentation
• Deep Feature Optimization for Enhanced Fish Freshness Assessment
• Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
• EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
• Self-supervised Synthetic Pretraining for Inference of Stellar Mass Embedded in Dense Gas
• Differential Privacy: Gradient Leakage Attacks in Federated Learning Environments
• UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations
• SLOTH: Lightweight Detection and Localization of On-Chip Fail-Slow Failures for DNN Accelerators
• Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
• Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
• Learning from History: A Retrieval-Augmented Framework for Spatiotemporal Prediction
• Mitigating Negative Transfer via Reducing Environmental Disagreement
• MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
• ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
• An efficient probabilistic hardware architecture for diffusion-like models
• Exploring an image-based b-jet tagging method using convolution neural networks
• Unmasking Facial DeepFakes: A Robust Multiview Detection Framework for Natural Images
• LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
• Improving the Straight-Through Estimator with Zeroth-Order Information
• Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Decoder-Only Transformers
• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
• Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
• IAEmu: Learning Galaxy Intrinsic Alignment Correlations
• RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
• Lung Cancer Classification from CT Images Using ResNet
• Super-recognizers sample visual information of superior computational value for facial recognition
• Image Categorization and Search via a GAT Autoencoder and Representative Models
• Connectome-Guided Automatic Learning Rates for Deep Networks
• Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
• Chebyshev Moment Regularization (CMR): Condition-Number Control with Moment Shaping
• Robust and Generalizable Background Subtraction on Images of Calorimeter Jets using Unsupervised Generative Learning
• Localising under the drape: proprioception in the era of distributed surgical robotic system
• iPac: Incorporating Intra-image Patch Context into Graph Neural Networks for Medical Image Classification
• CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification
• VIKING: Deep variational inference with stochastic projections
• PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
• Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
• One-Timestep is Enough: Achieving High-performance ANN-to-SNN Conversion via Scale-and-Fire Neurons
• An Efficient Remote Sensing Super Resolution Method Exploring Diffusion Priors and Multi-Modal Constraints for Crop Type Mapping
• Interpretable Tile-Based Classification of Paclitaxel Exposure
• Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
• Model-Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn't the Right One
• Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
• VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
• Approaching Domain Generalization with Embeddings for Robust Discrimination and Recognition of RF Communication Signals
• Implicit Modeling for Transferability Estimation of Vision Foundation Models
• Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
• Reliable Robotic Task Execution in the Face of Anomalies
• Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data
• Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI
• Softmax is 1/2-Lipschitz: A tight bound across all ℓ_p norms
• LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation
• Capsule Network-Based Multimodal Fusion for Mortgage Risk Assessment from Unstructured Data Sources
• How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
• From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators
• Bi-Encoder Contrastive Learning for Fingerprint and Iris Biometrics
• DNN-based Signal Processing for Liquid Argon Time Projection Chambers
• Transforming volcanic monitoring: A dataset and benchmark for onboard volcano activity detection
• MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
• What Do We Understand About Convolutional Networks?
• SeeDNorm: Self-Rescaled Dynamic Normalization
• Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting
• SemiETPicker: Fast and Label-Efficient Particle Picking for CryoET Tomography Using Semi-Supervised Learning
• Estimation of Fireproof Structure Class and Construction Year for Disaster Risk Assessment
• Block Coordinate Descent for Neural Networks Provably Finds Global Minima
• Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
• PSScreen V2: Partially Supervised Multiple Retinal Disease Screening
• Prediction-Powered Semi-Supervised Learning with Online Power Tuning
• From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
• An End-to-End Generative Diffusion Model for Heavy-Ion Collisions
• Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
• Mutual Information guided Visual Contrastive Learning
• C-arm Guidance: A Self-supervised Approach To Automated Positioning During Stroke Thrombectomy
• PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching
• Stable neural networks and connections to continuous dynamical systems
• DiffusionLane: Diffusion Model for Lane Detection
• Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
• Audio Frequency-Time Dual Domain Evaluation on Depression Diagnosis
• GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation
• Simplifying Knowledge Transfer in Pretrained Models
• Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation
• LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction
• FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis
• MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
• Frequentist Validity of Epistemic Uncertainty Estimators
• Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents: Pathways and Paradigms
• Caption-Driven Explainability: Probing CNNs for Bias via CLIP
• LiteDiff
• From Black-box to Causal-box: Towards Building More Interpretable Models
• Revisiting Orbital Minimization Method for Neural Operator Decomposition
• AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
• Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
• S3OD: Towards Generalizable Salient Object Detection with Synthetic Data
• MATrack: Efficient Multiscale Adaptive Tracker for Real-Time Nighttime UAV Operations
• AURASeg: Attention Guided Upsampling with Residual Boundary-Assistive Refinement for Drivable-Area Segmentation
• FrameShield: Adversarially Robust Video Anomaly Detection
• GRAP-MOT: Unsupervised Graph-based Position Weighted Person Multi-camera Multi-object Tracking in a Highly Congested Space
• ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping
• Towards Explainable Personalized Recommendations by Learning from Users' Photos
• OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
• Large Language Models as Model Organisms for Human Associative Learning
• Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
• Why Registration Quality Matters: Enhancing sCT Synthesis with IMPACT-Based Registration
• Cavity Duplexer Tuning with 1d Resnet-like Neural Networks
• 3D-DETNet: a Single Stage Video-Based Vehicle Detector
• Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts
• SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
• Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
• Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
• Long-tailed Species Recognition in the NACTI Wildlife Dataset
• Confounding Robust Deep Reinforcement Learning: A Causal Approach
• Multimodal Detection of Fake Reviews using BERT and ResNet-50
• Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset
• Generative Point Tracking with Flow Matching
• Lens Model Accuracy in the Expected LSST Lensed AGN Sample
• HybridSOMSpikeNet: A Deep Model with Differentiable Soft Self-Organizing Maps and Spiking Dynamics for Waste Classification
• H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
• Convergence Analysis of SGD under Expected Smoothness
• Hardware-Aware DNN Compression for Homogeneous Edge Devices
• Predicting the 3D microstructure of SOFC anodes from 2D SEM images using stochastic microstructure modeling and CNNs
• Revisiting Model Stitching to Compare Neural Representations
• Multimodal Negative Learning
• PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
• Do Vision Models Encode Object-Level Semantic Relatedness? A Cognitive Psychology-Inspired Benchmark
• Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey
• Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
• What Does It Take to Build a Performant Selective Classifier?
• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
• Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency
• Dynamic Weight Adjustment for Knowledge Distillation: Leveraging Vision Transformer for High-Accuracy Lung Cancer Detection and Real-Time Deployment
• HGraphScale: Hierarchical Graph Learning for Autoscaling Microservice Applications in Container-based Cloud Computing
• Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process
• GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection
• Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
• Deep Discriminative Clustering Analysis
• Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval
• Reliable and Reproducible Demographic Inference for Fairness in Face Analysis
• Revisiting Knowledge Distillation: The Hidden Role of Dataset Size
• FutrTrack: A Camera-LiDAR Fusion Transformer for 3D Multiple Object Tracking
• The Tail Tells All: Estimating Model-Level Membership Inference Vulnerability Without Reference Models
• Vision-language models learn the geometry of human perceptual space
• From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem
• BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models
• Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism
• Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
• DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
• Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
• Exploring "Many in Few" and "Few in Many" Properties in Long-Tailed, Highly-Imbalanced IC Defect Classification
• AutoMT: A Multi-Agent LLM Framework for Automated Metamorphic Testing of Autonomous Driving Systems
• Revisiting the Relation Between Robustness and Universality
• Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach
• Modeling Turn-Taking with Semantically Informed Gestures
• A Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIP
• Calibration and Discrimination Optimization Using Clusters of Learned Representation
• Knowledge Distillation of Uncertainty using Deep Latent Factor Model
• MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation
• A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models
• Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition
• HAMLOCK: HArdware-Model LOgically Combined attacK
• Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges
• TinyUSFM: Towards Compact and Efficient Ultrasound Foundation Models
• Enhancing Early Alzheimer Disease Detection through Big Data and Ensemble Few-Shot Learning
• Transformed Multi-view 3D Shape Features with Contrastive Learning
• Online Handwritten Signature Verification Based on Temporal-Spatial Graph Attention Transformer
• FrogDeepSDM: Improving Frog Counting and Occurrence Prediction Using Multimodal Data and Pseudo-Absence Imputation
• Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
• A Novel Combined Optical Flow Approach for Comprehensive Micro-Expression Recognition
• Towards Strong Certified Defense with Universal Asymmetric Randomization
• RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training
• Controllable Machine Unlearning via Gradient Pivoting
• Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
• QCFace: Image Quality Control for boosting Face Representation &amp; Recognition
• Denoising Complex Covariance Matrices with Hybrid ResNet and Random Matrix Theory: Cryptocurrency Portfolio Applications
• Explainable Deep Learning in Medical Imaging: Brain Tumor and Pneumonia Detection
• Wavelet-based GAN Fingerprint Detection using ResNet50
• Weight Decay may matter more than muP for Learning Rate Transfer in Practice
• Ninja Codes: Neurally Generated Fiducial Markers for Stealthy 6-DoF Tracking
• A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation
• SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery
• Learning Task-Agnostic Representations through Multi-Teacher Distillation
• Beyond the Pipeline: Analyzing Key Factors in End-to-End Deep Learning for Historical Writer Identification
• Training Keyword Spotters with Limited and Synthesized Speech Data
• Improving Micro-Expression Recognition with Phase-Aware Temporal Augmentation
• Deformable Convolutional Networks
• Towards In-Situ Failure Assessment: Deep Learning on DIC Results for Laminated Composites
• C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression
• CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution
• Instance-level Human Parsing via Part Grouping Network
• Latent-Info and Low-Dimensional Learning for Human Mesh Recovery and Parallel Optimization
• Hybrid Deep Learning Framework for Enhanced Diabetic Retinopathy Detection: Integrating Traditional Features with AI-driven Insights
• Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents
• AWSPNet: Attention-based Dual-Tree Wavelet Scattering Prototypical Network for MIMO Radar Target Recognition and Jamming Suppression
• S2AP: Score-space Sharpness Minimization for Adversarial Pruning
• Learning Human-Object Interaction as Groups
• Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning
• AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering
• ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection
• MCANet: A Coherent Multimodal Collaborative Attention Network for Advanced Modulation Recognition in Adverse Noisy Environments
• Uncertainty Estimation by Flexible Evidential Deep Learning
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
• FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning
• POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
• FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
• Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning
• MARS-M: When Variance Reduction Meets Matrices
• Automatic Classification of Circulating Blood Cell Clusters based on Multi-channel Flow Cytometry Imaging
• Enhancing Cross-Patient Generalization in AI-Based Parkinson s Disease Detection
• Towards 3D Objectness Learning in an Open World
• Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning
• Quantifying Multimodal Imbalance: A GMM-Guided Adaptive Loss for Audio-Visual Learning
• How human–AI feedback loops alter human perceptual, emotional and social judgements
• RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation
• SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
• MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning
• Exploration via Feature Perturbation in Contextual Bandits
• Facial Expression-based Parkinson's Disease Severity Diagnosis via Feature Fusion and Adaptive Class Balancing
• Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise
• Deep Neural Network extraction of Unpolarized Transverse Momentum Distributions
• Pano2CAD: Room Layout From A Single Panorama Image
• 2D₃D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection
• GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
• Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training
• Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement
• Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring
• Fair and Interpretable Deepfake Detection in Videos
• Mapping Hidden Heritage: Self-supervised Pre-training on High-Resolution LiDAR DEM Derivatives for Archaeological Stone Wall Detection
• GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models
• ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification
• Annotation-Efficient Universal Honesty Alignment
• EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification
• NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
• Conditional Synthetic Live and Spoof Fingerprint Generation
• STARK: Strategic Team of Agents for Refining Kernels
• State estimation in homogeneous isotropic turbulence using super-resolution with a 4DVar training algorithm
• Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
• ReefNet: A Large scale, Taxonomically Enriched Dataset and Benchmark for Hard Coral Classification
• An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision
• SAMOSA: Sharpness Aware Minimization for Open Set Active learning
• EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
• Symmetric Entropy-Constrained Video Coding for Machines
• Proto-Former: Unified Facial Landmark Detection by Prototype Transformer
• An Efficient Semantic Segmentation Decoder for In-Car or Distributed Applications
• Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis
• The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications
• All You Need is One: Capsule Prompt Tuning with a Single Vector
• Geospatial Machine Learning Libraries
• AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
• Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions
• Learning a Generalized Model for Substation Level Voltage Estimation in Distribution Networks
• EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices
• GENESIS: A Generative Model of Episodic-Semantic Interaction
• Deep Neural ODE Operator Networks for PDEs
• Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation
• Dynamic Recalibration in LiDAR SLAM: Integrating AI and Geometric Methods with Real-Time Feedback Using INAF Fusion
• OpenEDS: Open Eye Dataset
• Semantic segmentation with coarse annotations
• Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation
• TeamFormer: Shallow Parallel Transformers with Progressive Approximation
• VO-DP: Semantic-Geometric Adaptive Diffusion Policy for Vision-Only Robotic Manipulation
• Automated C-Arm Positioning via Conformal Landmark Localization
• RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
• Magnitude and Phase-based Feature Fusion Using Co-attention Mechanism for Speaker recognition
• VM-BeautyNet: A Synergistic Ensemble of Vision Transformer and Mamba for Facial Beauty Prediction
• ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
• Hyperparameter Optimization and Reproducibility in Deep Learning Model Training
• Fourier Transform Multiple Instance Learning for Whole Slide Image Classification
• Extending Temporal Disturbance Estimations For Magnetic Anomaly Navigation and Mapping
• A solution to generalized learning from small training sets found in infant repeated visual experiences of individual objects
• Adiabatic transport of neural network quantum states
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning
• RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
• C4D: 4D Made from 3D through Dual Correspondences
• OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
• CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects
• A Multi-Task Deep Learning Framework for Skin Lesion Classification, ABCDE Feature Quantification, and Evolution Simulation
• LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
• Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
• Geometric Moment Alignment for Domain Adaptation via Siegel Embeddings
• EuroMineNet: A Multitemporal Sentinel-2 Benchmark for Spatiotemporal Mining Footprint Analysis in the European Union (2015-2024)
• Causality Enhancement for Cross-Domain Recommendation
• SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
• Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding
• First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training
• Selective Labeling with False Discovery Rate Control
• Boosted Attention: Leveraging Human Attention for Image Captioning
• EcoScaleNet: A Lightweight Multi Kernel Network for Long Sequence 12 lead ECG Classification
• Towards Generalist Intelligence in Dentistry: Vision Foundation Models for Oral and Maxillofacial Radiology
• Vision Mamba for Permeability Prediction of Porous Media
• Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review
• Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
• BinCtx: Multi-Modal Representation Learning for Robust Android App Behavior Detection
• A Multi-domain Image Translative Diffusion StyleGAN for Iris Presentation Attack Detection
• TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening
• CLEAR: Causal Learning Framework For Robust Histopathology Tumor Detection Under Out-Of-Distribution Shifts
• PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis
• Spiking Neural Network Architecture Search: A Survey
• When Flatness Does (Not) Guarantee Adversarial Robustness
• LOTA: Bit-Planes Guided AI-Generated Image Detection
• Global-focal Adaptation with Information Separation for Noise-robust Transfer Fault Diagnosis
• Beat Tracking as Object Detection
• ViTacGen: Robotic Pushing with Vision-to-Touch Generation
• Nondeterminism-Aware Optimistic Verification for Floating-Point Neural Networks
• Conditional Clifford-Steerable CNNs with Complete Kernel Basis for PDE Modeling
• Revisiting Video Saliency: A Large-scale Benchmark and a New Model
• Axial Neural Networks for Dimension-Free Foundation Models
• Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
• Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
• Improving Visual Recommendation on E-commerce Platforms Using Vision-Language Models
• Removing Cost Volumes from Optical Flow Estimators
• UniVector: Unified Vector Extraction via Instance-Geometry Interaction
• Prompt-based Adaptation in Large-scale Vision Models: A Survey
• Approximate Bilevel Graph Structure Learning for Histopathology Image Classification
• DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models
• Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
• Counting Hallucinations in Diffusion Models
• Transformer-based Scalable Beamforming Optimization via Deep Residual Learning
• Beyond Pixels: A Differentiable Pipeline for Probing Neuronal Selectivity in 3D
• DP-TTA: Test-time Adaptation for Transient Electromagnetic Signal Denoising via Dictionary-driven Prior Regularization
• BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity
• Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion
• XD-RCDepth: Lightweight Radar-Camera Depth Estimation with Explainability-Aligned and Distribution-Aware Distillation
• FlashWorld: High-quality 3D Scene Generation within Seconds
• Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs
• DocVQA: A Dataset for VQA on Document Images
• Computationally Efficient Neural Receivers via Axial Self-Attention
• CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
• AnyUp: Universal Feature Upsampling
• KoALA: KL-L0 Adversarial Detector via Label Agreement
• Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization
• On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation
• Layer-Aware Influence for Online Data Valuation Estimation
• Learning Human Motion with Temporally Conditional Mamba
• PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
• Fast Visuomotor Policy for Robotic Manipulation
• MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
• A Function Centric Perspective On Flat and Sharp Minima
• Cautious Weight Decay
• Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
• Simple Projection Variants Improve ColBERT Performance
• Metronome: Efficient Scheduling for Periodic Traffic Jobs with Network and Priority Awareness
• Local Background Features Matter in Out-of-Distribution Detection
• Faster State Preparation with Randomization
• A Gradient Guided Diffusion Framework for Chance Constrained Programming
• Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
• SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
• Beyond the Brightest: A Deep Learning Approach to Identifying Major and Minor Galaxy Mergers in CANDELS at z ∼ 1
• nuGPR: GPU-Accelerated Gaussian Process Regression with Iterative Algorithms and Low-Rank Approximations
• MultiFoodhat: A potential new paradigm for intelligent food quality inspection
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
• CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection
• Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
• DIANet: A Phase-Aware Dual-Stream Network for Micro-Expression Recognition via Dynamic Images
• EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
• VCTR: A Transformer-Based Model for Non-parallel Voice Conversion
• Pyramid Stereo Matching Network
• Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
• A deep learning theory for neural networks grounded in physics
• Snapshot renormalization group for quantum matter
• Post-surgical Endometriosis Segmentation in Laparoscopic Videos
• PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation
• Lightweight CNN-Based Wi-Fi Intrusion Detection Using 2D Traffic Representations
• Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble
• DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
• Adversarial Attacks Leverage Interference Between Features in Superposition
• Hierarchical Qubit-Merging Transformer for Quantum Error Correction
• FACE: Faithful Automatic Concept Extraction
• How many samples to label for an application given a foundation model? Chest X-ray classification study
• Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
• Phase Aware Ear-Conditioned Learning for Multi-Channel Binaural Speaker Separation
• Joint Discriminative-Generative Modeling via Dual Adversarial Training
• Exploring and Leveraging Class Vectors for Classifier Editing
• DTEA: Dynamic Topology Weaving and Instability-Driven Entropic Attenuation for Medical Image Segmentation
• Building machines that learn and think like people
• Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos
• Lightweight Facial Landmark Detection in Thermal Images via Multi-Level Cross-Modal Knowledge Transfer
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
• Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
• Source-Free Object Detection with Detection Transformer
• ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
• Efficient Edge Test-Time Adaptation via Latent Feature Coordinate Correction
• Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset
• XGrasp: Gripper-Aware Grasp Detection with Multi-Gripper Data Generation
• Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
• High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
• Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
• Adversarial Robustness in One-Stage Learning-to-Defer
• Mixup Helps Understanding Multimodal Video Better
• Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
• SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
• Predicting the single-site and multi-site event discrimination power of dual-phase time projection chambers
• Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
• Audio-Guided Visual Perception for Audio-Visual Navigation
• Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
• Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
• Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans
• Optimally Deep Networks -- Adapting Model Depth to Datasets for Superior Efficiency
• Restricted Receptive Fields for Face Verification
• Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey
• Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping
• Deep semi-supervised approach based on consistency regularization and similarity learning for weeds classification
• Understanding Self-supervised Contrastive Learning through Supervised Objectives
• Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
• SoundReactor: Frame-level Online Video-to-Audio Generation
• SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network
• PENEX: AdaBoost-Inspired Neural Network Regularization
• High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
• Learning Model Representations Using Publicly Available Model Hubs
• Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking
• MRI Brain Tumor Detection with Computer Vision
• Performance of heavy-flavour jet identification in Lorentz-boosted topologies in proton-proton collisions at √(s) = 13 TeV
• Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification
• HccePose(BF): Predicting Front &amp; Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
• YOLOv11-Litchi: Efficient Litchi Fruit Detection based on UAV-Captured Agricultural Imagery in Complex Orchard Environments
• LocalViT: Analyzing Locality in Vision Transformers
• Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling
• Collaborative Learning of Semantic-Aware Feature Learning and Label Recovery for Multi-Label Image Recognition with Incomplete Labels
• DREAM: A Benchmark Study for Deepfake REalism AssessMent
• ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications
• Gradient-based Model Shortcut Detection for Time Series Classification
• Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
• Complementary and Contrastive Learning for Audio-Visual Segmentation
• Automated Glaucoma Report Generation via Dual-Attention Semantic Parallel-LSTM and Multimodal Clinical Data Integration
• Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
• Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
• A Style-Based Profiling Framework for Quantifying the Synthetic-to-Real Gap in Autonomous Driving Datasets
• BiFuseNet: A Multimodal Network for Estimating Blood Alcohol Concentration via Bidirectional Hierarchical Fusion
• A Multicentric Dataset for Training and Benchmarking Breast Cancer Segmentation in H&amp;E Slides
• TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
• StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
• A Methodology for Transparent Logic-Based Classification Using a Multi-Task Convolutional Tsetlin Machine
• Three-Stream Convolutional Networks for Video-based Person Re-Identification
• Leveraging Prior Knowledge of Diffusion Model for Person Search
• What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
• Rethinking the shape convention of an MLP
• High-resolution velocity model estimation with neural operator and the time-shift imaging condition
• On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks
• Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network
• Guided Proofreading of Automatic Segmentations for Connectomics
• GANs for Urban Design
• Stability of Transformers under Layer Normalization
• Holistic Order Prediction in Natural Scenes
• Cell Instance Segmentation: The Devil Is in the Boundaries
• Cross-Sensor Touch Generation
• HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network
• Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics
• Failure Prediction at Runtime for Generative Robot Policies
• A deep architecture for unified aesthetic prediction
• Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring
• A Novel Multi-branch ConvNeXt Architecture for Identifying Subtle Pathological Features in CT Scans
• MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
• Provable Watermarking for Data Poisoning Attacks
• TARO: Toward Semantically Rich Open-World Object Detection
• FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
• Denoised Diffusion for Object-Focused Image Augmentation
• Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
• SegTrans: Transferable Adversarial Examples for Segmentation Models
• MAT-Agent: Adaptive Multi-Agent Training Optimization
• Training Feature Attribution for Vision Models
• Toward Autonomous Soft Robotic Endovascular Navigation via Imitation Learning
• Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training
• Spatially-Augmented Sequence-to-Sequence Neural Diarization for Meetings
• Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale
• VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
• Vision Language Models: A Survey of 26K Papers
• Towards Information-Optimized Multi-Agent Path Finding: A Hybrid Framework with Reduced Inter-Agent Information Sharing
• Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization
• Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
• SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense
• Theoretical guarantees for change localization using conformal p-values
• ReSplat: Learning Recurrent Gaussian Splats
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
• DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
• AI-Driven Radiology Report Generation for Traumatic Brain Injuries
• Detecting and Recognizing Human-Object Interactions
• A Multimodal Depth-Aware Method For Embodied Reference Understanding
• Efficient Deployment of CNN Models on Multiple In-Memory Computing Units
• A Scalable FPGA Architecture With Adaptive Memory Utilization for GEMM-Based Operations
• Multi-Condition Conformal Selection
• A class-driven hierarchical ResNet for classification of multispectral remote sensing images
• DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
• On the Occurence of Critical Learning Periods in Neural Networks
• FlowLensing: Simulating Gravitational Lensing with Flow Matching
• Learning to Navigate Socially Through Proactive Risk Perception
• XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method
• Self-Supervised Learning Strategies for a Platform to Test the Toxicity of New Chemicals and Materials
• Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
• Demystifying Deep Learning-based Brain Tumor Segmentation with 3D UNets and Explainable AI (XAI): A Comparative Analysis
• Deep Neural Networks Inspired by Differential Equations
• FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulation
• Parallel-in-Time Solution of Allen-Cahn Equations by Integrating Operator Learning into the Parareal Method
• Sparse components distinguish visual pathways &amp; their alignment to neural networks
• Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
• Video Surveillance for Road Traffic Monitoring
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
• What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors
• RayFusion: Ray Fusion Enhanced Collaborative Visual Perception
• Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision
• MONKEY: Masking ON KEY-Value Activation Adapter for Personalization
• Curriculum Learning with Synthetic Data for Enhanced Pulmonary Nodule Detection in Chest Radiographs
• MeSH: Memory-as-State-Highways for Recursive Transformers
• Weights initialization of neural networks for function approximation
• Geometry-aware Policy Imitation
• Robust Canonicalization through Bootstrapped Data Re-Alignment
• High-dimensional Analysis of Synthetic Data Selection
• Long-Tailed Recognition via Information-Preservable Two-Stage Learning
• Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
• Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data
• Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning
• On the Alignment Between Supervised and Self-Supervised Contrastive Learning
• EMPalm: Exfiltrating Palm Biometric Data via Electromagnetic Side-Channels
• MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis
• Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
• SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
• Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection
• AppleCiDEr II: SpectraNet -- A Deep Learning Network for Spectroscopic Data
• Accelerating Inference for Multilayer Neural Networks with Quantum Computers
• Bridged Clustering: Semi-Supervised Sparse Bridging
• Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
• Sharpness-Aware Data Generation for Zero-shot Quantization
• Revealing the Temporally Stable Bimodal Energy Distribution of FRB 20121102A with a Tripled Burst Set from AI Detections
• Learning Global Representation from Queries for Vectorized HD Map Construction
• High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
• Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder
• HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentation
• Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Retrieval
• Online Generic Event Boundary Detection
• Consistent Assistant Domains Transformer for Source-free Domain Adaptation
• CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection
• Clinical-grade AI model for molecular subtyping of endometrial cancer: a multi-center cohort study in China
• Recurrence-Complete Frame-based Action Models
• Synaptic facilitation and learning of multiplexed neural signals
• Getting the Numbers Right\unicodex2014Modelling Multi-Class Object Counting in Dense and Varied Scenes
• AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
• Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions
• Adaptive Stain Normalization for Cross-Domain Medical Histology
• Mangrove3D: Terrestrial Laser Scanning Dataset for Coastal Mangrove Forests
• metabeta -- A fast neural model for Bayesian mixed-effects regression
• DPA-Net: A Dual-Path Attention Neural Network for Inferring Glycemic Control Metrics from Self-Monitored Blood Glucose Data
• The Framework That Survives Bad Models: Human-AI Collaboration For Clinical Trials
• Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
• Improving Artifact Robustness for CT Deep Learning Models Without Labeled Artifact Images via Domain Adaptation
• Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention
• Learning from Limited Multi-Phase CT: Dual-Branch Prototype-Guided Framework for Early Recurrence Prediction in HCC
• How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
• We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
• Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between
• Shaken or Stirred? An Analysis of MetaFormer's Token Mixing for Medical Imaging
• Kaputt: A Large-Scale Dataset for Visual Defect Detection
• Enhancing Automotive Security with a Hybrid Approach towards Universal Intrusion Detection System
• A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data
• Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
• Data Factory with Minimal Human Effort Using VLMs
• Membership Inference Attacks on Tokenizers of Large Language Models
• Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies
• VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
• TreeNet: Layered Decision Ensembles
• Efficient Conditional Generation on Scale-based Visual Autoregressive Models
• Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation
• Critical attention scaling in long-context transformers
• Human Action Recognition from Point Clouds over Time
• Machine Learning Detection of Road Surface Conditions: A Generalizable Model using Traffic Cameras and Weather Data
• Emergent AI Surveillance: Overlearned Person Re-Identification and Its Mitigation in Law Enforcement Context
• Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
• AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models
• Deep Generative Model for Human Mobility Behavior
• Towards Data-Efficient Medical Imaging: A Generative and Semi-Supervised Framework
• Large Language Model-Based Uncertainty-Adjusted Label Extraction for Artificial Intelligence Model Development in Upper Extremity Radiography
• OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA
• Computing frustration and near-monotonicity in deep neural networks
• Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
• Bidirectional Mammogram View Translation with Column-Aware and Implicit 3D Conditional Diffusion
• Unsupervised Active Learning via Natural Feature Progressive Framework
• ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
• Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
• A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation
• SFANet: Spatial-Frequency Attention Network for Deepfake Detection
• Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
• Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
• Improving Large-Scale Recommender Systems with Auxiliary Learning
• Knowledge Distillation Detection for Open-weights Models
• MultiModal Action Conditioned Video Generation
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
• Trade-off in Estimating the Number of Byzantine Clients in Federated Learning
• Fusion-Based Neural Generalization for Predicting Temperature Fields in Industrial PET Preform Heating
• Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction
• Bridging Text and Video Generation: A Survey
• Closed-Form Last Layer Optimization
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
• GenAR: Next-Scale Autoregressive Generation for Spatial Gene Expression Prediction
• Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
• BLADE: Bias-Linked Adaptive DEbiasing
• Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning
• Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition
• Atomistic Machine Learning with Irreducible Cartesian Natural Tensors
• RAP: 3D Rasterization Augmented End-to-End Planning
• RetiBridge: Bridging Quantitative Retinal Biomarkers and Qualitative Diagnosis with a Knowledge-Guided Multimodal Large Language Model
• Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks
• Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators
• Quantization Range Estimation for Convolutional Neural Networks
• Deep Defense: Training DNNs with Improved Adversarial Robustness
• Beyond Simple Fusion: Adaptive Gated Fusion for Robust Multimodal Sentiment Analysis
• FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
• VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs
• Privacy Enhancement in Over-the-Air Federated Learning via Adaptive Receive Scaling
• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
• No bad local minima: Data independent training error guarantees for\n multilayer neural networks
• Deep Learning for Physical Processes: Incorporating Prior Scientific\n Knowledge
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
• MambaCAFU: Hybrid Multi-Scale and Multi-Attention Model with Mamba-Based Fusion for Medical Image Segmentation
• A Benchmark Study of Deep Learning Methods for Multi-Label Pediatric Electrocardiogram-Based Cardiovascular Disease Classification
• Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization
• LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
• Click Here: Human-Localized Keypoints as Guidance for Viewpoint\n Estimation
• What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis
• MECKD: Deep Learning-Based Fall Detection in Multilayer Mobile Edge Computing With Knowledge Distillation
• A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games
• Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
• On Provable Benefits of Muon in Federated Learning
• Personalized federated prototype learning in mixed heterogeneous data scenarios
• A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems
• UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization
• AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
• CVSM: Contrastive Vocal Similarity Modeling
• Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources
• Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation
• Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking
• Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting
• ELMF4EggQ: Ensemble Learning with Multimodal Feature Fusion for Non-Destructive Egg Quality Assessment
• A physics-informed neural network approach to the point defect model for electrochemical oxide film growth
• Representing Beauty: Towards a Participatory but Objective Latent Aesthetics
• Forensic Similarity for Speech Deepfakes
• FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks
• Distributed Low-Communication Training with Decoupled Momentum Optimization
• Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models
• Net2Net: When Un-trained Meets Pre-trained Networks for Robust Real-World Denoising
• Accuracy Law for the Future of Deep Time Series Forecasting
• Hyperparameter Loss Surfaces Are Simple Near their Optima
• Using Fourier Analysis and Mutant Clustering to Accelerate DNN Mutation Testing
• Image Enhancement Based on Pigment Representation
• A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison
• Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
• Visual Language Model as a Judge for Object Detection in Industrial Diagrams
• On residual network depth
• Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage
• Self-Supervised Representation Learning as Mutual Information Maximization
• Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
• Towards Adversarial Training under Hyperspectral Images
• ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
• TextCAM: Explaining Class Activation Map with Text
• FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
• Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
• Feature Identification for Hierarchical Contrastive Learning
• Semantic Visual Simultaneous Localization and Mapping: A Survey on State of the Art, Challenges, and Future Directions
• Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
• Deep learning motion correction of quantitative stress perfusion cardiovascular magnetic resonance
• From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Review
• Batch-CAM: Introduction to better reasoning in convolutional deep learning models
• U-DFA: A Unified DINOv2-Unet with Dual Fusion Attention for Multi-Dataset Medical Segmentation
• Assessing Foundation Models for Mold Colony Detection with Limited Training Data
• Sentry: Authenticating Machine Learning Artifacts on the Fly
• Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation
• Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
• SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
• On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
• Automated Structured Radiology Report Generation with Rich Clinical Context
• Generative AI for subgrid turbulence in large-eddy simulations
• End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation
• Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation
• VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
• Teaching Categories to Human Learners with Visual Explanations
• Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
• GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
• Robust Federated Inference
• F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion models
• Learning Domain-Robust Bioacoustic Representations for Mosquito Species Classification with Contrastive Learning and Distribution Alignment
• Cutting the Skip: Training Residual-Free Transformers
• Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
• MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
• CODED-SMOOTHING: Coding Theory Helps Generalization
• Board Gender Diversity and Carbon Emissions Performance: Insights from Panel Regressions, Machine Learning and Explainable AI
• Creative synthesis of kinematic mechanisms
• Object-Centric Case-Based Reasoning via Argumentation
• Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
• Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
• Approximately Unimodal Likelihood Models for Ordinal Regression
• Uncertainty Quantification for Regression using Proper Scoring Rules
• Bayesian Influence Functions for Hessian-Free Data Attribution
• IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks
• FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
• Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
• Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation
• Marginal Flow: a flexible and efficient framework for density estimation
• Benchmarking Deep Learning Convolutions on Energy-constrained CPUs
• Architecturally Constrained Solutions to Ill-Conditioned Problems in QUBIC
• Machine Learning and Control: Foundations, Advances, and Perspectives
• Scaling Equilibrium Propagation to Deeper Neural Network Architectures
• The Impact of Scaling Training Data on Adversarial Robustness
• Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
• HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis
• MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning
• Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
• Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
• Using Images from a Video Game to Improve the Detection of Truck Axles
• Best of Sim and Real: Decoupled Visuomotor Manipulation via Learning Control in Simulation and Perception in Real
• Annotation-Efficient Active Test-Time Adaptation with Conformal Prediction
• Growing Winning Subnetworks, Not Pruning Them: A Paradigm for Density Discovery in Sparse Neural Networks
• DescribeEarth: Describe Anything for Remote Sensing Images
• Effective Model Pruning
• LAPIS: A Performance Portable, High Productivity Compiler Framework
• Ascent Fails to Forget
• Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
• Hybrid Dual-Batch and Cyclic Progressive Learning for Efficient Distributed Training
• MetaChest: Generalized few-shot learning of pathologies from chest X-rays
• AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
• Online Mapping for Autonomous Driving: Addressing Sensor Generalization and Dynamic Map Updates in Campus Environments
• Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanced Regimes
• TDHook: A Lightweight Framework for Interpretability
• Multi-patch isogeometric neural solver for partial differential equations on computer-aided design domains
• From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models
• DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
• LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
• Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids
• Crop Spirals: Re-thinking the field layout for future robotic agriculture
• MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification
• GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis
• VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
• DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation
• Vehicle Classification under Extreme Imbalance: A Comparative Study of Ensemble Learning and CNNs
• ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
• UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections
• ClustRecNet: A Novel End-to-End Deep Learning Framework for Clustering Algorithm Recommendation
• Vision Function Layer in Multimodal LLMs
• Quantifying Generalisation in Imitation Learning
• Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG
• Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm
• Advancing Zero-Shot Open-Set Speech Deepfake Source Tracing
• VNODE: A Piecewise Continuous Volterra Neural Network
• RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
• Foggy Crowd Counting: Combining Physical Priors and KAN-Graph
• Enabling Physical AI through Biological Principles
• Performance-Efficiency Trade-off for Fashion Image Retrieval
• Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure
• DINOReg: Strong Point Cloud Registration with Vision Foundation Model
• DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
• H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
• Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
• Towards Foundation Models for Cryo-ET Subtomogram Analysis
• Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports
• Adaptive Source-Channel Coding for Multi-User Semantic and Data Communications
• Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
• Conda: Column-Normalized Adam for Training Large Language Models Faster
• Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification
• High-Order Progressive Trajectory Matching for Medical Image Dataset Distillation
• Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
• Neural Visibility of Point Sets
• Analysis of Bias in Deep Learning Facial Beauty Regressors
• EYE-DEX: Eye Disease Detection and EXplanation System
• BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
• GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
• BERT Bi-modal self-supervised learning for crop classification using Sentinel-2 and Planetscope
• Improving Simple Models with Confidence Profiles
• Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks
• Characterizing and Improving Stability in Neural Style Transfer
• A Pixel-Based Framework for Data-Driven Clothing
• Relation Networks for Optic Disc and Fovea Localization in Retinal Images
• CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
• Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
• Deep Learning Reconstruction on Crab LST-1 Data
• A Systematic Review of Digital Twin-Driven Predictive Maintenance in Industrial Engineering: Taxonomy, Architectural Elements, and Future Research Directions
• A Second-Order Perspective on Pruning at Initialization and Knowledge Transfer
• On The Variability of Concept Activation Vectors
• End-to-end Topographic Auditory Models Replicate Signatures of Human Auditory Cortex
• Does Weak-to-strong Generalization Happen under Spurious Correlations?
• RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
• Enhancing hyperspectral image prediction with contrastive learning in low-label regimes
• Learning-Based Testing for Deep Learning: Enhancing Model Robustness with Adversarial Input Prioritization
• Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives
• Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis
• Differentiable Sparsity via D-Gating: Simple and Versatile Structured Penalization
• Gradient Flow Convergence Guarantee for General Neural Network Architectures
• Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
• FairViT-GAN: A Hybrid Vision Transformer with Adversarial Debiasing for Fair and Explainable Facial Beauty Prediction
• CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
• Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric
• LORT: Locally Refined Convolution and Taylor Transformer for Monaural Speech Enhancement
• GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning
• Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution
• GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
• Transparent Visual Reasoning via Object-Centric Agent Collaboration
• PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
• Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
• Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
• Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
• Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
• From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
• Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
• A Recall-First CNN for Sleep Apnea Screening from Snoring Audio
• EfficientMIL: Efficient Linear-Complexity MIL Method for WSI Classification
• BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images
• Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
• Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
• Multi-Level Heterogeneous Knowledge Transfer Network on Forward Scattering Center Model for Limited Samples SAR ATR
• Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
• Disentanglement of Variations with Multimodal Generative Modeling
• HunyuanImage 3.0 Technical Report
• QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
• Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
• Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis
• Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness
• S³F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network
• Neural Language Priors
• Generative Modeling of Shape-Dependent Self-Contact Human Poses
• UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation
• Graph Your Own Prompt
• Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling
• Seeing Through the Blur: Unlocking Defocus Maps for Deepfake Detection
• Learning Regional Monsoon Patterns with a Multimodal Attention U-Net
• PAL-AI reveals genetic determinants that control poly(A)-tail length during oocyte maturation, with relevance to human fertility
• More Data or Better Algorithms: Latent Diffusion Augmentation for Deep Imbalanced Regression
• Patch Rebirth: Toward Fast and Transferable Model Inversion of Vision Transformers
• UltraUNet: Real-Time Ultrasound Tongue Segmentation for Diverse Linguistic and Imaging Conditions
• Leave No Observation Behind: Real-time Correction for VLA Action Chunks
• PDE-Transformer: A Continuous Dynamical Systems Approach to Sequence Modeling
• Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction
• Effective Quantization of Muon Optimizer States
• HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
• Mask What Matters: Controllable Text-Guided Masking for Self-Supervised Medical Image Analysis
• Dynamics of Learning: Generative Schedules from Latent ODEs
• Activation Matching for Explanation Generation
• DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence
• Learning without Global Backpropagation via Synergistic Information Distillation
• ABConformer: Physics-inspired Sliding Attention for Antibody-Antigen Interface Prediction
• Single-Shot Refinement Neural Network for Object Detection
• ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View
• Deep Learning for Oral Health: Benchmarking ViT, DeiT, BEiT, ConvNeXt, and Swin Transformer
• URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
• Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
• AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
• Beyond Gaussian Initializations: Signal Preserving Weight Initialization for Odd-Sigmoid Activations
• Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition
• Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
• FusionStitching: Boosting Execution Efficiency of Memory Intensive Computations for DL Workloads
• Targeted perturbations reveal brain-like local coding axes in robustified, but not standard, ANN-based brain models
• Hemorica: A Comprehensive CT Scan Dataset for Automated Brain Hemorrhage Classification, Segmentation, and Detection
• T-TAMER: Provably Taming Trade-offs in ML Serving
• MindCraft: How Concept Trees Take Shape In Deep Models
• FedCF: Fair Federated Conformal Prediction
• Convolutional Set Transformer
• AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
• ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models
• Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN
• TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
• Introducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Model
• Toward a Physics of Deep Learning and Brains
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
• VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
• IONext: Unlocking the Next Era of Inertial Odometry
• Transformers for single-cell RNA sequencing: a survey
• Category Discovery: An Open-World Perspective
• γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
• U-MAN: U-Net with Multi-scale Adaptive KAN Network for Medical Image Segmentation
• FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
• A model of errors in transformers
• GPT-4 for Occlusion Order Recovery
• Multidimensional Uncertainty Quantification via Optimal Transport
• Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach
• Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
• Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
• Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation
• UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data
• Clinical Uncertainty Impacts Machine Learning Evaluations
• A Law of Data Reconstruction for Random Features (and Beyond)
• Red Teaming Quantum-Resistant Cryptographic Standards: A Penetration Testing Framework Integrating AI and Quantum Security
• Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead
• Multilingual Vision-Language Models, A Survey
• Concept activation vectors: a unifying view and adversarial attacks
• Self-driving cars: Are we there yet?
• Ground-Truthing AI Energy Consumption: Validating CodeCarbon Against External Measurements
• High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling
• Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
• Concept-SAE: Active Causal Probing of Visual Model Behavior
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation
• Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning
• LG-CD: Enhancing Language-Guided Change Detection through SAM2 Adaptation
• Zubov-Net: Adaptive Stability for Neural ODEs Reconciling Accuracy with Robustness
• Enhancing Low-Rank Adaptation with Structured Nonlinear Transformations
• Deepfakes: we need to re-think the concept of "real" images
• SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models
• Sharpness-Aware Minimization Can Hallucinate Minimizers
• Learning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation
• SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection
• HyperCore: Coreset Selection under Noise via Hypersphere Models
• On the Status of Foundation Models for SAR Imagery
• Machine Learning for Quantum State Tomography: Robust Covariance Matrix Estimation for Squeezed Vacuum States with Thermal Noise
• A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems
• A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
• Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
• Light Differentiable Logic Gate Networks
• Learning Admissible Heuristics for A*: Theory and Practice
• POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptation
• Budgeted Broadcast: An Activity-Dependent Pruning Rule for Neural Network Efficiency
• MonoCon: A general framework for learning ultra-compact high-fidelity representations using monotonicity constraints
• LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
• Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
• X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
• Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
• GraphPFN: A Prior-Data Fitted Graph Foundation Model
• Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
• VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations
• Model reduction of parametric ordinary differential equations via autoencoders: structure-preserving latent dynamics and convergence analysis
• Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability
• MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation
• Learning Conformal Explainers for Image Classifiers
• Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
• EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
• Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models
• LayerNorm Induces Recency Bias in Transformer Decoders
• Shapley Features for Robust Signal Prediction in Tactile Internet
• SiNGER: A Clearer Voice Distills Vision Transformers Further
• Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement
• Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)
• Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
• SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
• FERD: Fairness-Enhanced Data-Free Robustness Distillation
• LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty &amp; Improve Noisy Training
• Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization
• Single Image Depth Estimation Trained via Depth from Defocus Cues
• Enhancing Cross-View Geo-Localization Generalization via Global-Local Consistency and Geometric Equivariance
• The Unanticipated Asymmetry Between Perceptual Optimization and Assessment
• KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models
• DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning
• Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
• FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies
• FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
• Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy
• Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification
• SemSight: Probabilistic Bird's-Eye-View Prediction of Multi-Level Scene Semantics for Navigation
• Unlocking Financial Insights: An advanced Multimodal Summarization with Multimodal Output Framework for Financial Advisory Videos
• How fine can fine-tuning be? Learning efficient language models
• Plant identification in an open-world (LifeCLEF 2016)
• Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition
• Neural Integrated Sensing and Communication for the MIMO-OFDM Downlink
• The Unwinnable Arms Race of AI Image Detection
• An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
• Preparation Meets Opportunity: Enhancing Data Preprocessing for ML Training With Seneca
• Iterative Visual Reasoning Beyond Convolutions
• MARS: toward more efficient multi-agent collaboration for LLM reasoning
• PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization
• Velocity model building from seismic images using a Convolutional Neural Operator
• Fulcrum: Optimizing Concurrent DNN Training and Inferencing on Edge Accelerators
• Pagoda: An Energy and Time Roofline Study for DNN Workloads on Edge Accelerators
• Generative Model Inversion Through the Lens of the Manifold Hypothesis
• Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models
• Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
• Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
• mmHSense: Multi-Modal and Distributed mmWave ISAC Datasets for Human Sensing
• Embodied AI: From LLMs to World Models
• Does the Manipulation Process Matter? RITA: Reasoning Composite Image Manipulations via Reversely-Ordered Incremental-Transition Autoregression
• MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization
• Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
• Multimodal-enhanced Federated Recommendation: A Group-wise Fusion Approach
• When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset
• AJAHR: Amputated Joint Aware 3D Human Mesh Recovery
• ExpFace: Exponential Angular Margin Loss for Deep Face Recognition
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Adaptive Model Ensemble for Continual Learning
• Sobolev acceleration for neural networks
• Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
• MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
• IBiT: Utilizing Inductive Biases to Create a More Data Efficient Attention Mechanism
• Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
• Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation
• Efficiently Attacking Memorization Scores
• Are Foundation Models Ready for Industrial Defect Recognition? A Reality Check on Real-World Data
• ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research
• Region-of-Interest Augmentation for Mammography Classification under Patient-Level Cross-Validation
• Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning
• The Impact of 2D Segmentation Backbones on Point Cloud Predictions Using 4D Radar
• High Clockrate Free-space Optical In-Memory Computing
• Adaptive von Mises-Fisher Likelihood Loss for Supervised Deep Time Series Hashing
• CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems
• Confidence Calibration in Large Language Model-Based Entity Matching
• Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage
• ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
• Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
• CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration
• VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection
• Simplifying Neural Networks During Training
• Zero-shot Knowledge Transfer via Adversarial Belief Matching
• Looped Transformers with Source-Centered State Evolution
• Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective
• MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging
• Efficient Training of Convolutional Neural Nets on Large Distributed\n Systems
• Deep learning-based hierarchical insect classification using camera trap imagery
• Meteosat Third Generation imagery improves CNN-based SSI retrieval
• ATF6 activation alters colonic lipid metabolism causing tumour-associated microbial adaptation
• Towards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imaging
• Collaborative feature aggregation for face super-resolution and robust re-identification
• What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study
• ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
• Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
• CompoVista: A Composition-Graph-Based Visual Analytics System for Compositional Analysis of Traditional Chinese Paintings
• Lets keep it simple, Using simple architectures to outperform deeper and\n more complex architectures
• Multi-Head Attention Residuals
• Shortcut to Nowhere: Demystifying Deep Spurious Regression
• Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
• Successive convex optimization for transformer encoder model predictive control
• Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
• Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
• mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations
• A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
• Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
• A transformer-based multi-task deep learning model for urban livability evaluation by fusing remote sensing and textual geospatial data
• Learning Convolutional Networks for Content-weighted Image Compression
• Orexin population activity precisely reflects net body movement across behavioral and metabolic states
• Temporal Straightening for Latent Planning
• Ristretto: Hardware-Oriented Approximation of Convolutional Neural\n Networks
• Face-like holistic Processing in Non-Face Stimuli
• Topology Aware Neural Interpolation of Scalar Fields
• DL-QC-fNIRS: a deep learning tool for automated quality control in functional near-infrared spectroscopy signals
• Stiffness: A New Perspective on Generalization in Neural Networks
• Effect of Demographic Bias on Skin Lesion Classification
• Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
• TDAN: Temporally Deformable Alignment Network for Video Super-Resolution
• Edge-Enhanced Vision Transformer Framework for Accurate AI-Generated Image Detection
• Vocoder-Projected Feature Discriminator
• Face Detection through Scale-Friendly Deep Convolutional Networks
• Outplaying elite table tennis players with an autonomous robot
• XNOR-Net: ImageNet Classification Using Binary Convolutional Neural\n Networks
• Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology
• GAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image Analysis
• Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation
• Multi-style Generative Network for Real-time Transfer
• EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
• Learning to Segment Every Thing
• Art of singular vectors and universal adversarial perturbations
• BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
• DeepDeblur: Fast one-step blurry face images restoration
• Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition
• Artificial intelligence-enabled electrocardiography from scientific research to clinical application
• Box-Level Class-Balanced Sampling for Active Object Detection
• LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
• Fast Neural Architecture Construction using EnvelopeNets
• Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal
• Self-evolved Imitation Learning in Simulated World
• SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
• Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
• Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps
• Probabilistic Runtime Verification, Evaluation and Risk Assessment of Visual Deep Learning Systems
• World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
• Pure Vision Language Action (VLA) Models: A Comprehensive Survey
• Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset
• ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
• Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• A Kernel Space-based Multidimensional Sparse Model for Dynamic PET Image Denoising
• Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
• Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
• MLF-4DRCNet: Multi-Level Fusion with 4D Radar and Camera for 3D Object Detection in Autonomous Driving
• Deep Learning At Scale and At Ease
• Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment
• MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation
• Single-Branch Network Architectures to Close the Modality Gap in Multimodal Recommendation
• MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
• SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models
• Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks
• Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
• VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
• Towards Application Aligned Synthetic Surgical Image Synthesis
• MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
• Chiplet-Based RISC-V SoC with Modular AI Acceleration
• Learning to Condition: A Neural Heuristic for Scalable MPE Inference
• Recognition Of Surface Defects On Steel Sheet Using Transfer Learning
• Is It Certainly a Deepfake? Reliability Analysis in Detection &amp; Generation Ecosystem
• Lipschitz-Based Robustness Certification for Recurrent Neural Networks via Convex Relaxation
• Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
• Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
• Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding
• Automated Labeling of Intracranial Arteries with Uncertainty Quantification Using Deep Learning
• Accelerated characterization of two-level systems in superconducting qubits via machine learning
• RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion
• Tailored Transformation Invariance for Industrial Anomaly Detection
• Development and validation of an AI foundation model for endoscopic diagnosis of esophagogastric junction adenocarcinoma: a cohort and deep learning study
• A²M²-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
• PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification
• Visual Instruction Pretraining for Domain-Specific Foundation Models
• Multimodal Radio and Vision Fusion for Robust Localization in Urban V2I Communications
• MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perception
• Training-Free Label Space Alignment for Universal Domain Adaptation
• Exploring Machine Learning Models for Physical Dose Calculation in Carbon Ion Therapy Using Heterogeneous Imaging Data -- A Proof of Concept Study
• Optimizing Split Federated Learning with Unstable Client Participation
• Revisiting Vision Language Foundations for No-Reference Image Quality Assessment
• Attention-based Mixture of Experts for Robust Speech Deepfake Detection
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models
• ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion
• Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
• DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning
• From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge
• The evolution of neural network-based chart patterns
• Domain Adaptive Object Detection for Space Applications with Real-Time Constraints
• The unreasonable effectiveness of the forget gate
• Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification
• Convolutional Neural Network Optimization for Beehive Classification Using Bioacoustic Signals
• Towards General Computer Control with Hierarchical Agents and Multi-Level Action Spaces
• LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
• Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
• Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios
• DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
• Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing
• SynergyNet: Fusing Generative Priors and State-Space Models for Facial Beauty Prediction
• Flow-Induced Diagonal Gaussian Processes
• CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception
• MARS: A Malignity-Aware Backdoor Defense in Federated Learning
• Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations
• SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
• A review of Recent Techniques for Person Re-Identification
• SVDNet for Pedestrian Retrieval
• Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
• Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
• DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment
• LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
• 3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
• Mobile Video Object Detection with Temporally-Aware Feature Maps
• MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification
• STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
• PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion
• SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
• Clinical Multi-modal Fusion with Heterogeneous Graph and Disease Correlation Learning for Multi-Disease Prediction
• Graph Coloring for Multi-Task Learning
• Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
• FedEL: Federated Elastic Learning for Heterogeneous Devices
• ME-Mamba: Multi-Expert Mamba with Efficient Knowledge Capture and Fusion for Multimodal Survival Analysis
• Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations
• Optimized Learned Image Compression for Facial Expression Recognition
• Learning Hyperspectral Images with Curated Text Prompts for Efficient Multimodal Alignment
• SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training
• Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
• When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation
• Towards a Transparent and Interpretable AI Model for Medical Image Classifications
• IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
• Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence
• Learned Digital Codes for Over-the-Air Federated Learning
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting
• No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learning
• Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity
• TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation
• Describe-to-Score: Text-Guided Efficient Image Complexity Assessment
• Cross-Corpus and Cross-domain Handwriting Assessment of NeuroDegenerative Diseases via Time-Series-to-Image Conversion
• Explainable Deep Learning for Cataract Detection in Retinal Images: A Dual-Eye and Knowledge Distillation Approach
• DISCO: Disentangled Communication Steering for Large Language Models
• SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
• PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality
• CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding
• Factorizing Diffusion Policies for Observation Modality Prioritization
• CoUn: Empowering Machine Unlearning via Contrastive Learning
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
• Learning Safety for Obstacle Avoidance via Control Barrier Functions
• DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching
• Detecting Photoshopped Faces by Scripting Photoshop
• A multi-temporal multi-spectral attention-augmented deep convolution neural network with contrastive learning for crop yield prediction
• PAN: Pillars-Attention-Based Network for 3D Object Detection
• Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
• RMT-KD: Random Matrix Theoretic Causal Knowledge Distillation
• Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Model
• Toward Efficient Influence Function: Dropout as a Compression Tool
• ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning
• Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection
• Beyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues
• MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training
• Saccadic Vision for Fine-Grained Visual Classification
• Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification
• Distributed Multi-Task Learning for Joint Wireless Signal Enhancement and Recognition
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• Filter-and-Attend: Wireless Channel Foundation Model with Noise-Plus-Interference Suppression Structure
• MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation
• Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
• Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
• Boosting Active Learning with Knowledge Transfer
• On the Convergence of Muon and Beyond
• SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors
• Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models
• DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
• MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts Framework
• How many classes do we need to see for novel class discovery?
• Efficient Multimodal Dataset Distillation via Generative Models
• CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
• Causal Fingerprints of AI Generative Models
• Generating Part-Based Global Explanations Via Correspondence
• Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
• CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization
• TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE
• Who to Trust? Aggregating Client Knowledge in Logit-Based Federated Learning
• Dissecting the Graphcore IPU Architecture via Microbenchmarking
• Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
• Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges
• OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
• Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
• UCorr: Wire Detection and Depth Estimation for Autonomous Drones
• Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
• Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications
• FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver
• Designing Latent Safety Filters using Pre-Trained Vision Models
• Pre-training Autoencoder for Acoustic Event Classification via Blinky
• Multiscale super-resolution reconstruction of fluid flows with deep neural networks
• SpeechMLC: Speech Multi-label Classification
• How Does Instrumental Music Help SingFake Detection?
• Emotion-Aware Speech Generation with Character-Specific Voices for Comics
• An Attention Free Transformer
• Efficient 3D Perception on Embedded Systems via Interpolation-Free Tri-Plane Lifting and Volume Fusion
• CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
• Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections
• Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Masking
• Domain Adaptation for Ulcerative Colitis Severity Estimation Using Patient-Level Diagnoses
• DiffVL: Diffusion-Based Visual Localization on 2D Maps via BEV-Conditioned GPS Denoising
• TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalities
• Learning to Pick: A Visuomotor Policy for Clustered Strawberry Picking
• Object Recognition and Force Estimation with the GelSight Baby Fin Ray
• Survey on Deep Learning-based Kuzushiji Recognition
• BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots
• URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation
• Evaluating Multimodal Large Language Models on Spoken Sarcasm Understanding
• Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
• VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Games
• Semi-Supervised 3D Medical Segmentation from 2D Natural Images Pretrained Model
• FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning
• Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Space
• Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation
• Interleaved Group Convolutions for Deep Neural Networks
• Statistically Motivated Second Order Pooling
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Class-Invariant Test-Time Augmentation for Domain Generalization
• BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
• An Exploratory Study on Abstract Images and Visual Representations Learned from Them
• Data Leakage in Visual Datasets
• Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction
• FedERL: Federated Efficient and Robust Learning for Common Corruptions
• VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement
• SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
• RepCaM++: Exploring Transparent Visual Prompt With Inference-Time Re-Parameterization for Neural Video Delivery
• SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks
• Noise-Level Diffusion Guidance: Well Begun is Half Done
• Masked Feature Modeling Enhances Adaptive Segmentation
• Efficient Quantization-Aware Neural Receivers: Beyond Post-Training Quantization
• Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
• Self Identity Mapping
• Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
• Cross-modal Full-mode Fine-grained Alignment for Text-to-Image Person Retrieval
• ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
• Deep Lookup Network
• Improved Segmentation of Polyps and Visual Explainability Analysis
• Deep Learning-Driven Peptide Classification in Biological Nanopores
• VocSegMRI: Multimodal Learning for Precise Vocal Tract Segmentation in Real-time MRI
• WatchAnxiety: A Transfer Learning Approach for State Anxiety Prediction from Smartwatch Data
• UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
• Integrated diffractive full-Stokes spectro-polarimetric imaging
• FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras
• Federated Learning for Deforestation Detection: A Distributed Approach with Satellite Imagery
• EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View
• GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
• Defending Deepfake via Texture Feature Perturbation
• Behavior Foundation Model for Humanoid Robots
• FlowDrive: Energy Flow Field for End-to-End Autonomous Driving
• Annotating Satellite Images of Forests with Keywords from a Specialized Corpus in the Context of Change Detection
• Learning Progression-Guided AI Evaluation of Scientific Models To Support Diverse Multi-Modal Understanding in NGSS Classroom
• Explain Before You Answer: A Survey on Compositional Visual Reasoning
• Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation
• Image Realness Assessment and Localization with Multimodal Features
• ResidualViT for Efficient Temporally Dense Video Encoding
• An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivity
• Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks
• UTI-LLM: A Personalized Articulatory-Speech Therapy Assistance System Based on Multimodal Large Language Model
• CvT: Introducing Convolutions to Vision Transformers
• Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategy
• Reversible Deep Equilibrium Models
• EByFTVeS: Efficient Byzantine Fault Tolerant-based Verifiable Secret-sharing in Distributed Privacy-preserving Machine Learning
• HQCNN: A Hybrid Quantum-Classical Neural Network for Medical Image Classification
• Performance is not All You Need: Sustainability Considerations for Algorithms
• AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural Networks
• A biological vision inspired framework for machine perception of abutting grating illusory contours
• Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
• Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions
• Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations
• CIARD: Cyclic Iterative Adversarial Robustness Distillation
• Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling
• Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection
• Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew
• High-Energy Concentration for Federated Learning in Frequency Domain
• 4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
• FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation
• SegStereo: Exploiting Semantic Information for Disparity Estimation
• Curvature Learning for Generalization of Hyperbolic Neural Networks
• Detecting Cyberattacks in Industrial Control Systems Using Convolutional Neural Networks
• SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
• The Lifecycle Principle: Stabilizing Dynamic Neural Networks with State Memory
• Multi-scale Scanning Network for Machine Anomalous Sound Detection
• FusionMAE: large-scale pretrained model to optimize and simplify diagnostic and control of fusion plasma
• Conflect: Designing Reflective Thinking-Based Contextual Privacy Policy for Mobile Applications
• VQT-Light:Lightweight HDR Illumination Map Prediction with Richer Texture.pdf
• TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images
• T-SiamTPN: Temporal Siamese Transformer Pyramid Networks for Robust and Efficient UAV Tracking
• Introduce the Result Into Self-Attention
• End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection
• Exploring Training Data Attribution under Limited Access Constraints
• Contextualized Representation Learning for Effective Human-Object Interaction Detection
• Learning Deep ResNet Blocks Sequentially using Boosting Theory
• SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
• AON: Towards Arbitrarily-Oriented Text Recognition
• Rethinking Radiology: An Analysis of Different Approaches to BraTS
• A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs
• Beyond Gaze Overlap: Analyzing Joint Visual Attention Dynamics Using Egocentric Data
• GhostNetV3-Small: A Tailored Architecture and Comparative Study of Distillation Strategies for Tiny Images
• Uncertainty-Aware Hourly Air Temperature Mapping at 2 km Resolution via Physics-Guided Deep Learning
• U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT
• FedDAF: Federated Domain Adaptation Using Model Functional Distance
• Deceptive Risk Minimization: Out-of-Distribution Generalization by Deceiving Distribution Shift Detectors
• Automatically detecting pig position and posture by 2D camera imaging and deep learning
• Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
• LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
• CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation
• A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction
• SpotTune: Transfer Learning through Adaptive Fine-tuning
• Take it in your stride: Do we need striding in CNNs?
• SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
• PD-Loss: Proxy-Decidability for Efficient Metric Learning
• MSMA: Multi-Scale Feature Fusion For Multi-Attribute 3D Face Reconstruction From Unconstrained Images
• DRAG: Data Reconstruction Attack using Guided Diffusion
• The Quest for Universal Master Key Filters in DS-CNNs
• DTGen: Generative Diffusion-Based Few-Shot Data Augmentation for Fine-Grained Dirty Tableware Recognition
• Determining the boundary of dynamical chaos in the generalized Chirikov map via machine learning
• Optimizing Class Distributions for Bias-Aware Multi-Class Learning
• A Fine-Grained 3D Radio Map Construction Paradigm with Ultra-Low Sampling Rates by Large Generative Models
• Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis
• DARD: Dice Adversarial Robustness Distillation against Adversarial Attacks
• Synthetic vs. Real Training Data for Visual Navigation
• Adaptive Spatial Goodness Encoding: Advancing and Scaling Forward-Forward Learning Without Backpropagation
• Error Control and Loss Functions for the Deep Learning Inversion of Borehole Resistivity Measurements
• Advanced Layout Analysis Models for Docling
• Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
• EMeRALDS: Electronic Medical Record Driven Automated Lung Nodule Detection and Classification in Thoracic CT Images
• Reduced Order Modeling of Energetic Materials Using Physics-Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)
• Two-Stage Decoupling Framework for Variable-Length Glaucoma Prognosis
• Reconstruction of IACT events using deep learning techniques with CTLearn
• NeuroGaze-Distill: Brain-informed Distillation and Depression-Inspired Geometric Priors for Robust Facial Emotion Recognition
• Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
• Logit Mixture Outlier Exposure for Fine-grained Out-of-Distribution Detection
• MAFS: Masked Autoencoder for Infrared-Visible Image Fusion and Semantic Segmentation
• Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generation
• Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
• Neural networks in the search for fast radio bursts with RATAN-600
• FEWT: Improving Humanoid Robot Perception with Frequency-Enhanced Wavelet-based Transformers
• SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing
• Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
• Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation
• End-to-End Visual Autonomous Parking via Control-Aided Attention
• Hybrid Quantum Neural Networks for Efficient Protein-Ligand Binding Affinity Prediction
• SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion
• Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models
• CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning
• Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
• UnLoc: Leveraging Depth Uncertainties for Floorplan Localization
• Policy-Driven Transfer Learning in Resource-Limited Animal Monitoring
• Point-Plane Projections for Accurate LiDAR Semantic Segmentation in Small Data Scenarios
• A Modern Look at Simplicity Bias in Image Classification Tasks
• Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection
• ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation
• Building a General SimCLR Self-Supervised Foundation Model Across Neurological Diseases to Advance 3D Brain MRI Diagnoses
• SSL-AD: Spatiotemporal Self-Supervised Learning for Generalizability and Adaptability Across Alzheimer's Prediction Tasks and Datasets
• EfficientNet-Based Multi-Class Detection of Real, Deepfake, and Plastic Surgery Faces
• A Symmetry-Integrated Approach to Surface Code Decoding
• FedBiF: Communication-Efficient Federated Learning via Bits Freezing
• Towards Understanding the Data Dependency of Mixup-style Training
• Leveraging Multi-View Weak Supervision for Occlusion-Aware Multi-Human Parsing
• Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection
• Balanced Sharpness-Aware Minimization for Imbalanced Regression
• Local Information Matters: A Rethink of Crowd Counting
• Neural Scaling Laws for Deep Regression
• Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification
• Service Function Chaining Architecture for Multi-hop Split Inference and Learning
• FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection
• The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram
• Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Images
• Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
• DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators
• Why and How Auxiliary Tasks Improve JEPA Representations
• TUNI: Unifying Pre-training and Fine-tuning with Modality-Aware Mutual Learning and Rectification for RGB-T Semantic Segmentation
• Imagined Autocurricula
• HGEN: Heterogeneous Graph Ensemble Networks
• DVQA: Understanding Data Visualizations via Question Answering
• Deep Learning with Apache SystemML
• From the Gradient-Step Denoiser to the Proximal Denoiser and their associated convergent Plug-and-Play algorithms
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
• Uncertainty Propagation Networks for Neural Ordinary Differential Equations
• NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
• MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
• PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
• Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution
• Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification
• Cough Classification using Few-Shot Learning
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
• MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
• CoAtNeXt:An Attention-Enhanced ConvNeXtV2-Transformer Hybrid Model for Gastric Tissue Classification
• Modular, On-Site Solutions with Lightweight Anomaly Detection for Sustainable Nutrient Management in Agriculture
• Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
• Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing
• OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge
• Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
• FPI-Det: a face--phone Interaction Dataset for phone-use detection and understanding
• Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
• Scalable extensions to given-data Sobol' index estimators
• Improvement of Human-Object Interaction Action Recognition Using Scene Information and Multi-Task Learning Approach
• Tri-Accel: Curvature-Aware Precision-Adaptive and Memory-Elastic Optimization for Efficient GPU Usage
• AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
• MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
• MSDANet: A Multiscale Dual-Channel Spatial Attention Network with Depthwise Separable Convolution for Hyperspectral Image Classification
• OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
• Patch-based Automatic Rosacea Detection Using the ResNet Deep Learning Framework
• WAVE-DETR Multi-Modal Visible and Acoustic Real-Life Drone Detector
• Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning
• Privacy-Preserving Automated Rosacea Detection Based on Medically Inspired Region of Interest Selection
• Model compression via distillation and quantization
• CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
• Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
• Diffusion-Based Action Recognition Generalizes to Untrained Domains
• GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
• End-to-End Learning of Geometry and Context for Deep Stereo Regression
• An End-to-End Deep Learning Framework for Arsenicosis Diagnosis Using Mobile-Captured Skin Images
• ArgoTweak: Towards Self-Updating HD Maps through Structured Priors
• Compressing CNN models for resource-constrained systems by channel and layer pruning
• RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts
• CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretraining
• Audio Deepfake Verification
• Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data
• Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
• VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
• Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
• Chordless cycle filtrations for dimensionality detection in complex networks via topological data analysis
• Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
• Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference
• Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
• Advancing Few-Shot Pediatric Arrhythmia Classification with a Novel Contrastive Loss and Multimodal Learning
• Dual-Thresholding Heatmaps to Cluster Proposals for Weakly Supervised Object Detection
• Segment Transformer: AI-Generated Music Detection via Music Structural Analysis
• Value bounds and Convergence Analysis for Averages of LRP attributions
• Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
• Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection
• CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
• Sparsity in Deep Neural Networks - An Empirical Investigation with\n TensorQuant
• Rollout-LaSDI: Enhancing the long-term accuracy of Latent Space Dynamics
• ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
• Localized PCA-Net Neural Operators for Scalable Solution Reconstruction of Elliptic PDEs
• Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning
• Hammer and Anvil: A Principled Defense Against Backdoors in Federated Learning
• How Far Are We from True Unlearnability?
• Neuromorphic Simulation of Drosophila Melanogaster Brain Connectome on Loihi 2
• RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
• One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
• Feature Space Analysis by Guided Diffusion Model
• ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion
• Object-level Correlation for Few-Shot Segmentation
• Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
• Two Stage Context Learning with Large Language Models for Multimodal Stance Detection on Climate Change
• Efficient resource management in UAVs for Visual Assistance
• EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration
• EHWGesture -- A dataset for multimodal understanding of clinical gestures
• Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognition
• Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence
• Deep Image Retrieval: Learning global representations for image search
• MixGAN: A Hybrid Semi-Supervised and Generative Approach for DDoS Detection in Cloud-Integrated IoT Networks
• Using Optimal Transport Aligned Latent Embeddings for Separated Flow Analysis
• Basis Vector Metric: A Method for Robust Open-Ended State Change Detection
• Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
• XSRD-Net: EXplainable Stroke Relapse Detection
• Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
• A machine learning assistant for detecting fraudulent activities in synchronous online programming exams
• ACE and Diverse Generalization via Selective Disagreement
• Testing chatbots on the creation of encoders for audio conditioned image generation
• Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
• SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
• G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
• NeuroFabric: Identifying Ideal Topologies for Training A Priori Sparse Networks
• Representation Transfer by Optimal Transport
• XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning
• H₂OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
• BatStation: Toward In-Situ Radar Sensing on 5G Base Stations with Zero-Shot Template Generation
• Are Targeted Data Poisoning Attacks as Effective as We Think?
• Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers
• floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
• Automated Radiographic Total Sharp Score (ARTSS) in Rheumatoid Arthritis: A Solution to Reduce Inter-Intra Reader Variation and Enhancing Clinical Practice
• Imitative Membership Inference Attack
• MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
• MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
• Food Ingredients Recognition through Multi-label Learning
• Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos
• Integrated Detection and Tracking Based on Radar Range-Doppler Feature
• QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patients
• FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection
• An Analysis of Scale Invariance in Object Detection - SNIP
• Expert-Guided Explainable Few-Shot Learning for Medical Image Diagnosis
• Multi-Modal Camera-Based Detection of Vulnerable Road Users
• AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution
• Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
• Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration
• Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection
• NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
• Pothole Detection and Recognition based on Transfer Learning
• A Multi-Modal Deep Learning Framework for Colorectal Pathology Diagnosis: Integrating Histological and Colonoscopy Data in a Pilot Study
• Signal-Based Malware Classification Using 1D CNNs
• Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment
• IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networks
• Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
• Dimensionally Reduced Open-World Clustering: DROWCULA
• Predicting Brain Tumor Response to Therapy using a Hybrid Deep Learning and Radiomics Approach
• Analysis of Transferability Estimation Metrics for Surgical Phase Recognition
• Lookup multivariate Kolmogorov-Arnold Networks
• Quantitative Currency Evaluation in Low-Resource Settings through Pattern Analysis to Assist Visually Impaired Users
• Exploring Light-Weight Object Recognition for Real-Time Document Detection
• Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)
• UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning
• A Surrogate model for High Temperature Superconducting Magnets to Predict Current Distribution with Neural Network
• Robotic Manipulation Framework Based on Semantic Keypoints for Packing Shoes of Different Sizes, Shapes, and Softness
• TinyDef-DETR: A Transformer-Based Framework for Defect Detection in Transmission Lines from UAV Imagery
• Micro-Expression Recognition via Fine-Grained Dynamic Perception
• Khana: A Comprehensive Indian Cuisine Dataset
• Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimation
• AttriPrompt: Dynamic Prompt Composition Learning for CLIP
• Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets
• DeepStream: Prototyping Deep Joint Source-Channel Coding for Real-Time Multimedia Transmissions
• Parameter-Free Logit Distillation via Sorting Mechanism
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement\n Learning
• CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation
• Tell-Tale Watermarks for Explanatory Reasoning in Synthetic Media Forensics
• SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models
• Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
• Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• High Utilization Energy-Aware Real-Time Inference Deep Convolutional Neural Network Accelerator
• JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization
• Transformer-based Topology Optimization
• Toward Efficient and Scalable Design of In-Memory Graph-Based Vector Search
• ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization
• Causal Multi-fidelity Surrogate Forward and Inverse Models for ICF Implosions
• Prior Distribution and Model Confidence
• TripOptimizer: Generative 3D Shape Optimization and Drag Prediction using Triplane VAE Networks
• Stochastic Analysis of Overlapping Generations Models Under Incomplete Markets
• FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
• On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
• NSML: Meet the MLaaS platform with a real-world case study
• Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
• On Hyperparameters and Backdoor-Resistance in Horizontal Federated Learning
• Semi-supervised Deep Transfer for Regression without Domain Alignment
• A biologically inspired separable learning vision model for real-time traffic object perception in Dark
• TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution
• Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
• Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
• Beyond I-Con: Exploring New Dimension of Distance Measures in Representation Learning
• Advanced Brain Tumor Segmentation Using EMCAD: Efficient Multi-scale Convolutional Attention Decoding
• Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
• An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
• COGITAO: A Visual Reasoning Framework To Study Compositionality &amp; Generalization
• Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
• Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's
• Towards Open World Detection: A Survey
• Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
• CD-Mamba: Cloud detection with long-range spatial dependency modeling
• Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation
• MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery
• VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
• Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision
• Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families
• Beyond Output Faithfulness: Learning Attributions that Preserve Computational Pathways
• MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
• Noisy Label Refinement with Semantically Reliable Synthetic Images
• Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Differential Morphological Profile Neural Networks for Semantic Segmentation
• Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression
• An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline
• DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
• YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components
• Real Time FPGA Based CNNs for Detection, Classification, and Tracking in Autonomous Systems: State of the Art Designs and Optimizations
• Revisiting Simple Baselines for In-The-Wild Deepfake Detection
• A Synthetic-to-Real Dehazing Method based on Domain Unification
• TriLiteNet: Lightweight Model for Multi-Task Visual Perception
• Using Deep Learning to Identify Artificial Satellite Trails in Multi-band Photometric Astronomical Images
• Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
• Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
• SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation
• PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
• SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification
• Multimodal Feature Fusion Network with Text Difference Enhancement for Remote Sensing Change Detection
• ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
• Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
• From Predictions to Explanations: Explainable AI for Autism Diagnosis and Identification of Critical Brain Regions
• Learning Neural Decoding with Parallelism and Self-Coordination for Quantum Error Correction
• Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
• Map as a By-product: Collective Landmark Mapping from IMU Data and User-provided Texts in Situated Tasks
• 2018 Robotic Scene Segmentation Challenge
• Optimizing Frequent Checkpointing via Low-Cost Differential for Distributed Training Systems
• Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects
• STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
• Estudio de la eficiencia en la escalabilidad de GPUs para el entrenamiento de Inteligencia Artificial
• Insights from Gradient Dynamics: Gradient Autoscaled Normalization
• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
• An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification
• Teacher-Student Model for Detecting and Classifying Mitosis in the MIDOG 2025 Challenge
• The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
• Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
• Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning
• ANNIE: Be Careful of Your Robots
• Prototype-Guided Robust Learning against Backdoor Attacks
• InWaveSR: Topography-Aware Super-Resolution Network for Internal Solitary Waves
• Temporal social network modeling of mobile connectivity data with graph neural networks
• SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather
• RTGMFF: Enhanced fMRI-based Brain Disorder Diagnosis via ROI-driven Text Generation and Multimodal Feature Fusion
• A Plug-and-play Model-agnostic Embedding Enhancement Approach for Explainable Recommendation
• LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization
• FastCaps: A Design Methodology for Accelerating Capsule Network on Field Programmable Gate Arrays
• High Cursive Complex Character Recognition using GAN External Classifier
• Isolated Bangla Handwritten Character Classification using Transfer Learning
• Putting An End to End-to-End: Gradient-Isolated Learning of Representations
• Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
• A Lightweight Group Multiscale Bidirectional Interactive Network for Real-Time Steel Surface Defect Detection
• Enhancing Robustness in Post-Processing Watermarking: An Ensemble Attack Network Using CNNs and Transformers
• VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results
• Unsupervised Instance Segmentation with Superpixels
• SPENet: Self-guided Prototype Enhancement Network for Few-shot Medical Image Segmentation
• S2M2ECG: Spatio-temporal bi-directional State Space Model Enabled Multi-branch Mamba for ECG
• Single Domain Generalization in Diabetic Retinopathy: A Neuro-Symbolic Learning Approach
• Artificial Intelligence-derived Cardiotocography Age as a Digital Biomarker for Predicting Future Adverse Pregnancy Outcomes
• LGBP-OrgaNet: Learnable Gaussian Band Pass Fusion of CNN and Transformer Features for Robust Organoid Segmentation and Tracking
• Invariant Features for Global Crop Type Classification
• Gradient Estimation Methods of Approximate Multipliers for High-Accuracy Retraining of Deep Learning Models
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
• Continuous Saudi Sign Language Recognition: A Vision Transformer Approach
• Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
• Information transmission: Inferring change area from change moment in time series remote sensing images
• DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
• Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
• Heatmap Guided Query Transformers for Robust Astrocyte Detection across Immunostains and Resolutions
• Lattice Annotated Temporal (LAT) Logic for Non-Markovian Reasoning
• Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses
• RiverScope: High-Resolution River Masking Dataset
• A Convolutional Hierarchical Deep-learning Neural Network (C-HiDeNN) Framework for Non-linear Finite Element Analysis
• Fisher information flow in artificial neural networks
• Vision encoders should be image size agnostic and task driven
• Earthquake Source Depth Determination using Single Station Waveforms and Deep Learning
• SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images
• DeepGeo: Photo Localization with Deep Neural Network
• Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers
• TIRAMISU: A Polyhedral Compiler for Dense and Sparse Deep Learning
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• A Multimodal-Multitask Framework with Cross-modal Relation and Hierarchical Interactive Attention for Semantic Comprehension
• Prospects for acoustically monitoring ecosystem tipping points
• Enhancing Zero-Shot Pedestrian Attribute Recognition with Synthetic Data Generation: A Comparative Study with Image-To-Image Diffusion Models
• Robust Small Methane Plume Segmentation in Satellite Imagery
• SALAD -- Semantics-Aware Logical Anomaly Detection
• Targeted Physical Evasion Attacks in the Near-Infrared Domain
• A flexible FPGA accelerator for convolutional neural networks
• Exploring Diffusion Models for Generative Forecasting of Financial Charts
• An Investigation of Visual Foundation Models Robustness
• Physics-Informed Machine Learning with Adaptive Grids for Optical Microrobot Depth Estimation
• A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search
• Energy-Efficient Split Learning for Resource-Constrained Environments: A Smart Farming Solution
• HydroVision: Predicting Optically Active Parameters in Surface Water Using Computer Vision
• Enhancing Fitness Movement Recognition with Attention Mechanism and Pre-Trained Feature Extractors
• Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors
• Deep learning-enabled virtual multiplexed immunostaining of label-free tissue for vascular invasion assessment
• Augmented KRnet for density estimation and approximation
• VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
• Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis
• Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
• CLINN: Conservation Law Informed Neural Network for Approximating Discontinuous Solutions
• DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
• Synesthesia of Machines (SoM)-Based Task-Driven MIMO System for Image Transmission
• A Multimodal Cross-View Model for Predicting Postoperative Neck Pain in Cervical Spondylosis Patients
• Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detection
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Towards deep-learning based detection and quantification of intestinal metaplasia on digitized gastric biopsies: a multi-expert comparative study
• ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
• Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks
• BM-CL: Bias Mitigation through the lens of Continual Learning
• Handling imbalance and few-sample size in ML based Onion disease classification
• Examination of PCA Utilisation for Multilabel Classifier of Multispectral Images
• One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption
• Structured AI Decision-Making in Disaster Management
• Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction
• SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization
• LiFeChain: Lightweight Blockchain for Secure and Efficient Federated Lifelong Learning in IoT
• Mamba-CNN: A Hybrid Architecture for Efficient and Accurate Facial Beauty Prediction
• Domain Adaptation via Feature Refinement
• Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
• Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices
• CbLDM: A Diffusion Model for recovering nanostructure from atomic pair distribution function
• AgroSense: An Integrated Deep Learning System for Crop Recommendation via Soil Image Analysis and Nutrient Profiling
• Non-local RoIs for Instance Segmentation
• Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
• RT-DETRv2 Explained in 8 Illustrations
• Enhanced Fingerprint-based Positioning With Practical Imperfections: Deep learning-based approaches
• MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
• SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning
• Calibration-sample free distortion correction of electron diffraction patterns using deep learning
• Seeing through Unclear Glass: Occlusion Removal with One Shot
• Node-Equivariant Message Passing for Efficient and Accurate Machine Learning Interatomic Potentials
• Person Search with Natural Language Description
• Expandable Residual Approximation for Knowledge Distillation
• Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning
• Controllable Generation of Implied Volatility Surfaces with Variational Autoencoders
• Deep Learning-Based Rock Particulate Classification Using Attention-Enhanced ConvNeXt
• Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block
• ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
• PrediTree: A Multi-Temporal Sub-meter Dataset of Multi-Spectral Imagery Aligned With Canopy Height Maps
• Wavelet-Enhanced PaDiM for Industrial Anomaly Detection
• Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
• Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervals
• CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation
• Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective
• Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
• Sequential Difference Maximization: Generating Adversarial Examples via Multi-Stage Optimization
• A computer vision-based approach to enhance seismic catalogues
• IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects
• Decomposing and Revising What Language Models Generate
• MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure
• Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification
• A Closer Look at Local Aggregation Operators in Point Cloud Analysis
• Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
• MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
• AI-driven Dispensing of Coral Reseeding Devices for Broad-scale Restoration of the Great Barrier Reef
• First RAG, Second SEG: A Training-Free Paradigm for Camouflaged Object Detection
• Data Distillation: Towards Omni-Supervised Learning
• Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
• Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19
• Multi-Focused Video Group Activities Hashing
• MLLMRec: Exploring the Potential of Multimodal Large Language Models in Recommender Systems
• NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis
• AQFusionNet: Multimodal Deep Learning for Air Quality Index Prediction with Imagery and Sensor Data
• Target-Oriented Single Domain Generalization
• Scene Graph Generation via Conditional Random Fields
• Towards Zero-shot Cross-lingual Image Retrieval and Tagging
• Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
• CryptoFace: End-to-End Encrypted Face Recognition
• Re-ID done right: towards good practices for person re-identification
• Learning to Synthesize a 4D RGBD Light Field from a Single Image
• Theory Foundation of Physics-Enhanced Residual Learning
• Multimodal Deep Learning for Phyllodes Tumor Classification from Ultrasound and Clinical Data
• Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements
• Generative Latent Space Dynamics of Electron Density
• Unsupervised Video Continual Learning via Non-Parametric Deep Embedded Clustering
• Learning from Silence and Noise for Visual Sound Source Localization
• Cross-Attention Multimodal Fusion for Breast Cancer Diagnosis: Integrating Mammography and Clinical Data with Explainability
• FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
• Solutions for Mitotic Figure Detection and Atypical Classification in MIDOG 2025
• Activation Subspaces for Out-of-Distribution Detection
• Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
• Self-supervised large-scale kidney abnormality detection in drug safety assessment studies
• Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
• Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
• Trees as Gaussians: Large-Scale Individual Tree Mapping
• Scalable Equilibrium Propagation via Intermediate Error Signals for Deep Convolutional CRNNs
• Automated Multi-label Classification of Eleven Retinal Diseases: A Benchmark of Modern Architectures and a Meta-Ensemble on a Large Synthetic Dataset
• Learning to Assemble the Soma Cube with Legal-Action Masked DQN and Safe ZYZ Regrasp on a Doosan M0609
• Mini Autonomous Car Driving based on 3D Convolutional Neural Networks
• Guess-and-Learn (G&amp;L): Measuring the Cumulative Error Cost of Cold-Start Adaptation
• Representation Learning with Adaptive Superpixel Coding
• Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
• Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation
• Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
• A Simple Cache Model for Image Recognition
• Learning Longer-term Dependencies in RNNs with Auxiliary Losses
• MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems
• Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
• Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay
• Unitary Synthesis with AlphaZero via Dynamic Circuits
• Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
• Network of Experts for Large-Scale Image Categorization
• Fast Convergence Rates for Subsampled Natural Gradient Algorithms on Quadratic Model Problems
• Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives
• E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation\n with Deep Gaussian CRFs
• Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
• Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
• To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software
• Deep Learning Framework for Early Detection of Pancreatic Cancer Using Multi-Modal Medical Imaging Analysis
• Adapting Foundation Model for Dental Caries Detection with Dual-View Co-Training
• SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer
• Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach
• GLaRE: A Graph-based Landmark Region Embedding Network for Emotion Recognition
• Contrastive Learning through Auxiliary Branch for Video Object Detection
• Domain Adaptation Techniques for Natural and Medical Image Classification
• MoTAS: MoE-Guided Feature Selection from TTS-Augmented Speech for Enhanced Multimodal Alzheimer's Early Screening
• IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection
• CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information
• Prediction of mortality and resource utilization in critical care: a deep learning approach using multimodal electronic health records with natural language processing techniques
• MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection
• More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning
• Developing a Multi-Modal Machine Learning Model For Predicting Performance of Automotive Hood Frames
• Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization
• Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
• Unified Acoustic Representations for Screening Neurological and Respiratory Pathologies from Voice
• End-to-End Analysis of Charge Stability Diagrams with Transformers
• RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration
• A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection
• Turning Tabular Foundation Models into Graph Foundation Models
• Exploring Machine Learning and Language Models for Multimodal Depression Detection
• Coresets from Trajectories: Selecting Data via Correlation of Loss Differences
• Split-Merge Pooling
• HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation
• OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• Dual Attention Networks for Multimodal Reasoning and Matching
• Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
• NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs
• Self-supervised structured object representation learning
• Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models
• RATopo: Improving Lane Topology Reasoning via Redundancy Assignment
• From Research to Reality: Feasibility of Gradient Inversion Attacks in Federated Learning
• AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment
• The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
• SCAR: A Characterization Scheme for Multi-Modal Dataset
• ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation
• Intriguing Properties of Contrastive Losses
• Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
• Advanced Deep Learning Techniques for Classifying Dental Conditions Using Panoramic X-Ray Images
• Weed Detection in Challenging Field Conditions: A Semi-Supervised Framework for Overcoming Shadow Bias and Data Scarcity
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
• Fast 3D Diffusion for Scalable Granular Media Synthesis
• On Surjectivity of Neural Networks: Can you elicit any behavior from your model?
• Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
• EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
• Development and Evaluation of an AI-Driven Telemedicine System for Prenatal Healthcare
• DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
• Get Global Guarantees: On the Probabilistic Nature of Perturbation Robustness
• Few-Shot Connectivity-Aware Text Line Segmentation in Historical Documents
• AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
• Tackling Federated Unlearning as a Parameter Estimation Problem
• No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes
• DeeperGCN: All You Need to Train Deeper GCNs
• ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval
• Enhancing Document VQA Models via Retrieval-Augmented Generation
• TaiBai: A fully programmable brain-inspired processor with topology-aware efficiency
• The GINN framework: a stochastic QED correspondence for stability and chaos in deep neural networks
• HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling
• SegReConcat: A Data Augmentation Method for Voice Anonymization Attack
• Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
• DQEN: Dual Query Enhancement Network for DETR-based HOI Detection
• Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Prediction
• T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation
• PseudoMapTrainer: Learning Online Mapping without HD Maps
• EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding
• Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network
• Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
• Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
• Flatness-aware Curriculum Learning via Adversarial Difficulty
• Class-wise Flooding Regularization for Imbalanced Image Classification
• Enhancing Video-Based Robot Failure Detection Using Task Knowledge
• Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
• Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency
• Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection
• eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
• Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
• UrgenGo: Urgency-Aware Transparent GPU Kernel Launching for Autonomous Driving
• DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Ability
• A Deep Learning Application for Psoriasis Detection
• Bladder Cancer Diagnosis with Deep Learning: A Multi-Task Framework and Online Platform
• PneuGelSight: Soft Robotic Vision-Based Proprioception and Tactile Sensing
• CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering
• CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy
• DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models
• ANO : Faster is Better in Noisy Landscape
• Practical GPU Choices for Earth Observation: ResNet-50 Training Throughput on Integrated, Laptop, and Cloud Accelerators
• BirdRecorder's AI on Sky: Safeguarding birds of prey by detection and classification of tiny objects around wind turbines
• FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
• Robust and Efficient Quantum Reservoir Computing with Discrete Time Crystal
• SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis
• Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
• A Cascaded Residual UNET for Fully Automated Segmentation of Prostate and Peripheral Zone in T2-weighted 3D Fast Spin Echo Images
• Improved Recurrent Neural Networks for Session-based Recommendations
• RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
• GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes
• Transfer learning optimization based on evolutionary selective fine tuning
• BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
• Are Virtual DES Images a Valid Alternative to the Real Ones?
• Integrated Sensing, Communication, and Computation for Over-the-Air Federated Edge Learning
• Lift-the-flap: what, where and when for context reasoning
• BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT
• DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding
• SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
• HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment
• Towards Source-Free Machine Unlearning
• "What happens if..." Learning to Predict the Effect of Forces in Images
• TAIGen: Training-Free Adversarial Image Generation via Diffusion Models
• You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimation
• Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds
• Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method
• Adversarial Hospital-Invariant Feature Learning for WSI Patch Classification
• Real-time Human Detection Model for Edge Devices
• Deep Learning for Taxol Exposure Analysis: A New Cell Image Dataset and Attention-Based Baseline Model
• Understanding Data Influence with Differential Approximation
• Reliable Smoke Detection via Optical Flow-Guided Feature Fusion and Transformer-Based Uncertainty Modeling
• Minimizing Task-Oriented Age of Information for Remote Monitoring with Pre-Identification
• Locality-aware Concept Bottleneck Model
• Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services
• Global-Distribution Aware Scenario-Specific Variational Representation Learning Framework
• WeedSense: Multi-Task Learning for Weed Segmentation, Height Estimation, and Growth Stage Classification
• Large-Scale Image Retrieval with Attentive Deep Local Features
• Computing-In-Memory Dataflow for Minimal Buffer Traffic
• Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
• Towards PerSense++: Advancing Training-Free Personalized Instance Segmentation in Dense Images
• AFABench: A Generic Framework for Benchmarking Active Feature Acquisition
• Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping
• DeepEmoNet: Building Machine Learning Models for Automatic Emotion Recognition in Human Speeches
• Adaptive Interpolating Quantum Transform: A Quantum-Native Framework for Efficient Transform Learning
• DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints
• AnchorSync: Global Consistency Optimization for Long Video Editing
• Mitigating Data Exfiltration Attacks through Layer-Wise Learning Rate Decay Fine-Tuning
• Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement
• Rethinking the Potential of Layer Freezing for Efficient DNN Training
• Maintaining Discrimination and Fairness in Class Incremental Learning
• Effect of Data Augmentation on Conformal Prediction for Diabetic Retinopathy
• A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment
• CLIPSym: Delving into Symmetry Detection with CLIP
• Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer
• In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
• Priority-based Parameter Propagation for Distributed DNN Training
• GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
• OmViD: Omni-supervised active learning for video action detection
• Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles
• One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
• Communication-Efficient Federated Learning with Adaptive Number of Participants
• Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation
• MUFFIN: Mixture of User-Adaptive Frequency Filtering for Sequential Recommendation
• DeH4R: A Decoupled and Hybrid Method for Road Network Graph Extraction
• Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
• AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
• CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
• Fracture Detection and Localisation in Wrist and Hand Radiographs using Detection Transformer Variants
• Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models
• Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
• Revisiting Deep Learning Models for Tabular Data
• Airborne acoustic emission enables sub-scanline keyhole porosity quantification and effective process characterization for metallic laser powder bed fusion
• Few Shot Speaker Recognition using Deep Neural Networks
• Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
• FAMNet: Integrating 2D and 3D Features for Micro-expression Recognition via Multi-task Learning and Hierarchical Attention
• Electromagnetic Signal Modulation Recognition based on Subgraph Embedding Learning
• Genuine multipartite entanglement verification with convolutional neural networks
• Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
• Hotels-50K: A Global Hotel Recognition Dataset
• Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
• One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
• DPad: Efficient Diffusion Language Models with Suffix Dropout
• Graph Concept Bottleneck Models
• Lightweight Convolutional Representations for On-Device Natural Language Processing
• Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
• A Dual-Attention Graph Network for fMRI Data Classification
• GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis
• SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception
• Learning local and global prototypes with optimal transport for unsupervised anomaly detection and localization
• ONG: One-Shot NMF-based Gradient Masking for Efficient Model Sparsification
• Multi-source Multimodal Progressive Domain Adaption for Audio-Visual Deception Detection
• Exploration of Deep Learning Based Recognition for Urdu Text
• An Empirical Model of Large-Batch Training
• SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behavior
• CLAIRE-DSA: Fluoroscopic Image Classification for Quality Assurance of Computer Vision Pipelines in Acute Ischemic Stroke
• Deep Semantic Inference over the Air: An Efficient Task-Oriented Communication System
• Range-Angle Likelihood Maps for Indoor Positioning Using Deep Neural Networks
• Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring
• Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods
• Neural Rendering for Sensor Adaptation in 3D Object Detection
• Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
• Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection
• Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning
• SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
• Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation
• Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors
• DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
• A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
• Towards High-Resolution Industrial Image Anomaly Detection
• Towards SISO Bistatic Sensing for ISAC
• EgoTwin: Dreaming Body and View in First Person
• Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
• Morphological classification of eclipsing binary stars using computer vision methods
• Field-level Reconstruction from Foreground-Contaminated 21-cm Maps
• Constraint-Aware Flow Matching via Randomized Exploration
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML
• Skin Cancer Classification: Hybrid CNN-Transformer Models with KAN-Based Fusion
• FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models
• GazeDETR: Gaze Detection using Disentangled Head and Gaze Representations
• Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
• Omni Survey for Multimodality Analysis in Visual Object Tracking
• Visual-Neural-Inspired Image Inpainting for Specific Objects-of-Interest Imaging
• Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature
• FLARE: Fast Low-rank Attention Routing Engine
• Anatomic Feature Fusion Model for Diagnosing Calcified Pulmonary Nodules on Chest X-Ray
• OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
• Hierarchical Conformal Classification
• MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training
• ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
• Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems
• HDA-SELD: Hierarchical Cross-Modal Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection
• Jamming Identification with Differential Transformer for Low-Altitude Wireless Networks
• WXSOD: A Benchmark for Robust Salient Object Detection in Adverse Weather Conditions
• Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
• Attention Pooling Enhances NCA-based Classification of Microscopy Images
• Splat Feature Solver
• RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
• RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis
• AICRN: Attention-Integrated Convolutional Residual Network for Interpretable Electrocardiogram Analysis
• TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
• Generic Event Boundary Detection via Denoising Diffusion
• Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models
• WiseLVAM: A Novel Framework For Left Ventricle Automatic Measurements
• FedUHD: Unsupervised Federated Learning using Hyperdimensional Computing
• MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding
• Consensus-based Sequence Training for Video Captioning
• Large Kernel Modulation Network for Efficient Image Super-Resolution
• A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
• DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects
• Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
• BConformeR: A Conformer Based on Mutual Sampling for Unified Prediction of Continuous and Discontinuous Antibody Binding Sites
• Dual-species atomic absorption image reconstruction using deep neural networks
• Regularized Ensembles and Transferability in Adversarial Learning
• Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
• Machine Learning-Based AES Key Recovery via Side-Channel Analysis on the ASCAD Dataset
• Mitigating Adversarial Effects Through Randomization
• OVSegDT: Segmenting Transformer for Open-Vocabulary Object Goal Navigation
• Grab-n-Go: On-the-Go Microgesture Recognition with Objects in Hand
• Recurrent Residual Module for Fast Inference in Videos
• Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
• TrajSV: A Trajectory-based Model for Sports Video Representations and Applications
• A Real-time Concrete Crack Detection and Segmentation Model Based on YOLOv11
• Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion Classification
• Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
• Repetitive TMS-based Identification of Methamphetamine-Dependent Individuals Using EEG Spectra
• CoMoNM: A Cost Modeling Framework for Compute-Near-Memory Systems
• LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution
• Model Interpretability and Rationale Extraction by Input Mask Optimization
• Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition
• Harmonized Gradient Descent for Class Imbalanced Data Stream Online Learning
• NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
• Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble
• Probing the Representational Power of Sparse Autoencoders in Vision Models
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
• Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
• A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network
• E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
• A Semi-supervised Generative Model for Incomplete Multi-view Data Integration with Missing Labels
• BeeNet: Reconstructing Flower Shapes from Electric Fields using Deep Learning
• Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
• EMLIO: Minimizing I/O Latency and Energy Consumption for Large-Scale AI Training
• Generalizable Federated Learning using Client Adaptive Focal Modulation
• A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
• Axis-level Symmetry Detection with Group-Equivariant Representation
• Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
• Symmetry-Constrained Multi-Scale Physics-Informed Neural Networks for Graphene Electronic Band Structure Prediction
• Lightweight CNNs for Embedded SAR Ship Target Detection and Classification
• Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
• A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
• HyperTea: A Hypergraph-based Temporal Enhancement and Alignment Network for Moving Infrared Small Target Detection
• Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
• Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
• FIND-Net -- Fourier-Integrated Network with Dictionary Kernels for Metal Artifact Reduction
• Fourier-Guided Attention Upsampling for Image Super-Resolution
• On Spectral Properties of Gradient-based Explanation Methods
• Adapting SAM via Cross-Entropy Masking for Class Imbalance in Remote Sensing Change Detection
• PSScreen: Partially Supervised Multiple Retinal Disease Screening
• EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba
• On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
• DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations
• Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
• CTAP: Complementary Temporal Action Proposal Generation
• Super LiDAR Reflectance for Robotic Perception
• PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection
• Improving OCR for Historical Texts of Multiple Languages
• Glo-UMF: A Unified Multi-model Framework for Automated Morphometry of Glomerular Ultrastructural Characterization
• SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems
• Efficient Image Denoising Using Global and Local Circulant Representation
• BERT-VQA: Visual Question Answering on Plots
• Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images
• Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets
• Hierarchical Representations for Efficient Architecture Search
• Explainable AI Technique in Lung Cancer Detection Using Convolutional Neural Networks
• Out-of-Distribution Detection using Counterfactual Distance
• Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
• Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
• Empowering Morphing Attack Detection using Interpretable Image-Text Foundation Model
• January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis
• SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
• SHREC'25 Track on Multiple Relief Patterns: Report and Analysis
• Perceptual Reality Transformer: Neural Architectures for Simulating Neurological Perception Conditions
• Reverse Convolution and Its Applications to Image Restoration
• BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
• DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning
• Analysis of the Compaction Behavior of Textile Reinforcements in Low-Resolution In-Situ CT Scans via Machine-Learning and Descriptor-Based Methods
• TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional Specialization
• The Role of Radiographic Knee Alignment in Total Knee Replacement Outcomes and Opportunities for Artificial Intelligence-Driven Assessment
• Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing System
• Multimodal Sheaf-based Network for Glioblastoma Molecular Subtype Prediction
• NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generation
• Artificial Intelligence, Domain AI Readiness, and Firm Productivity
• Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion
• TFPose: Direct Human Pose Estimation with Transformers
• Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks
• Scalable Person Re-identification on Supervised Smoothed Manifold
• A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation
• WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization
• Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
• Dynamical Alignment: A Principle for Adaptive Neural Computation
• Holistic Heterogeneous Scheduling for Autonomous Applications using Fine-grained, Multi-XPU Abstraction
• Large-Small Model Collaborative Framework for Federated Continual Learning
• Deep Learning for Automated Identification of Vietnamese Timber Species: A Tool for Ecological Monitoring and Conservation
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
• What-Meets-Where: Unified Learning of Action and Contact Localization in a New Dataset
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
• Semantic-Aware Reconstruction Error for Detecting AI-Generated Images
• Predicting protein variant properties with electrostatic representations
• Inter-expert reliability in multi-field-of-view automatic drusen segmentation analysis using optical coherence tomography
• Harnessing Input-Adaptive Inference for Efficient VLN
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
• Low-Regret and Low-Complexity Learning for Hierarchical Inference
• Label Smoothing is a Pragmatic Information Bottleneck
• Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning
• Frequency-Assisted Adaptive Sharpening Scheme Considering Bitrate and Quality Tradeoff
• Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
• DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimation
• SafeFix: Targeted Model Repair via Controlled Image Generation
• Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
• P-CAFE: Personalized Cost-Aware Incremental Feature Selection For Electronic Health Records
• Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation
• Fact-Checking at Scale: Multimodal AI for Authenticity and Context Verification in Online Media
• QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection
• Feature Enhancement Network: A Refined Scene Text Detector
• Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
• Resource-Aware Aggregation and Sparsification in Heterogeneous Ensemble Federated Learning
• Biased Local SGD for Efficient Deep Learning on Heterogeneous Systems
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
• Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space
• Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents
• Adaptive High-Frequency Preprocessing for Video Coding
• Image selective encryption analysis using mutual information in CNN based embedding space
• Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
• Pep2Prob Benchmark: Predicting Fragment Ion Probability for MS²-based Proteomics
• Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation
• Towards Efficient and Practical GPU Multitasking in the Era of LLM
• IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
• Identifying nonequilibrium degrees of freedom in high-dimensional stochastic systems
• Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions
• RedDino: A foundation model for red blood cell analysis
• TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation
• Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition
• Deep Generative Models for Discrete Genotype Simulation
• Selective Contrastive Learning for Weakly Supervised Affordance Grounding
• EFU: Enforcing Federated Unlearning via Functional Encryption
• Morphological Analysis of Semiconductor Microstructures using Skeleton Graphs
• Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models
• AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
• Collaborative Learning of Scattering and Deep Features for SAR Target Recognition with Noisy Labels
• GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm
• ImageDDI: Image-enhanced Molecular Motif Sequence Representation for Drug-Drug Interaction Prediction
• Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning
• CNN Acceleration by Low-rank Approximation with Quantized Factors
• Fast and Generalizable parameter-embedded Neural Operators for Lithium-Ion Battery Simulation
• CBDES MoE: Hierarchically Decoupled Mixture-of-Experts for Functional Modules in Autonomous Driving
• Enhanced Generative Structure Prior for Chinese Text Image Super-resolution
• Vision-Based Localization and LLM-based Navigation for Indoor Environments
• Prototype-Guided Curriculum Learning for Zero-Shot Learning
• MIMIC: Multimodal Inversion for Model Interpretation and Conceptualization
• Enhancing Small-Scale Dataset Expansion with Triplet-Connection-based Sample Re-Weighting
• Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformer
• Adaptive Source-Channel Coding for Semantic Communications
• Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
• Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities
• Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos
• When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
• Revisiting Data Attribution for Influence Functions
• SUIT: Spatial-Spectral Union-Intersection Interaction Network for Hyperspectral Object Tracking
• Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling
• EventRR: Event Referential Reasoning for Referring Video Object Segmentation
• Lightweight Multi-Scale Feature Extraction with Fully Connected LMF Layer for Salient Object Detection
• Large-scale Multi-sequence Pretraining for Generalizable MRI Analysis in Versatile Clinical Applications
• SketchConcept: Sketching-based Concept Recomposition for Product Design using Generative AI
• ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
• Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
• Representation Understanding via Activation Maximization
• DexFruit: Dexterous Manipulation and Gaussian Splatting Inspection of Fruit
• ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting
• Membership Inference Attacks with False Discovery Rate Control
• QuiZSF: An efficient data-model interaction framework for zero-shot time-series forecasting
• eMotions: A Large-Scale Dataset and Audio-Visual Fusion Network for Emotion Analysis in Short-form Videos
• Data-Efficient Neural Training with Dynamic Connectomes
• Label Inference Attacks against Federated Unlearning
• TADoc: Robust Time-Aware Document Image Dewarping
• Can Multitask Learning Enhance Model Explainability?
• BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
• Sensory robustness through top-down feedback and neural stochasticity in recurrent vision models
• Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery
• Rethinking Key-frame-based Micro-expression Recognition: A Robust and Accurate Framework Against Key-frame Errors
• CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation
• Position: Ideas Should be the Center of Machine Learning Research
• Practical Block-wise Neural Network Architecture Generation
• Learnable pooling with Context Gating for video classification
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods
• SiMiC: Context-aware silicon microstructure characterization using attention-based convolutional neural networks for field-emission tip analysis
• Feature-Space Oversampling for Addressing Class Imbalance in SAR Ship Classification
• A Classification-Aware Super-Resolution Framework for Ship Targets in SAR Imagery
• Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd
• Zero-shot self-supervised learning of single breath-hold magnetic resonance cholangiopancreatography (MRCP) reconstruction
• Vertex reconstruction in the TAO experiment
• Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation
• Learning Representations of Satellite Images with Evaluations on Synoptic Weather Events
• Ensemble-Based Graph Representation of fMRI Data for Cognitive Brain State Classification
• MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging
• Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
• Efficient Bayer-Domain Video Computer Vision with Fast Motion Estimation and Learned Perception Residual
• Hybrid(Transformer+CNN)-based Polyp Segmentation
• Hybrid Physics-Machine Learning Models for Quantitative Electron Diffraction Refinements
• ASAudio: A Survey of Advanced Spatial Audio Research
• GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving
• Accelerating Quantum Monte Carlo Calculations with Set-Equivariant Architectures and Transfer Learning
• Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation
• MCA: 2D-3D Retrieval with Noisy Labels via Multi-level Adaptive Correction and Alignment
• FedX: Explanation-Guided Pruning for Communication-Efficient Federated Learning in Remote Sensing
• AGI for the Earth, the path, possibilities and how to evaluate intelligence of models that work with Earth Observation Data?
• Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
• Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
• Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning
• Multi-view Gaze Target Estimation
• When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework
• SMOL-MapSeg: Show Me One Label as prompt
• Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification
• Does Multimodality Improve Recommender Systems as Expected? A Critical Analysis and Future Directions
• Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach
• Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
• CoCAViT: Compact Vision Transformer with Robust Global Coordination
• VS-LLM: Visual-Semantic Depression Assessment based on LLM for Drawing Projection Test
• Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
• EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery
• SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images
• Neural Estimation of Information Leakage for Secure Communication System Design
• Human Activity Recognition from Smartphone Sensor Data for Clinical Trials
• Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering
• X-MoGen: Unified Motion Generation across Humans and Animals
• PSEO: Optimizing Post-hoc Stacking Ensemble Through Hyperparameter Tuning
• Digital Twin Channel-Aided CSI Prediction: An Environment-Based Subspace Extraction Approach for Achieving Low Overhead and High Robustness
• HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
• Learning from Similarity-Confidence and Confidence-Difference
• Multimodal Fact Checking with Unified Visual, Textual, and Contextual Representations
• DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic
• ULU: A Unified Activation Function
• Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks
• A Context-aware Attention and Graph Neural Network-based Multimodal Framework for Misogyny Detection
• Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
• MedMambaLite: Hardware-Aware Mamba for Medical Image Classification
• Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification
• Unified modality separation: A vision-language framework for unsupervised domain adaptation
• FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective
• Tesserae: Scalable Placement Policies for Deep Learning Workloads
• Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering
• ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates
• SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
• Functional Connectivity Graph Neural Networks
• Few-Shot Deployment of Pretrained MRI Transformers in Brain Imaging Tasks
• Surformer v1: Transformer-Based Surface Classification Using Tactile and Vision Features
• Gaussian mixture layers for neural networks
• Occupancy Learning with Spatiotemporal Memory
• BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning
• PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
• How Does Bilateral Ear Symmetry Affect Deep Ear Features?
• BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
• Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation
• Drone Detection with Event Cameras
• TopKD: Top-scaled Knowledge Distillation
• RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection
• Learning Robust Intervention Representations with Delta Embeddings
• Benchmarking Foundation Models for Mitotic Figure Classification
• InfoQ: Mixed-Precision Quantization via Global Information Flow
• WSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification
• S2M3: Split-and-Share Multi-Modal Models for Distributed Multi-Task Inference on the Edge
• Revisiting Continual Semantic Segmentation with Pre-trained Vision Models
• FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning
• Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark
• Automated ultrasound doppler angle estimation using deep learning
• DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification
• DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models
• Boosting Adversarial Transferability via Residual Perturbation Attack
• Bootstrap Deep Spectral Clustering with Optimal Transport
• Multilingual Source Tracing of Speech Deepfakes: A First Benchmark
• UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
• Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution: A Comprehensive Study
• Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement
• CLIPVehicle: A Unified Framework for Vision-based Vehicle Search
• SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
• Hybrid Quantum--Classical Machine Learning Potential with Variational Quantum Circuits
• Convolutional autoencoders for the reconstruction of three-dimensional interfacial multiphase flows
• Slice or the Whole Pie? Utility Control for AI Models
• TNet: Terrace Convolutional Decoder Network for Remote Sensing Image Semantic Segmentation
• FeDaL: Federated Dataset Learning for Time Series Foundation Models
• CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
• Decoupled Contrastive Learning for Federated Learning
• Investigating the Impact of Large-Scale Pre-training on Nutritional Content Estimation from 2D Images
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Deep learning framework for crater detection and identification on the Moon and Mars
• Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images
• AttZoom: Attention Zoom for Better Visual Features
• Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
• DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
• SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks
• SoilNet: A Multimodal Multitask Model for Hierarchical Classification of Soil Horizons
• MURAUER: Mapping Unlabeled Real Data for Label AUstERity
• 4D-PreNet: A Unified Preprocessing Framework for 4D-STEM Data Analysis
• GaitAdapt: Continual Learning for Evolving Gait Recognition
• A Multimodal Late Fusion Model for E-Commerce Product Classification
• Evaluating the Predictive Value of Preoperative MRI for Erectile Dysfunction Following Radical Prostatectomy
• MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
• Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations
• DeepAP: Deep Learning-based Aperture Photometry Feasibility Assessment and Aperture Size Prediction
• Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation
• Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution
• BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
• The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustness
• PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting
• COFFEE: A Shadow-Resilient Real-Time Pose Estimator for Unknown Tumbling Asteroids using Sparse Neural Networks
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
• Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection
• Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning
• T2UE: Generating Unlearnable Examples from Text Descriptions
• Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
• On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach
• Adversarial Attention Perturbations for Large Object Detection Transformers
• Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
• Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices
• Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentation
• Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections
• Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review
• MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine
• Neural Networks with Orthogonal Jacobian
• Communication and Computation Efficient Split Federated Learning in O-RAN
• Rethinking Transparent Object Grasping: Depth Completion with Monocular Depth Estimation and Instance Mask
• ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning
• Hydra: Accurate Multi-Modal Leaf Wetness Sensing with mm-Wave and Camera Fusion
• TRUDI and TITUS: A Multi-Perspective Dataset and A Three-Stage Recognition System for Transportation Unit Identification
• Assessing the Impact of Image Super Resolution on White Blood Cell Classification Accuracy
• Is Uncertainty Quantification a Viable Alternative to Learned Deferral?
• FAIR-Pruner: Leveraging Tolerance of Difference for Flexible Automatic Layer-Wise Neural Network Pruning
• FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation
• Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training
• Test-Time Model Adaptation for Quantized Neural Networks
• TrackletGait: A Robust Framework for Gait Recognition in the Wild
• AdvGAN++ : Harnessing latent layers for adversary generation
• DySTop
• Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
• Semi-Supervised Dual-Threshold Contrastive Learning for Ultrasound Image Classification and Segmentation
• Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
• Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling
• mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Arrhythmia
• YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges
• Accurate and Interpretable Postmenstrual Age Prediction via Multimodal Large Language Model
• PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments
• Multi-contrast machine learning improves schistosomiasis diagnostic performance
• NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
• Neuromorphic Computing with Multi-Frequency Oscillations: A Bio-Inspired Approach to Artificial Intelligence
• SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis
• Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation
• Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
• AID4AD: Aerial Image Data for Automated Driving Perception
• Quantum Machine Learning-based Test Oracle for Autonomous Mobile Robots
• Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations
• Enhancing Object Discovery for Unsupervised Instance Segmentation and Object Detection
• Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Dataset
• Forecasting West Nile virus with deep graph encoders
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
• GlaBoost: A multimodal Structured Framework for Glaucoma Risk Stratification
• InspectVLM: Unified in Theory, Unreliable in Practice
• M³AD: Multi-task Multi-gate Mixture of Experts for Alzheimer's Disease Diagnosis with Conversion Pattern Modeling
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Boosting Generalization Performance in Model-Heterogeneous Federated Learning Using Variational Transposed Convolution
• Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models
• Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction
• IMU: Influence-guided Machine Unlearning
• Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
• CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis
• MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection
• Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancer
• Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements
• Adaptive LiDAR Scanning: Harnessing Temporal Cues for Efficient 3D Object Detection via Multi-Modal Fusion
• CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation
• Adverse Weather-Independent Framework Towards Autonomous Driving Perception through Temporal Correlation and Unfolded Regularization
• Glass Surface Segmentation with an RGB-D Camera via Weighted Feature Fusion for Service Robots
• Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Models
• VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems
• Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems
• SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritization
• Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
• Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
• MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model
• OmniEvent: Unified Event Representation Learning
• Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models
• The Vanishing Gradient Problem for Stiff Neural Differential Equations
• PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
• Physically-based Lighting Generation for Robotic Manipulation
• Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms
• DeepGB-TB: A Risk-Balanced Cross-Attention Gradient-Boosted Convolutional Network for Rapid, Interpretable Tuberculosis Screening
• Enhancing Diffusion-based Dataset Distillation via Adversary-Guided Curriculum Sampling
• Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
• Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
• Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
• Calibrated Prediction Set in Fault Detection with Risk Guarantees via Significance Tests
• Deep Learning for Pavement Condition Evaluation Using Satellite Imagery
• ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models
• Classification of Brain Tumors using Hybrid Deep Learning Models
• Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency
• Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust
• Large Language Models Facilitate Vision Reflection in Image Classification
• COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition
• Evading Data Provenance in Deep Neural Networks
• Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans
• AutoSIGHT: Automatic Eye Tracking-based System for Immediate Grading of Human experTise
• A Simple and Effective Method for Uncertainty Quantification and OOD Detection
• Masked Omics Modeling for Multimodal Representation Learning across Histopathology and Molecular Profiles
• Can Large Pretrained Depth Estimation Models Help With Image Dehazing?
• Using Deep Learning for Segmentation and Counting within Microscopy Data
• CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometry
• Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
• DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification
• HannesImitation: Grasping with the Hannes Prosthetic Hand via Imitation Learning
• Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency
• Representation Shift: Unifying Token Compression with FlashAttention
• Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training
• ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
• Multimodal Referring Segmentation: A Survey
• Multi-Layer Attention is the Amplifier of Demonstration Effectiveness
• Backdoor Attacks on Deep Learning Face Detection
• UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken
• Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
• BOOD: Boundary-based Out-Of-Distribution Data Generation
• MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encoder
• Improving Multimodal Contrastive Learning of Sentence Embeddings with Object-Phrase Alignment
• Deep Joint Source-Channel Coding for Small Satellite Applications
• Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition
• Segmenting proto-halos with vision transformers
• Explainable Image Classification with Reduced Overconfidence for Tissue Characterisation
• Max-Mahalanobis Linear Discriminant Analysis Networks
• Deep Learning-based Prediction of Clinical Trial Enrollment with Uncertainty Estimates
• Mamba-based Efficient Spatio-Frequency Motion Perception for Video Camouflaged Object Detection
• DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction
• Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation
• Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks
• 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
• Deep Contextual Recurrent Residual Networks for Scene Labeling
• I Am Big, You Are Little; I Am Right, You Are Wrong
• Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
• Foundations and Models in Modern Computer Vision: Key Building Blocks in Landmark Architectures
• FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models
• SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy
• CUHK-EE Systems for the vTAD Challenge at NCMMSC 2025