Adam: A Method for Stochastic Optimization

2014/12/22 by Diederik P. Kingma, Jimmy Ba, Kingma, Diederik P. +1 · 2898 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Stochastic Gradient Optimization Techniques

paper · doi:10.48550/arxiv.1412.6980

openalex publication_date 2014/12/22 · openalex created_date 2019/05/03 · openalex updated_date 2026/07/31

Abstract

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• Improving neural networks by preventing co-adaptation of feature detectors
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Cited by

• Deep classifier kriging for probabilistic spatial prediction of air quality index
• SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context
• The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis
• Deep Learning for Art Market Valuation
• Reconstructing Relativistic Magnetohydrodynamics with Physics-Informed Neural Networks
• A PAC-Bayesian approach to generalization for quantum models
• To What Extent Are Star Cluster Ages Encoded in Their Environments? Exploring the Spatial Distribution of Age-Related Information with PHANGS-HST Imaging and Convolutional Neural Networks
• Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning
• Clinically Calibrated Machine Learning Benchmarks for Large-Scale Multi-Disorder EEG Classification
• Visual Autoregressive Modelling for Monocular Depth Estimation
• FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking
• DeepNC: A Fast GNN-based Pre-Verification Surrogate for TSN Configuration
• Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
• JParc: Joint cortical surface parcellation with registration
• Expert System for Bitcoin Forecasting: Integrating Global Liquidity via TimeXer Transformers
• Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors
• Towards Signboard-Oriented Visual Question Answering: ViSignVQA Dataset, Method and Benchmark
• PaperNet: Efficient Temporal Convolutions and Channel Residual Attention for EEG Epilepsy Detection
• AudioGAN: A Compact and Efficient Framework for Real-Time High-Fidelity Text-to-Audio Generation
• Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification
• BeyondFusion: Self-Aligned Latent Diffusion for Calibration-Free Infrared Super-Resolution and Infrared-Visible Fusion
• Methods for Inferring Interaction Potentials from Cross-Linking Mass Spectrometry Data
• PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation
• Stabilizing Deep Reconstruction Operators with Contractive Anchoring
• Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings
• Identifying Dolphin Whistle Producers With Deep Learning: Moving Beyond Signature Whistles
• Enhancing Code Understanding for Impact Analysis by Combining Transformers and Program Dependence Graphs
• Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features
• Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search
• Perturbative-NeuSA: A Structured Spectral Framework for Time-Dependent PDEs
• FloAff-Kitchen: Bridging Navigation and Manipulation via Canonical and Progressive Floor Affordance Learning
• SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation
• Electromagnetic Neural Network for Direction-of-Arrival Estimation
• What do Reward Models Memorize?
• DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing
• The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows
• Amortized Posteriors for Estimation of Material Constitutive Parameters from Multimodal Measurements on Small Punch Tests
• Molecular electrostatic potentials from machine learning models for dipole and quadrupole predictions
• CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models
• Nuclear Many-Body Systems as Benchmarks for Quantum Computing
• FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery
• Simplex Demixing: Disentangling Multiple Light-Flavor Jets at Colliders
• Score-Based Stabilization for Time-Dependent Problems
• Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors
• P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning
• Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation
• Inferring Missing Trajectory Data with Temporal Convolutional Networks
• Fourier Feature Physics-Informed Neural Networks for Elasto-Plastic Analysis of Geomaterials with a Non-Associative Mohr-Coulomb Model
• Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding
• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement
• Learning Association via Track-Detection Matching for Multi-Object Tracking
• Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
• Controlling Embedding Spaces with Text-Conditioned Transformations
• Frequency-Aware Dual-Stream Learning for Balanced Realism and Fidelity in Electron Microscopy Imaging
• Statistical Mechanics of Thermal Diffusion in Rough Energy Landscapes
• URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars
• Nitrous Oxide Emissions Across Sub‐Saharan Africa: Meta‐Analysis and Data‐Driven Modeling
• Symmetry Alone Is Not an Ansatz: Task-Aligned Interactions in Equivariant Quantum Circuits
• polyDAG: Polynomial Acyclicity Constraints for Efficient Continuous Causal Discovery in Visual Semantic Graphs
• Evaluating the resolution of AI-based accelerated MR reconstruction using a deep learning-based model observer
• Diffusion models for SU(2) lattice gauge theory in two dimensions
• WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems
• GeoDecider: An Evidence-Grounded Agent for Geological Interpretation via Deliberative Reasoning
• Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
• Latent Space Probing for Adult Content Detection in Video Generative Models
• PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing
• Optimize discrete loss with finite-difference physics constraint and time-stepping for PDE solving
• FlashEvaluator: Expanding Search Space with Parallel Sequence-Level Evaluation
• A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
• Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
• Forward and Inverse Mantle Convection with Neural Operators
• Ordering-based Causal Discovery via Generalized Score Matching
• The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs
• Calibrating adaptive smoothing methods for freeway traffic reconstruction
• ARCANE–Early Detection of Interplanetary Coronal Mass Ejections
• The roles of bulk and surface thermodynamics in the selective adsorption of a confined azeotropic mixture
• Patch-Discontinuity Mining for Generalized Deepfake Detection
• LVLM-Aided Alignment of Task-Specific Vision Models
• InstructDubber: Instruction-based Alignment for Zero-shot Movie Dubbing
• Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors
• Programmable Photonic Circuits with Embedded Feedback for Parallel Multi-Wavelength Operations
• Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentation
• More Consistent Accuracy PINN via Alternating Easy-Hard Training
• Global-Graph Guided and Local-Graph Weighted Contrastive Learning for Unified Clustering on Incomplete and Noise Multi-View Data
• Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction
• LLM-Driven Feature-Level Adversarial Attacks on Android Malware Detectors
• TexAvatars : Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars
• Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
• PUFM++: Point Cloud Upsampling via Enhanced Flow Matching
• Generalization of Diffusion Models Arises with a Balanced Representation Space
• Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data
• UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
• Programmable Optical Spectrum Shapers as Computing Primitives for Accelerating Convolutional Neural Networks
• Over-the-Air Goal-Oriented Communications
• Explainable time-series forecasting with sampling-free SHAP for Transformers
• Neural Scaling Laws for Learning-based Identification of Nonlinear Systems
• Machine-learning techniques for model-independent searches in dijet final states
• EnvSSLAM-FFN: Lightweight Layer-Fused System for ESDD 2026 Challenge
• AprielGuard
• FaithLens: Detecting and Explaining Faithfulness Hallucination
• SpatialNet with Binaural Loss Function for Correcting Binaural Signal Matching Outputs under Head Rotations
• Orthogonal Activation with Implicit Group-Aware Bias Learning for Class Imbalance
• BiCoR-Seg: Bidirectional Co-Refinement Framework for High-Resolution Remote Sensing Image Segmentation
• Semi-automated estimation of hydrogenic initial states for localized Wannier functions
• Non-Contrast CT Esophageal Varices Grading through Clinical Prior-Enhanced Multi-Organ Analysis
• MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
• Variational Autoregressive Networks Applied to ϕ⁴ Field Theory Systems
• Optimal Uncertainty Quantification under General Moment Constraints on Input Subdomains
• Sprecher Networks: A Parameter-Efficient Kolmogorov-Arnold Architecture
• Learning General Policies with Policy Gradient Methods
• PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
• D²Stream: Decoupled Dual-Stream Temporal-Speaker Interaction for Audio-Visual Speaker Detection
• Randomized time stepping of nonlinearly parametrized solutions of evolution problems
• DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis
• Alternative positional encoding functions for neural transformers
• Misbehavior Forecasting for Focused Autonomous Driving Systems Testing
• Non-stationary Spatial Modeling Using Fractional SPDEs
• PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation
• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
• Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts
• Neural Network Construction of the Equation of State from Relativistic ab initio Calculations
• BeamformNet: Deep Learning-Based Beamforming Method for DoA Estimation via Implicit Spatial Signal Focusing and Noise Suppression
• Learning vertical coordinates via automatic differentiation of a dynamical core
• Data-Driven Calibration of Large Liquid Detectors with Unsupervised Learning
• Robust and scalable simulation-based inference for gravitational wave signals with gaps
• Plasticine: A Traceable Diffusion Model for Medical Image Translation
• Physics-Informed Neural Solvers for Periodic Quantum Eigenproblems
• HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
• InstructNet: A Novel Approach for Multi-Label Instruction Classification through Advanced Deep Learning
• Offline Behavioral Data Selection
• FairExpand: Individual Fairness on Graphs with Partial Similarity Information
• Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra
• Estimating Solvation Free Energies with Boltzmann Generators
• Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
• SERA-H: Beyond Native Sentinel Spatial Limits for High-Resolution Canopy Height Mapping
• Microstructure-based Variational Neural Networks for Robust Uncertainty Quantification in Materials Digital Twins
• AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning
• Learning Spatio-Temporal Feature Representations for Video-Based Gaze Estimation
• Xiaomi MiMo-VL-Miloco Technical Report
• Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors
• Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
• Multi-level distortion-aware deformable network for omnidirectional image super-resolution
• SynergyWarpNet: Attention-Guided Cooperative Warping for Neural Portrait Animation
• Vision-Language Model Guided Image Restoration
• Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors
• MAPPO-LCR: Multi-Agent Proximal Policy Optimization with Local Cooperation Reward in Spatial Public Goods Games
• Peeking Into The Future For Contextual Biasing
• DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations
• Deep Learning-Enabled Multi-Tag Detection in Ambient Backscatter Communications
• Towards an agnostic algorithm for sampling empirical structure models: The case of Uranus and Neptune
• Instant Expressive Gaussian Head Avatars at Over 100 FPS
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
• What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels
• KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals
• TreeNet: A Light Weight Model for Low Bitrate Image Compression
• Symbolic Pauli Propagation for Gradient-Enabled Pre-Training of Quantum Circuits
• Exploiting Radio Frequency Fingerprints for Device Identification: Tackling Cross-receiver Challenges in the Source-data-free Scenario
• Learning holographic QCD with unflavoured meson spectra
• Real-Time Human-Robot Interaction Intent Detection Using RGB-based Pose and Emotion Cues with Cross-Camera Model Generalization
• Sharpness-aware Second-order Latent Factor Model for High-dimensional and Incomplete Data
• Latent-space variational data assimilation in two-dimensional turbulence
• LAPX: Lightweight Hourglass Network with Global Context
• CauSTream: Causal Spatio-Temporal Representation Learning for Streamflow Forecasting
• SMART: Semantic Matching Contrastive Learning for Partially View-Aligned Clustering
• A Conditioned UNet for Music Source Separation
• RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting
• ST-DETrack: Identity-Preserving Branch Tracking in Entangled Plant Canopies via Dual Spatiotemporal Evidence
• CLIP-FTI: Fine-Grained Face Template Inversion via CLIP-Driven Attribute Conditioning
• Trustworthy Neighborhoods Mining: Homophily-Aware Neutral Contrastive Learning for Graph Clustering
• Enhancing Alzheimer's Detection through Late Fusion of Multi-Modal EEG Features
• Huayu: Advanced Real-Time Precipitation Estimation from Geostationary Satellite
• QoS-Aware Hierarchical Reinforcement Learning for Joint Link Selection and Trajectory Optimization in SAGIN-Supported UAV Mobility Management
• Meta-learners for few-shot weakly-supervised optic disc and cup segmentation on fundus images
• RELIC-GNN: Efficient State Registers Identification with Graph Neural Network for Reverse Engineering
• A Parameter-Free Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals
• Borrowing from anything: A generalizable framework for reference-guided instance editing
• Dynamic Learning Rate Scheduling based on Loss Changes Leads to Faster Convergence
• Deep learning water-unsuppressed MRSI at ultra-high field for simultaneous quantitative metabolic, susceptibility and myelin water imaging
• Decoding Orbital Angular Momentum in Turbid Tissue-like Scattering Medium via Fourier-Domain Deep Learning
• A Hybrid Reactive-Proactive Auto-scaling Algorithm for SLA-Constrained Edge Computing
• Graph Signal Denoising Using Regularization by Denoising and Its Parameter Estimation
• Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms
• Optimizing the Adversarial Perturbation with a Momentum-based Adaptive Matrix
• Learning Minimal Representations of Fermionic Ground States
• Agile Affine Frequency Division Multiplexing
• Consistent Instance Field for Dynamic Scene Understanding
• AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation
• Maximum Mean Discrepancy with Unequal Sample Sizes via Generalized U-Statistics
• An intercomparison of generative machine learning methods for downscaling precipitation at fine spatial scales
• Verifying Rumors via Stance-Aware Structural Modeling
• Do Reviews Matter for Recommendations in the Era of Large Language Models?
• StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion
• Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
• No One Left Behind: How to Exploit the Incomplete and Skewed Multi-Label Data for Conversion Rate Prediction
• Measurement of Material Volume Fractions in a Microwave Resonant Cavity Sensor Using Convolutional Neural Network
• Differentiable Material Point Method for the Control of Deformable Objects
• Computational tuning of the elastic properties of low- and high-entropy ultra-high temperature ceramics
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency
• StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completion
• Time-aware UNet and super-resolution deep residual networks for spatial downscaling
• Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization
• Light Field Based 6DoF Tracking of Previously Unobserved Objects
• Learning Terrain Aware Bipedal Locomotion via Reduced Dimensional Perceptual Representations
• Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
• Neural Control Barrier Functions for Signal Temporal Logic Specifications with Input Constraints
• Enhancing polynomial approximation of continuous functions by composition with homeomorphisms
• OLR-WAA: Adaptive and Drift-Resilient Online Regression with Dynamic Weighted Averaging
• AttenGW: A Lightweight Attention-Based Multi-Detector Gravitational-Wave Detection Pipeline
• Learning Dynamics in Memristor-Based Equilibrium Propagation
• Hybrid algorithm combining matched filtering and convolutional neural networks for searching gravitational waves from binary black hole mergers
• TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion
• Algorithms for Achieving Subpixel Resolution in Muon Tomography
• All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
• On the Dangers of Bootstrapping Generation for Continual Learning and Beyond
• Integrated Prediction and Multi-period Portfolio Optimization
• Personalized Pricing in Social Networks with Individual and Group Fairness Considerations
• Machine learned potential for defected single layer hexagonal boron nitride
• Neural Network-based Partial-Linear Single-Index Models for Environmental Mixtures Analysis
• Assisted Refinement Network Based on Channel Information Interaction for Camouflaged and Salient Object Detection
• Projected Sobolev Natural Gradient Descent for Efficient Neural Network Solution of the Gross-Pitaevskii Equation
• CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?
• A Variable Step Sizes Frequency Offsets-Compensated Least Mean Squares Algorithm
• Weakly Supervised Tuberculosis Localization in Chest X-rays through Knowledge Distillation
• GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting
• SoccerMaster: A Vision Foundation Model for Soccer Understanding
• RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds
• Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network
• Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignment
• ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs
• T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground
• HypeR Adaptivity: Joint hr-Adaptive Meshing via Hypergraph Multi-Agent Deep Reinforcement Learning
• DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
• A Model-Guided Neural Network Method for the Inverse Scattering Problem
• Machine Learning Optimization of BEGe Detector Event Selection in the VIP Experiment
• Content-Adaptive Image Retouching Guided by Attribute-Based Text Representation
• Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation
• BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks
• Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
• Robust Speech Activity Detection in the Presence of Singing Voice
• Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization
• GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars
• BISTRO -- A Bi-Fidelity Stochastic Gradient Framework using Trust-Regions for Optimization Under Uncertainty
• Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
• Graph Deep Learning for Intracranial Aneurysm Blood Flow Simulation and Risk Assessment
• Adaptive Regularized Newton Method with Inexact Hessian
• Neural Ordinary Differential Equations for Simulating Metabolic Pathway Dynamics from Time-Series Multiomics Data
• VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation
• Beyond Diagonal RIS-assisted MIMO Transmission: Beamforming Gain and Capacity Optimization
• Leveraging Multispectral Sensors for Color Correction in Mobile Cameras
• Detection of Digital Facial Retouching utilizing Face Beauty Information
• Turning Threat into Opportunity: DRL-Powered Anti-Jamming via Energy Harvesting in UAV-Disrupted Channels
• Bi²MAC: Bimodal Bi-Adaptive Mask-Aware Convolution for Remote Sensing Pansharpening
• PolySwyft: sequential simulation-based nested sampling
• Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making
• OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer
• ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making
• A Bayesian latent class reinforcement learning framework to capture adaptive, feedback-driven travel behaviour
• Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders
• Identification of Deforestation Areas in the Amazon Rainforest Using Change Detection Models
• Neural Compress-and-Forward for the Primitive Diamond Relay Channel
• SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification
• Trapped Fermions Through Kolmogorov-Arnold Wavefunctions
• Augmented Neural Ordinary Differential Equations for Power System Identification
• Enhancing Medical Cross-Modal Hashing Retrieval using Dropout-Voting Mixture-of-Experts Fusion
• A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
• MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer
• Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects
• MultiAPI Spoof: A Multi-API Dataset and Local-Attention Network for Speech Anti-spoofing Detection
• Machine learning in an expectation-maximisation framework for nowcasting
• Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Clouds
• PICKT: Practical Interlinked Concept Knowledge Tracing for Personalized Learning using Knowledge Map Concept Relations
• Enhanced Chest Disease Classification Using an Improved CheXNet Framework with EfficientNetV2-M and Optimization-Driven Learning
• Machine Learning-based Unfolding for Cross Section Measurements in the Presence of Nuisance Parameters
• From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images
• DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation
• Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior
• Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces
• SparsePixels: Efficient Convolution for Sparse Data on FPGAs
• Modeling Spatio-temporal Extremes via Conditional Variational Autoencoders
• A Novel Deep Neural Network Architecture for Real-Time Water Demand Forecasting
• From Forecast to Action: A Deep Learning Model for Predicting Power Outages During Tropical Cyclones
• Learning to Hedge Swaptions
• PRIMRose: Insights into the Per-Residue Energy Metrics of Proteins with Double InDel Mutations using Deep Learning
• Modeling Contextual Passage Utility for Multihop Question Answering
• Machine-learning-enabled interpretation of tribological deformation patterns in large-scale MD data
• Kitaev Meets AKLT: Competing Quantum Disorder in Spin-3/2 Honeycomb Systems
• Learning Without Time-Based Embodiment Resets in Soft-Actor Critic
• A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation
• A Latent Variable Framework for Scaling Laws in Large Language Models
• Physics-Grounded Attached Shadow Detection Using Approximate 3D Geometry and Light Direction
• Probabilistic Weapon Engagement Zones for a Turn Constrained Pursuer
• Learning the Cosmic Web: Graph-based Classification of Simulated Galaxies by their Dark Matter Environments
• DAE-HardNet: A Physics Constrained Neural Network Enforcing Differential-Algebraic Hard Constraints
• Predicting Price Movements in High-Frequency Financial Data with Spiking Neural Networks
• A Fast Anti-Jamming Cognitive Radar Deployment Algorithm Based on Reinforcement Learning
• Stochastic Reconfiguration with Warm-Started SVD
• HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
• Meta-Learning Multi-armed Bandits for Beam Tracking in 5G and 6G Networks
• LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
• A Regularization and Active Learning Method for Identification of Quasi Linear Parameter Varying Systems
• Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
• Wasserstein distance based semi-supervised manifold learning and application to GNSS multi-path detection
• DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
• Beyond Adam: Disentangling Optimizer Effects in the Fine-Tuning of Atomistic Foundation Models
• Control Consistency Losses for Diffusion Bridges
• Hybrid Quantum-Classical Autoencoders for Unsupervised Network Intrusion Detection
• Fine-Tuning BERT for Domain-Specific Question Answering: Toward Educational NLP Resources at University Scale
• QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory
• CNN on `Top': In Search of Scalable & Lightweight Image-based Jet Taggers
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows
• Equivariant symmetry-aware head pose estimation for fetal MRI
• STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
• Functional Stability of Software-Hardware Neural Network Implementation The NeuroComp Project
• Safe model-based Reinforcement Learning via Model Predictive Control and Control Barrier Functions
• Contract-Governed Training for Earth Observation: Observed Service Agreement Graphs and Coverage-Accuracy Trade-offs
• Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
• Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges
• DeRA: Decoupled Representation Alignment for Video Tokenization
• GuidNoise: Single-Pair Guided Diffusion for Generalized Noise Synthesis
• FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring
• The Initialization Determines Whether In-Context Learning Is Gradient Descent
• Beyond Flicker: Detecting Kinematic Inconsistencies for Generalizable Deepfake Video Detection
• Resummed Distribution Functions: Making Perturbation Theory Positive and Normalized
• Refining Machine Learning Potentials through Thermodynamic Theory of Phase Transitions
• Performance and efficiency of a transformer-based quark/gluon jet tagger in the ATLAS experiment
• Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
• Hybrid Temporal-8-Bit Spike Coding for Spiking Neural Network Surrogate Training
• Scalable Decision Focused Learning via Online Trainable Surrogates
• Comparison of neural network training strategies for the simulation of dynamical systems
• Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+(λ,λ))-GA
• LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
• 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
• A Gradient Method for Risk Averse Control of a PDE-SDE Interconnected System
• CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion
• CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures
• Adaptive sampling using variational autoencoder and reinforcement learning
• SweetDeep: A Wearable AI Solution for Real-Time Non-Invasive Diabetes Screening
• FuXi-Nowcast: Environment-conditioned deep learning for severe convection nowcasting
• RNNs perform task computations by dynamically warping neural representations
• CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models
• PyroFocus: A Deep Learning Approach to Real-Time Wildfire Detection in Multispectral Remote Sensing Imagery
• Assessing the performance of correlation-based multi-fidelity neural emulators
• Position-Sensitive Silicon Photomultiplier Array with Enhanced Position Reconstruction by means of a Deep Neural Network
• G-PIFNN: A Generalizable Physics-informed Fourier Neural Network Framework for Electrical Circuits
• Leveraging generative adversarial networks with spatially adaptive denormalization for multivariate stochastic seismic data inversion
• Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation
• Tensor Network Based Feature Learning Model
• Towards Unified Video Quality Assessment
• Parameter-Efficient Subspace Optimization for LLM Fine-Tuning
• Learning Dexterous Manipulation Skills from Imperfect Simulations
• Cross-Lingual Interleaving for Speech Language Models
• Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
• BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch
• Cuffless Blood Pressure Estimation from Six Wearable Sensor Modalities in Multi-Motion-State Scenarios
• Searching for EeV photons with Telescope Array Surface Detector and neural networks
• Neural network-based deconvolution for GeV-Scale Gamma-Ray Spectroscopy
• Semantic-aware Random Convolution and Source Matching for Domain Generalization in Medical Image Segmentation
• AI-Enabled grading with near-domain data for scaling feedback with human-level accuracy
• ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation
• TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
• Learning to Reconstruct Temperature Field from Sparse Observations with Implicit Physics Priors
• VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering
• Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages
• M³A Policy: Mutable Material Manipulation Augmentation Policy through Photometric Re-rendering
• Learning Eigenstructures of Unstructured Data Manifolds
• Upper Approximation Bounds for Neural Oscillators
• Provenance-Driven Reliable Semantic Medical Image Vector Reconstruction via Lightweight Blockchain-Verified Latent Fingerprints
• PhotoFramer: Multi-modal Image Composition Instruction
• Planar Diffractive Neural Networks Empowered Communications: A Spatial Modulation Scheme
• Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation
• Robust Probabilistic Load Forecasting for a Single Household: A Comparative Study from SARIMA to Transformers on the REFIT Dataset
• Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting
• Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
• Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
• CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty
• ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for Recommendation
• Hyperbolic Continuous Structural Entropy for Hierarchical Clustering
• Vision Transformer for Classification of UAV and Helicopters Using Micro-Doppler Spectrograms in Surveillance Radar
• S²-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting
• Datamodel-Based Data Selection for Nonlinear Data-Enabled Predictive Control
• PAT3D: Physics-Augmented Text-to-3D Scene Generation
• Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
• Search for H→ cc and measurement of H→ bb in vector-boson fusion production with the ATLAS Detector
• First Steps towards Machine Learning for Prediction and Pre-Correction in Direct Laser Writing
• Deep Learning for Restoring MPI System Matrices Using Simulated Training Data
• Nonequilibrium dynamics of magnetic hopfions driven by spin-orbit torque
• DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
• Blazar classification from multi-wavelength data using Deep Learning
• BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning
• Hybrid Context-Fusion Attention (CFA) U-Net and Clustering for Robust Seismic Horizon Interpretation
• Leveraging Textual Compositional Reasoning for Robust Change Captioning
• Dynamic mixed turbulence modeling using a super-resolution generative adversarial approach
• Alzheimer's Disease Prediction Using EffNetViTLoRA and BiLSTM with Multimodal Longitudinal MRI Data
• A3T-GCN for FTSE100 Components Price Forecasting
• Predicting liquid properties and behavior via droplet pinch-off and machine learning
• Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
• A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral data
• Learning the MPC objective function from human preferences
• Adversarial Flow Models
• UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data
• Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism
• NOMA Assisted Downlink Power Allocation in Pinching Antenna Systems Using Convolutional Neural Network
• IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer
• Waveform-Based Probabilistic Seismic Hazard Analysis Using Ground-Motion Generative Models
• BAMAS: Structuring Budget-Aware Multi-Agent Systems
• Self-Paced Learning for Images of Antinuclear Antibodies
• Dynamical Implicit Neural Representations
• SUPN: Shallow Universal Polynomial Networks
• The Directed Prediction Change - Efficient and Trustworthy Fidelity Assessment for Local Feature Attribution Methods
• Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues
• Acoustic neural networks: Identifying design principles and exploring physical feasibility
• Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
• Multi-modal On-Device Learning for Monocular Depth Estimation on Ultra-low-power MCUs
• Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
• MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization
• DeepRFTv2: Kernel-level Learning for Image Deblurring
• Data-Driven Assessment of Concrete Slab Integrity via Impact-Echo Signals and Neural Networks
• A Unified Understanding of Offline Data Selection and Online Self-refining Generation for Post-training LLMs
• Adaptive Gradient Descent MPPT Algorithm With Complexity-Aware Benchmarking for Low-Power PV Systems
• Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
• Pre-train to Gain: Robust Learning Without Clean Labels
• Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification
• Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features
• Active learning with physics-informed neural networks for optimal sensor placement in deep tunneling through transversely isotropic elastic rocks
• Evaluating the Performance of Deep Learning Models in Whole-body Dynamic 3D Posture Prediction During Load-reaching Activities
• BRIC: Bridging Kinematic Plans and Physical Control at Test Time
• Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning
• RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches
• SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors
• HVAdam: A Full-Dimension Adaptive Optimizer
• Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization
• Fusion of Simulation and Experiment Data for Hypersonic Flow Field Prediction via Pre-Training and Fine-Tuning
• Towards A Tri-View Diffusion Framework for Recommendation
• Sparse MIMO-OFDM Channel Estimation via RKHS Regularization
• DeLightMono: Enhancing Self-Supervised Monocular Depth Estimation in Endoscopy by Decoupling Uneven Illumination
• Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting
• GazeProphetV2: Head-Movement-Based Gaze Prediction Enabling Efficient Foveated Rendering on Mobile VR
• SONIC: Spectral Optimization of Noise for Inpainting with Consistency
• On the Fundamental Limit of Stochastic Gradient Identification Algorithm Under Non-Persistent Excitation
• Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
• 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
• Latent-space metrics for Complex-Valued VAE out-of-distribution detection under radar clutter
• Online-PVLM: Advancing Personalized VLMs with Online Concept Learning
• Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
• Differentiable Attenuation Filters for Feedback Delay Networks
• Efficient Optimization of a Permanent Magnet Array for a Stable 2D Trap
• Heterogeneous Multi-treatment Uplift Modeling for Trade-off Optimization in Short-Video Recommendation
• SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting
• IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
• AvatarBrush: Monocular Reconstruction of Gaussian Avatars with Intuitive Local Editing
• SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection
• Fast Adaptive Neural Control of Resonant Extraction at Fermilab
• Rethinking Plant Disease Diagnosis: Bridging the Academic-Practical Gap with Vision Transformers and Zero-Shot Learning
• UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection
• BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
• Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
• Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
• Large-Scale In-Game Outcome Forecasting for Match, Team and Players in Football using an Axial Transformer Neural Network
• CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection
• Neural Geometry Image-Based Representations with Optimal Transport (OT)
• LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space
• Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
• MambaX: Image Super-Resolution with State Predictive Control
• An Invariant Latent Space Perspective on Language Model Inversion
• NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations
• InstructAudio: Unified speech and music generation with natural language instruction
• Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM
• A Fair OR-ML Framework for Resource Substitution in Large-Scale Networks
• End-to-End Automated Logging via Multi-Agent Framework
• Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection
• Off-Road Navigation via Implicit Neural Representation of Terrain Traversability
• Bayesian Calibration of Engine-out NOx Models for Engine-to-Engine Transferability
• MEDIC: a network for monitoring data quality in collider experiments
• Active Learning with Selective Time-Step Acquisition for PDEs
• Diffusion-based Surrogate Model for Time-varying Underwater Acoustic Channels
• Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay
• Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging
• A multi-view contrastive learning framework for spatial embeddings in risk modelling
• JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception
• Iterative improvement of free energy landscape reconstructions with optimal protocols derived from differentiable simulations
• Quantum Masked Autoencoders for Vision Learning
• Deep Learning Analysis of Ions Accelerated at Shocks
• FLUID: Training-Free Face De-identification via Latent Identity Substitution
• Dual-domain Adaptation Networks for Realistic Image Super-resolution
• Real Noise Decoupling for Hyperspectral Image Denoising
• Geometric-disentangelment Unlearning
• Super-Resolution ISAC Receivers: An MCMC-Based Gridless Sparse Bayesian Learning Approach
• Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks
• A Priori Assessment of Rotational Invariance in Multiscale Convolutional Neural Network-Based Subgrid-Scale Model for Wall-Bounded Turbulent Flows
• PhysMorph-GS: Differentiable Shape Morphing via Joint Optimization of Physics and Rendering Objectives
• Point-Supervised Facial Expression Spotting with Gaussian-Based Instance-Adaptive Intensity Modeling
• Flow-Guided Implicit Neural Representation for Motion-Aware Dynamic MRI Reconstruction
• Towards a Safer and Sustainable Manufacturing Process: Material classification in Laser Cutting Using Deep Learning
• Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
• SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
• Neural Positioning Without External Reference
• Deep Learning Framework for Enhanced Neutrino Reconstruction of Single-line Events in the ANTARES Telescope
• Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
• General-purpose Data-driven Wall Model for Low-speed Flows Part I: Baseline Model
• CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement
• Consistency requirement of data-driven subgrid-scale modeling in large-eddy simulation
• Efficient quantum state preparation of multivariate functions using tensor networks
• Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks
• Memory-DD: A Low-Complexity Dendrite-Inspired Neuron for Temporal Prediction Tasks
• TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid
• Prediction of atomic H adsorption energies in metalloid doped MSSe (M = Mo/W) Janus layers: A combined DFT and machine learning study
• How Noise Benefits AI-generated Image Detection
• Incorporating Token Importance in Multi-Vector Retrieval
• Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference
• From Prompts to Printable Models: Support-Effective 3D Generation via Offset Direct Preference Optimization
• TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models
• PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
• Computation for Epidemic Prediction with Graph Neural Network by Model Combination
• CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search
• RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer
• Judicial Sentencing Prediction Based on Hybrid Models and Two-Stage Learning Algorithms
• Multi-layer Stack Ensembles for Time Series Forecasting
• STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Detection
• SplitFlux: Learning to Decouple Content and Style from a Single Image
• Effective Code Membership Inference for Code Completion Models via Adversarial Prompts
• WiCo-PG: Wireless Channel Foundation Model for Pathloss Map Generation via Synesthesia of Machines
• WiCo-MG: Wireless Channel Foundation Model for Multipath Generation via Synesthesia of Machines
• A Neural Network Approach to Preferred Event Selection for Low-Latency Gravitational-Wave Alerts
• Multimodal Optical Imaging Platform for Quantitative Burn Assessment
• Gradient-descent methods for quantum detector tomography
• Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
• Adversarial Learning-Based Radio Map Reconstruction for Fingerprinting Localization
• Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching
• Analyzing the Impact of Participant Failures in Cross-Silo Federated Learning
• Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
• Dental3R: Geometry-Aware Pairing for Intraoral 3D Reconstruction from Sparse-View Photographs
• Count The Notes: Histogram-Based Supervision for Automatic Music Transcription
• ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders
• 10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training
• Fully Automated Deep Learning Based Glenoid Bone Loss Measurement and Severity Stratification on 3D CT in Shoulder Instability
• Reconstructing the Aerosol State from Partial Observations with Generative Modeling
• CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution
• VLMs Guided Interpretable Decision Making for Autonomous Driving
• Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation
• Making Evidence Actionable in Adaptive Learning Closing the Diagnostic Pedagogical Loop
• Taming Barren Plateaus in Arbitrary Parameterized Quantum Circuits without Sacrificing Expressibility
• Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping
• HPC-Accelerated Simulation and Calibration for Silicon Quantum Dots
• A Bi-fidelity based asymptotic-preserving neural network for the semiconductor Boltzmann equation and its inverse problem
• View-aware Cross-modal Distillation for Multi-view Action Recognition
• Force-Aware 3D Contact Modeling for Stable Grasp Generation
• A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification
• NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes
• DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
• Orientation-Free Neural Network-Based Bias Estimation for Low-Cost Stationary Accelerometers
• FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentation
• Dimension vs. Precision: A Comparative Analysis of Autoencoders and Quantization for Efficient Vector Retrieval on BEIR SciFact
• Mitigating Recommendation Biases via Group-Alignment and Global-Uniformity in Representation Learning
• TacEleven: generative tactic discovery for football open play
• Learned Adaptive Kernels for High-Fidelity Image Downscaling
• PCD-ReID: Occluded Person Re-Identification for Base Station Inspection
• On the Cross-lingual Transferability of Pre-trained wav2vec2-based Models
• Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
• Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement
• CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory
• FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• Pixels or Positions? Benchmarking Modalities in Group Activity Recognition
• CAO: Curvature-Adaptive Optimization via Periodic Low-Rank Hessian Sketching
• D²-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation
• Lightweight Optimal-Transport Harmonization on Edge Devices
• xLSTM-PINN: Memory-Gated Spectral Remodeling for Physics-Informed Learning
• Diffusion Model Based Signal Recovery Under 1-Bit Quantization
• Multi-Domain EEG Representation Learning with Orthogonal Mapping and Attention-based Fusion for Cognitive Load Classification
• VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing
• SplineSplat: 3D Ray Tracing for Higher-Quality Tomography
• Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
• Optimising Density Computations in Probabilistic Programs via Automatic Loop Vectorisation
• 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
• Hybrid Predictive Quantum Feedback: Extending Qubit Lifetimes Beyond the Wiseman-Milburn Limit
• RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving
• ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation
• SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images
• HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings
• An Adjoint Formulation of Energetic Particle Confinement
• Multimodal Fusion Network for Micro-displacement Measurement via Michelson Interferometer
• Testbed Evaluation of AI-based Precoding in Distributed MIMO Systems
• Learning Conjugate Direction Fields for Planar Quadrilateral Mesh Generation
• Leveraging Exogenous Signals for Hydrology Time Series Forecasting
• FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition
• Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates
• Dynamic Avatar-Scene Rendering from Human-centric Context
• Variational Quantum Algorithms for Particle Track Reconstruction
• Deep active inference
• Coordinate Descent for Network Linearization
• iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
• TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
• Gene Incremental Learning for Single-Cell Transcriptomics
• Learning Fair Representations with Kolmogorov-Arnold Networks
• ChemFixer: Correcting Invalid Molecules to Unlock Previously Unseen Chemical Space
• VitalBench: A Rigorous Multi-Center Benchmark for Long-Term Vital Sign Prediction in Intraoperative Care
• Sumudu Neural Operator for ODEs and PDEs
• Benchmarking Quantum Kernels Across Diverse and Complex Data
• Maximizing Efficiency of Dataset Compression for Machine Learning Potentials With Information Theory
• Minimizing smooth Kurdyka-Łojasiewicz functions via generalized descent methods: Convergence rate and complexity
• Generalizing to Unseen Disaster Events: A Causal View
• 2.5D Transformer: An Efficient 3D Seismic Interpolation Method without Full 3D Training
• AdaptViG: Adaptive Vision GNN with Exponential Decay Gating
• ConSurv: Multimodal Continual Learning for Survival Analysis
• SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
• Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation
• Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
• Multiple Treatments Causal Effects Estimation with Task Embeddings and Balanced Representation Learning
• Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO
• Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
• Improving Sustainability of Adversarial Examples in Class-Incremental Learning
• Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
• An ultrafast plenoptic-camera system for high-resolution 3D particle tracking in unsegmented scintillators
• Improving Quantum Neural Networks exploration by Noise-Induced Equalization
• Multimodal ML: Quantifying the Improvement of Calorie Estimation Through Image-Text Pairs
• Parametric Expensive Multi-Objective Optimization via Generative Solution Modeling
• OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS
• AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
• Learning Binary Autoencoder-Based Codes with Progressive Training
• DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization
• Regularized Schrödinger Bridge: Alleviating Distortion and Exposure Bias in Solving Inverse Problems
• Blurred Encoding for Trajectory Representation Learning
• Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning
• Convex Clustering Redefined: Robust Learning with the Median of Means Estimator
• Ultrafast Pulse Retrieval from Partial FROG Traces Using Implicit Diffusion Models
• Learning with Preserving for Continual Multitask Learning
• Hyperdimensional Decoding of Spiking Neural Networks
• RESTL: Reinforcement Learning Guided by Multi-Aspect Rewards for Signal Temporal Logic Transformation
• MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
• MVSMamba: Multi-View Stereo with State Space Model
• EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting
• Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
• Fidelity sweet spot in transmon qubit rings under strong connectivity noise
• Uncertainty Calibration of Multi-Label Bird Sound Classifiers
• Data-Driven Discovery of Feature Groups in Clinical Time Series
• Filtering Jump Markov Systems with Partially Known Dynamics: A Model-Based Deep Learning Approach
• Good flavor search in SU(5): a machine learning approach
• DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes
• Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
• Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection
• The Impact of Longitudinal Mammogram Alignment on Breast Cancer Risk Assessment
• Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval
• Misaligned by Design: Incentive Failures in Machine Learning
• Predicting Coronary Artery Calcium Severity based on Non-Contrast Cardiac CT images using Deep Learning
• Kolmogorov-Arnold Chemical Reaction Neural Networks for learning pressure-dependent kinetic rate laws
• Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network
• Supervised learning of protein variant effects across large‐scale mutagenesis datasets
• High-level hadronic tau lepton triggers of the CMS experiment in proton-proton collisions at √(s) = 13.6 TeV
• Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
• LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
• Reduced Density Matrices Through Machine Learning
• TNT: Improving Chunkwise Training for Test-Time Memorization
• AcousTools: A 'Full-Stack', Python-Based, Acoustic Holography Library
• When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
• Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?
• On Stealing Graph Neural Network Models
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation
• Performance Decay in Deepfake Detection: The Limitations of Training on Outdated Data
• PADM: A Physics-aware Diffusion Model for Attenuation Correction
• Fine-Tuning Diffusion-Based Recommender Systems via Reinforcement Learning with Reward Function Optimization
• Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation
• ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search
• Learning to Fast Unrank in Collaborative Filtering Recommendation
• Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning
• Bilevel Learning via Inexact Stochastic Gradient Descent
• Flexible Concept Bottleneck Model
• Beyond Fixed Depth: Adaptive Graph Neural Networks for Node Classification Under Varying Homophily
• CAE: Character-Level Autoencoder for Non-Semantic Relational Data Grouping
• DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
• Recovering Sub-threshold S-wave Arrivals in Deep Learning Phase Pickers via Shape-Aware Loss
• MuonAll: Muon Variant for Efficient Finetuning of Large Language Models
• DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning
• Uncertainty-Aware Dual-Ranking Strategy for Offline Data-Driven Multi-Objective Optimization
• Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning
• Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field
• Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection
• Constraint-Informed Active Learning for End-to-End ACOPF Optimization Proxies
• SPASHT: An image-enhancement method for sparse-view MPI SPECT
• Resilience Inference for Supply Chains with Hypergraph Neural Network
• Models Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training
• Distributed Deep Learning for Medical Image Denoising with Data Obfuscation
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
• DWM-RO: Decentralized World Models with Reasoning Offloading for SWIPT-enabled Satellite-Terrestrial HetNets
• Loud-loss: A Perceptually Motivated Loss Function for Speech Enhancement Based on Equal-Loudness Contours
• A Remarkably Efficient Paradigm to Multimodal Large Language Models for Sequential Recommendation
• Predicting the Future by Retrieving the Past
• Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and Methodology
• Turning Noise into Value: Uncovering Service Preferences from Ambiguous Interaction in E-commerce
• Zero-Shot Function Encoder-Based Differentiable Predictive Control
• Adversarially Regularized Policy Learning Guided by Trajectory Optimization
• Identification of tau leptons using a convolutional neural network with domain adaptation
• Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration
• Extrapolation to infinite model space of no-core shell model calculations using machine learning
• Shallow IQP circuits and graph generation
• Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning
• Hybrid action Reinforcement Learning for quantum architecture search
• CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting
• What's on Your Plate? Inferring Chinese Cuisine Intake from Wearable IMUs
• Multimodal Diffusion Forcing for Forceful Manipulation
• Early GVHD Prediction in Liver Transplantation via Multi-Modal Deep Learning on Imbalanced EHR Data
• Accelerating metamaterial topology optimization using deep super-resolution networks
• Dark Energy Survey Year 3 results: Simulation-based wCDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design
• Multi-Method Analysis of Mathematics Placement Assessments: Classical, Machine Learning, and Clustering Approaches
• Unified Theory of Adaptive Variance Reduction
• wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
• High-Resolution Forest Mapping from L-Band Interferometric SAR Time Series using Deep Learning over Northern Spain
• Probing the Probes: Methods and Metrics for Concept Alignment
• FastGS: Training 3D Gaussian Splatting in 100 Seconds
• Accelerated Sequential Posterior Inference via Reuse for Gravitational-Wave Analyses
• AStF: Motion Style Transfer via Adaptive Statistics Fusor
• Covariance Descriptors Meet General Vision Encoders: Riemannian Deep Learning for Medical Image Classification
• Shellular Metamaterial Design via Compact Electric Potential Parametrization
• PETRA: Pretrained Evolutionary Transformer for SARS-CoV-2 Mutation Prediction
• Adaptive Phase Shift Information Compression for IRS Systems: A Prompt Conditioned Variable Rate Framework
• DeepFixel: Crossing white matter fiber identification through spherical convolutional neural networks
• CLAX: Fast and Flexible Neural Click Models in JAX
• LoRA-Edge: Tensor-Train-Assisted LoRA for Practical CNN Fine-Tuning on Edge Devices
• Extended Physics Informed Neural Network for Hyperbolic Two-Phase Flow in Porous Media
• Enhancing Medical Image Segmentation via Heat Conduction Equation
• D2-UC: A Distributed-Distributed Quantum-Classical Framework for Unit Commitment
• DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs
• Scheduling the Off-Diagonal Weingarten Loss of Neural SDFs for CAD Models
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• Value of Information-Enhanced Exploration in Bootstrapped DQN
• In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
• Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
• ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
• Test-Time Steering for Lossless Text Compression via Weighted Product of Experts
• Neural Network Interoperability Across Platforms
• Generalizable super-resolution turbulence reconstruction from minimal training data
• Resource-efficient Automatic Refinement of Segmentations via Weak Supervision from Light Feedback
• EV-NVC: Efficient Variable bitrate Neural Video Compression
• Improving Unlearning with Model Updates Probably Aligned with Gradients
• LLM4PG: Adapting Large Language Model for Pathloss Map Generation via Synesthesia of Machines
• A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control
• Constrained Performance Boosting Control for Nonlinear Systems via ADMM
• Locally-Supervised Global Image Restoration
• From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos
• LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization
• Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements
• Rethinking LLM Human Simulation: When a Graph is What You Need
• Towards Continuous-variable Quantum Neural Networks for Biomedical Imaging
• Quasars acting as Strong Lenses Found in DESI DR1
• Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping
• HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain
• Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
• Partial Trace-Class Bayesian Neural Networks
• IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
• Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors
• Secure Distributed RIS-MIMO over Double Scattering Channels: Adversarial Attack, Defense, and SER Improvement
• ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
• Assessing LLM Reasoning Steps via Principal Knowledge Grounding
• A Distributed Plug-and-Play MCMC Algorithm for High-Dimensional Inverse Problems
• Power Control Based on Multi-Agent Deep Q Network for D2D Communication
• Outlier-Aware Post-Training Quantization for Image Super-Resolution
• Gaining Momentum: Uncovering Hidden Scoring Dynamics in Hockey through Deep Neural Sequencing and Causal Modeling
• Simple and Behavior-Driven Augmentation for Recommendation with Rich Collaborative Signals
• Physics-Informed Neural Networks for Speech Production
• Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
• X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction
• Variational Geometry-aware Neural Network based Method for Solving High-dimensional Diffeomorphic Mapping Problems
• Spatial Controls of Lower Tropospheric Stability
• FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
• MVeLMA: Multimodal Vegetation Loss Modeling Architecture for Predicting Post-fire Vegetation Loss
• Temporal Cardiovascular Dynamics for Improved PPG-Based Heart Rate Estimation
• GFORS: GPU-Accelerated First-Order Method with Randomized Sampling for Binary Integer Programs
• Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition
• pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements
• Domain decomposition architectures and Gauss-Newton training for physics-informed neural networks
• All is More: Energy Flow Networks for Jet Quenching
• A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validation
• Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
• Multiclass Local Calibration With the Jensen-Shannon Distance
• Approximating Heavy-Tailed Distributions with a Mixture of Bernstein Phase-Type and Hyperexponential Models
• SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
• Multi-hop Parallel Image Semantic Communication for Distortion Accumulation Mitigation
• Generative Artificial Intelligence for Air Shower Simulation
• Learning Soil Physics from Partial Knowledge and Data: Partitioning Capillary and Adsorbed Soil Water
• Similarity-Distance-Magnitude Language Models
• ReaKase-8B: Legal Case Retrieval via Knowledge and Reasoning Representations with LLMs
• StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement
• Security Risk of Misalignment between Text and Image in Multi-modal Model
• FGGM: Formal Grey-box Gradient Method for Attacking DRL-based MU-MIMO Scheduler
• Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems
• MeixnerNet: Adaptive and Robust Spectral Graph Neural Networks with Discrete Orthogonal Polynomials
• Overcoming disorder in superconducting globally-driven quantum computing
• Fixed-point graph convolutional networks against adversarial attacks
• Model-Free Robust Beamforming in Satellite Downlink using Reinforcement Learning
• Active Learning with Task-Driven Representations for Messy Pools
• Equation Discovery, Parametric Simulation, and Optimization Using the Physics-Informed Neural Network (PINN) Method for the Heat Conduction Problem
• FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
• Meshless solutions of PDE inverse problems on irregular geometries
• Agentic Economic Modeling
• Scaling flow-based approaches for topology sampling in SU(3) gauge theory
• Convolutional Spiking-based GRU Cell for Spatio-temporal Data
• PyDPF: A Python Package for Differentiable Particle Filtering
• Mechanistic Interpretability of RNNs emulating Hidden Markov Models
• Automatic selection of hyper-parameters via the use of softened profile likelihood
• Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
• Solving the Right Problem with Multi-Robot Formations
• Adaptive End-to-End Transceiver Design for NextG Pilot-Free and CP-Free Wireless Systems
• Cross Learning between Electronic Structure Theories for Unifying Molecular, Surface, and Inorganic Crystal Foundation Force Fields
• A Convexity-dependent Two-Phase Training Algorithm for Deep Neural Networks
• Tight Collision Avoidance for Stochastic Optimal Control: with Applications in Learning-based, Interactive Motion Planning
• Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment
• Calibrating the Digital Twin Channel: Statistics-Consistent Sim-to-Lab Adaptation for W-Band Industrial OFDM Links
• DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval
• CASIAL: Geometric Distortion Robust Image Watermarking
• Extracting informative vortical structures of turbulent wake-extreme vortex gust interactions with machine learning
• JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation
• Multi-User Localization via Active Sensing with Electromagnetically Reconfigurable Antennas
• Relation Geometry in Semantic Space of Language Models
• Between Gradient and Natural Gradient: A Continuum of LoRA Initializations
• Eddeep: a deep-learning framework for fast eddy-current distortion correction in diffusion MRI
• Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
• Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography
• ExplainRec: Towards Explainable Multi-Modal Zero-Shot Recommendation with Preference Attribution and Large Language Models
• A Study on Online Mask-based Beamforming Using Per-channel Masking for Spatially Distributed Microphones
• Rotational equivariance and locality in data-driven subgrid-scale closures
• StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction
• IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation
• Target localization, identification and sensing using latent symmetries
• Projective Graph Residualization: Variation-Allocation Frontiers for Control-Function IV
• Neural Texture Compression using Hypernetworks
• Teaching Machine Learning to Software Engineers
• TweetyBERT: Automated parsing of birdsong through self-supervised machine learning
• Tensor Decomposition for Compressing Recurrent Neural Network
• Large-scale empirical tuning and comparison of default optimizers for variational inference
• Escalating Hydroclimatic Extremes and Volatility in the UK Under 2°C and 4°C Warming
• Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography
• An artificial neural network–based deep learning model to predict combined stress impact and interaction in plants
• Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
• The Fast Lane Hypothesis: Von Economo Neurons Implement a Biological Speed-Accuracy Tradeoff
• Characterisation of the Clouds' young stellar Bridge using Gaia DR3
• Operational evaluation of data-driven forest fire forecasting models
• A Fourier-Space Approach to Physics-Informed Magnetization Reconstruction from Nitrogen-Vacancy Measurements
• Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis
• Multi-Marginal Schrödinger Bridge Matching
• The Stretto Execution Engine for LLM-Augmented Data Systems
• Data-Efficient Electromagnetic Surrogate Solver Through Dissipative Relaxation Transfer Learning
• Meta Flow Maps enable scalable reward alignment
• XRefine: Attention-Guided Keypoint Match Refinement
• Learning collision operators from plasma phase space data using differentiable simulators
• Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
• LogUpdater : Automated Detection and Repair of Specific Defects in Logging Statements
• Seeing Clearly and Deeply: An RGBD Imaging Approach with a Bio-inspired Monocentric Design
• Machine Learning Design of Soft Magnetoresponsive Materials With Multidirectional Fields
• BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
• GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Prediction
• Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts
• Learning Disentangled Speech- and Expression-Driven Blendshapes for 3D Talking Face Animation
• Balanced conic rectified flow
• Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
• GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
• Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision
• Towards Real-Time Inference of Thin Liquid Film Thickness Profiles from Interference Patterns Using Vision Transformers
• Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk
• Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
• Adaptive Proof Refinement with LLM-Guided Strategy Selection
• Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training
• A Black Box Variational Inference Scheme for Inverse Problems with Demanding Physics-Based Models
• A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection
• Contributions to Semialgebraic-Set-Based Stability Verification of Dynamical Systems with Neural-Network-Based Controllers
• Preconditioned Truncated Single-Sample Estimators for Scalable Stochastic Optimization
• Enforcing boundary conditions for physics-informed neural operators
• Online neural fusion of distortionless differential beamformers for robust speech enhancement
• HergNet: a Fast Neural Surrogate Model for Sound Field Predictions via Superposition of Plane Waves
• Training-free Source Attribution of AI-generated Images via Resynthesis
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization
• MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
• Exploring an image-based b-jet tagging method using convolution neural networks
• Fast and scalable joint-LORAKS reconstruction and data-driven sampling optimisation of high-dimensional MRI datasets using a GPU-accelerated and learning-free differentiable framework: PyLORAKS
• Strengths and Limitations of Statistical and Dynamical Downscaling for the Representation of Compound Dry and Hot Events Over Spain
• RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba
• Call-Center Staff Scheduling Considering Performance Evolution under Emotional Stress
• A Physics-informed Multi-resolution Neural Operator
• Does Machine Learning Work? A Comparative Analysis of Strong Gravitational Lens Searches in the Dark Energy Survey
• Bayesian neural networks with interpretable priors from Mercer kernels
• Sequence Modeling with Spectral Mean Flows
• Training Deep Physics-Informed Kolmogorov-Arnold Networks
• Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap
• Neural Networks for AC Optimal Power Flow: Improving Worst-Case Guarantees during Training
• The First Star-by-star N-body/Hydrodynamics Simulation of Our Galaxy Coupling with a Surrogate Model
• Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
• QUEST (Quasar Unsupervised Encoder and Synthesis Tool): A machine learning framework to generate quasar spectra
• Benchmarking VQE Configurations: Architectures, Initializations, and Optimizers for Silicon Ground State Energy
• EndoWave: Rational-Wavelet 4D Gaussian Splatting for Endoscopic Reconstruction
• Enabling American Sign Language Communication Under Low Data Rates
• How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
• Manifold Approximation leads to Robust Kernel Alignment
• Transforming volcanic monitoring: A dataset and benchmark for onboard volcano activity detection
• Limits of Generative Pre-Training in Structured EMR Trajectories with Irregular Sampling
• Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles
• SALSA: Single-pass Autoregressive LLM Structured Classification
• 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
• End-to-end Learning of Probabilistic and Geometric Constellation Shaping with Iterative Receivers
• SWAN: Self-supervised Wavelet Neural Network for Hyperspectral Image Unmixing
• Prediction-Powered Semi-Supervised Learning with Online Power Tuning
• Toward Robust Signed Graph Learning through Joint Input-Target Denoising
• TERRA: A Transformer-Enabled Recursive R-learner for Longitudinal Heterogeneous Treatment Effect Estimation
• An Interval Hessian-based line-search method for unconstrained nonconvex optimization
• Model-Free Power System Stability Enhancement with Dissipativity-Based Neural Control
• Does Homophily Help in Robust Test-time Node Classification?
• Streaming Generation for Music Accompaniment
• Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
• Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
• ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping
• Towards Explainable Personalized Recommendations by Learning from Users' Photos
• Plugging Weight-tying Nonnegative Neural Network into Proximal Splitting Method: Architecture for Guaranteeing Convergence to Optimal Point
• 3DPR: Single Image 3D Portrait Relight using Generative Priors
• BADiff: Bandwidth Adaptive Diffusion Model
• Learning Correlated Reward Models: Statistical Barriers and Opportunities
• Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
• Cold-Diffusion Driven Downward Continuation of Gravity Data
• Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
• Distributionally Robust Feature Selection
• SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization
• RIS-assisted Atomic MIMO Receiver
• Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization
• DMVFC: Deep Learning Based Functionally Consistent Tractography Fiber Clustering Using Multimodal Diffusion MRI and Functional MRI
• FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis
• Expectation-propagation for Bayesian empirical likelihood inference
• Optimization in Theory and Practice
• HRT1: One-Shot Human-to-Robot Trajectory Transfer for Mobile Manipulation
• Gaussian Mixture Flow Matching with Domain Alignment for Multi-Domain Sequential Recommendation
• Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers
• Lens Model Accuracy in the Expected LSST Lensed AGN Sample
• Learning Optimal Power Flow with Pointwise Constraints
• Bayesian Jammer Localization with a Hybrid CNN and Path-Loss Mixture of Experts
• Convergence Analysis of SGD under Expected Smoothness
• Bayesian Inference for PDE-based Inverse Problems using the Optimization of a Discrete Loss
• Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation
• Symbolic Regression and Differentiable Fits in Beyond the Standard Model Physics
• Channel Estimation and Passive Beamforming for Pixel-based Reconfigurable Intelligent Surfaces with Non-Separable State Response
• AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
• Calibrating Multimodal Consensus for Emotion Recognition
• DMC³: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering
• Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters
• Target-aware Image Editing via Cycle-consistent Constraints
• Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics
• Deep Learning Based Joint Space-Time-Frequency Domain Channel Prediction for Cell-Free Massive MIMO Systems
• General transformation neural networks: A class of parametrized functions for high-dimensional function approximation
• Kinetics of Peierls dimerization transition: Machine learning force-field approach
• Resounding Acoustic Fields with Reciprocity
• Unsupervised Anomaly Prediction with N-BEATS and Graph Neural Network in Multi-variate Semiconductor Process Time Series
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
• Towards Interpretable Deep Learning and Analysis of Dynamical Systems via the Discrete Empirical Interpolation Method
• A flexible framework for structural plasticity in GPU-accelerated sparse spiking neural networks
• BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models
• Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research
• DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
• OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning
• Seabed-Net: A multi-task network for joint bathymetry estimation and seabed classification from remote sensing imagery in shallow waters
• QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
• Parameter Estimation in River Transport Models With Immobile Phase Exchange Using Dimensional Analysis and Reduced-Order Models
• Configuration-Dependent Robot Kinematics Model and Calibration
• CDI-DTI: A Strong Cross-domain Interpretable Drug-Target Interaction Prediction Framework Based on Multi-Strategy Fusion
• Neural Variational Dropout Processes
• BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography
• Enhancing Graph Neural Networks: A Mutual Learning Approach
• C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search
• An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Version
• On Biologically Plausible Learning in Continuous Time
• Enhancing Fractional Gradient Descent with Learned Optimizers
• Diffusion Buffer for Online Generative Speech Enhancement
• mSQUID: Model-Based Leanred Modulo Recovery at Low Sampling Rates
• MC-LExt: Multi-Channel Target Speaker Extraction with Onset-Prompted Speaker Conditioning Mechanism
• Nonlinear Dimensionality Reduction Techniques for Bayesian Optimization
• Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments
• ProLAP: Probabilistic Language-Audio Pre-Training
• Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
• AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering
• DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing
• Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
• RadDiagSeg-M: A Vision Language Model for Joint Diagnosis and Multi-Target Segmentation in Radiology
• MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
• Efficient Model-Based Reinforcement Learning for Robot Control via Online Optimization
• From Volume Rendering to 3D Gaussian Splatting: Theory and Applications
• MEG-GPT: A transformer-based foundation model for magnetoencephalography data
• Cosmological constraints from the angular power spectrum and bispectrum of luminous red galaxies and CMB lensing
• Prediction of Sea Ice Velocity and Concentration in the Arctic Ocean using Physics-informed Neural Network
• MARS-M: When Variance Reduction Meets Matrices
• Quantifying Multimodal Imbalance: A GMM-Guided Adaptive Loss for Audio-Visual Learning
• A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
• Symmetries in PAC-Bayesian Learning
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning
• HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection
• Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
• GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models
• Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
• Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization
• Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed Prediction
• State estimation in homogeneous isotropic turbulence using super-resolution with a 4DVar training algorithm
• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
• MuonBP: Faster Muon via Block-Periodic Orthogonalization
• From Mannequin to Human: A Pose-Aware and Identity-Preserving Video Generation Framework for Lifelike Clothing Display
• Impact of Random Bond Disorder on Quantum Skyrmions in a spin-half Quantum Heisenberg Model
• Cross-Genre Authorship Attribution via LLM-Based Retrieve-and-Rerank
• Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation
• Poultry Farm Intelligence: An Integrated Multi-Sensor AI Platform for Enhanced Welfare and Productivity
• Still Competitive: Revisiting Recurrent Models for Irregular Time Series Prediction
• MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
• SADCHER: Scheduling using Attention-based Dynamic Coalitions of Heterogeneous Robots in Real-Time
• A Geometric Approach to Optimal Experimental Design
• A Hybrid Quantum Solver for Gaussian Process Regression
• On the Neural Feature Ansatz for Deep Neural Networks
• Neuro-Symbolic Spatial Reasoning in Segmentation
• Polarization based direction of arrival estimation using a radio interferometric array
• EARS-UDE: Evaluating Auditory Response in Sensory Overload with Universal Differential Equations
• Forecasting Quantum Observables: A Compressed Sensing Approach with Performance Guarantees
• Modeling nonlinear scales for dynamical dark energy cosmologies with COLA
• Morphology-Aware Prognostic model for Five-Year Survival Prediction in Colorectal Cancer from H&E Whole Slide Images
• Search for exocomets transits in Kepler light curves: Ten new transits identified
• GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement
• An insight into the rare Z→ b bγ at the HL-LHC
• Vision Mamba for Permeability Prediction of Porous Media
• A Structured Neural ODE Approach for Real Time Evaluation of AC Losses in 3D Superconducting Tapes
• Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
• Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimization and L1 Sparsity Constraints
• Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
• Glitch noise classification in KAGRA O3GK observing data using unsupervised machine learning
• A novel Information-Driven Strategy for Optimal Regression Assessment
• Physics‐Aware Probabilistic Modeling of Subsurface Soil Moisture Using Diffusion Processes Across Different Climate Settings
• Quantized Skeletal Learning (QSL): A Differentiable Programming Approach for Skeletal Reduction of Chemical Mechanisms
• PulseFi: A Low Cost Robust Machine Learning System for Accurate Cardiopulmonary and Apnea Monitoring Using Channel State Information
• ViTacGen: Robotic Pushing with Vision-to-Touch Generation
• DROID: Dual Representation for Out-of-Scope Intent Detection
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources
• Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs
• APRIL: Auxiliary Physically-Redundant Information in Loss - A physics-informed framework for parameter estimation with a gravitational-wave case study
• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization
• RockNet: Distributed Learning on Ultra-Low-Power Devices
• MimicParts: Part-aware Style Injection for Speech-Driven 3D Motion Generation
• Counting Hallucinations in Diffusion Models
• Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models
• PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
• Hypernetworks for Perspectivist Adaptation
• ProtoTopic: Prototypical Network for Few-Shot Medical Topic Modeling
• FlashWorld: High-quality 3D Scene Generation within Seconds
• Randomness and Interpolation Improve Gradient Descent
• Computationally Efficient Neural Receivers via Axial Self-Attention
• CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
• Wavefront Coding for Accommodation-Invariant Near-Eye Displays
• Why the noise model matters: A performance gap in learned regularization
• MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding
• M3ST-DTI: A multi-task learning model for drug-target interactions based on multi-modal features and multi-stage alignment
• Scene Coordinate Reconstruction Priors
• Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
• Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection
• A Gradient Guided Diffusion Framework for Chance Constrained Programming
• 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
• Hardware-aware Coding Function Design for Compressive Single-Photon 3D Cameras
• Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
• Human-in-the-Loop Bandwidth Estimation for Quality of Experience Optimization in Real-Time Video Communication
• Actron3D: Learning Actionable Neural Functions from Videos for Transferable Robotic Manipulation
• VCTR: A Transformer-Based Model for Non-parallel Voice Conversion
• E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
• Utility-Scale Quantum State Preparation: Classical Training using Pauli Path Simulation
• On Thompson Sampling and Bilateral Uncertainty in Additive Bayesian Optimization
• Reinforced sequential Monte Carlo for amortised sampling
• REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
• QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
• PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
• High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
• Differentiable Fast Top-K Selection for Large-Scale Recommendation
• GADA: Graph Attention-based Detection Aggregation for Ultrasound Video Classification
• Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
• Towards Real-Time Fake News Detection under Evidence Scarcity
• G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation
• PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Text-Enhanced Panoptic Symbol Spotting in CAD Drawings
• GrASP: A Generalizable Address-based Semantic Prefetcher for Scalable Transactional and Analytical Workloads
• ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
• HatLLM: Hierarchical Attention Masking for Enhanced Collaborative Modeling in LLM-based Recommendation
• HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
• Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
• Dynamic Target Attack
• Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems
• Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
• Reinforcement Learning-based Dynamic Adaptation for Sampling-Based Motion Planning in Agile Autonomous Driving
• A Hybrid Machine Learning Approach for Synthetic Data Generation with Post Hoc Calibration for Clinical Tabular Datasets
• Quantum Integration Networks for Efficient Monte Carlo in High-Energy Physics
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
• Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation
• Hierarchical LoRA MoE for Efficient CTR Model Scaling
• Ensemble Threshold Calibration for Stable Sensitivity Control
• SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
• Learning Model Representations Using Publicly Available Model Hubs
• Generative Modeling of Aerosol State Representations
• B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding
• Meronymic Ontology Extraction via Large Language Models
• Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
• Uncertainty-Aware Post-Detection Framework for Enhanced Fire and Smoke Detection in Compact Deep Learning Models
• Gradient-based Model Shortcut Detection for Time Series Classification
• Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
• Neuro-inspired automated lens design
• A Copula-based variational autoencoder for uncertainty quantification in inverse problems: application to damage identification in an offshore wind turbine
• Leveraging Prior Knowledge of Diffusion Model for Person Search
• Towards Speeding up Program Repair with Non-Autoregressive Model
• Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification
• Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
• An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
• Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction
• Extreme value forecasting using relevance-based data augmentation with deep learning models
• TAWRMAC: A Novel Dynamic Graph Representation Learning Method
• Leveraging Shared Prototypes for a Multimodal Pulse Motion Foundation Model
• On the Representations of Entities in Auto-regressive Large Language Models
• Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendation
• WaveNet's Precision in EEG Classification
• Group-Adaptive Adversarial Learning for Robust Fake News Detection Against Malicious Comments
• AB-PINNs: Adaptive-Basis Physics-Informed Neural Networks for Residual-Driven Domain Decomposition
• Model-Based Lookahead Reinforcement Learning for in-hand manipulation
• Rewiring Development in Brain Segmentation: Leveraging Adult Brain Priors for Enhancing Infant MRI Segmentation
• Conditional Flow Matching for Bayesian Posterior Inference
• CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
• MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths
• Patchy Particles Design: From Floppy Modes to Sloppy Dimensions
• MAT-Agent: Adaptive Multi-Agent Training Optimization
• Geo-Aware Models for Stream Temperature Prediction across Different Spatial Regions and Scales
• Solving Fokker-Planck-Kolmogorov Equation by Distribution Self-adaptation Normalized Physics-informed Neural Networks
• Enhancing the Sensitivity for Triple Higgs Boson Searches with Deep Learning Techniques
• Discrete Facial Encoding: : A Framework for Data-driven Facial Display Discovery
• Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise
• DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems
• AI-Driven Radiology Report Generation for Traumatic Brain Injuries
• Spectral Prefiltering of Neural Fields
• Expressive Value Learning for Scalable Offline Reinforcement Learning
• MRI-derived quantification of hepatic vessel-to-volume ratios in chronic liver disease using a deep learning approach
• NRRS: Neural Russian Roulette and Splitting
• Zero-Shot Forecasting of Network Dynamics through Weight Flow Matching
• Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
• Rotated Mean-Field Variational Inference and Iterative Gaussianization
• DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
• Value Flows
• Joint Deblurring and 3D Reconstruction for Macrophotography
• Optimal Stopping in Latent Diffusion Models
• Statistical Benchmarking of Optimization Methods for Variational Quantum Eigensolver under Quantum Noise
• CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
• Enhancing Hybrid Methods in Parameterized Quantum Circuit Optimization
• Platform-Agnostic Modular Architecture for Quantum Benchmarking
• A Geomechanically-Informed Framework for Wellbore Trajectory Prediction: Integrating First-Principles Kinematics with a Rigorous Derivation of Gated Recurrent Networks
• A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata
• Unified Spectrospatial Forward Models: Spatially Continuous Maps of Weak Emission Lines in the Rosette Nebula with SDSS-V LVM
• Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
• An in-depth look at approximation via deep and narrow neural networks
• A General Framework for Joint Multi-State Models
• Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?
• Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring
• Adaptive Semantic Communication for UAV/UGV Cooperative Path Planning
• Accelerating wave simulations with neural dispersion correctors
• Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Retrieval
• Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
• Mechanisms of Surface Meltwater Ponding and Drainage on the Greenland Ice Sheet Revealed Using SkySat Imagery and Deep Learning
• MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
• Modeling COVID-19 Dynamics in German States Using Physics-Informed Neural Networks
• Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
• Reproducible Evaluation of Data Augmentation and Loss Functions for Brain Tumor Segmentation
• TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting
• A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
• Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
• Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
• Surrogate Modeling for the Design of Optimal Lattice Structures using Tensor Completion
• Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi⁴ field theory
• Multiprobe constraints on early and late time dark energy
• Universal super-resolution framework for imaging of quantum dots
• Scalable deep fusion of spaceborne lidar and synthetic aperture radar for global forest structural complexity mapping
• Representing Subgrid-Scale Cloud Effects in a Radiation Parameterization using Machine Learning: MLe-radiation v1.0
• GRPO-GCC: Enhancing Cooperation in Spatial Public Goods Games via Group Relative Policy Optimization with Global Cooperation Constraint
• Multimodal Trajectory Representation Learning for Travel Time Estimation
• VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
• Mixture of Neuron Experts
• Nonlinear System Identification for Model-Based Control of Waked Wind Turbines
• A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
• NorMuon: Making Muon more efficient and scalable
• Rasterized Steered Mixture of Experts for Efficient 2D Image Regression
• Climate Model Tuning with Online Synchronization-Based Parameter Estimation
• RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics
• Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
• QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification
• Tensor-on-tensor Regression Neural Networks for Process Modeling with High-dimensional Data
• Adjusting the Output of Decision Transformer with Action Gradient
• LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstruction
• Learning a distance measure from the information-estimation geometry of data
• Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
• On Predicting Post-Click Conversion Rate via Counterfactual Inference
• Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
• ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
• MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts
• Data-Driven Adaptive PID Control Based on Physics-Informed Neural Networks
• Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
• TinyViT-Batten: Few-Shot Vision Transformer with Explainable Attention for Early Batten-Disease Detection on Pediatric MRI
• CodeFormer++: Blind Face Restoration Using Deformable Registration and Deep Metric Learning
• MARCO: A Cooperative Knowledge Transfer Framework for Personalized Cross-domain Recommendations
• Galaxy Model Subtraction with a Convolutional Denoising Autoencoder
• Glocal Information Bottleneck for Time Series Imputation
• Fit Pixels, Get Labels: Meta-learned Implicit Networks for Image Segmentation
• Learning to Predict Chaos: Curriculum-Driven Training for Robust Forecasting of Chaotic Dynamics
• GenAR: Next-Scale Autoregressive Generation for Spatial Gene Expression Prediction
• Generalized Deep Image to Image Regression
• Diffusion Low Rank Hybrid Reconstruction for Sparse View Medical Imaging
• Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition
• Thai Semantic End-of-Turn Detection for Real-Time Voice Agents
• Designing Coherent Optical Environment for Dynamic Optical Manipulation with a Simple Control Beam
• VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events
• Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets
• Model-Based Adaptive Precision Control for Tabletop Planar Pushing Under Uncertain Dynamics
• ProxSTORM -- A Stochastic Trust-Region Algorithm for Nonsmooth Optimization
• Multi-Modal Oral Cancer Detection Using Weighted Ensemble Convolutional Neural Networks
• LHGEL: Large Heterogeneous Graph Ensemble Learning using Batch View Aggregation
• Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices
• CVSM: Contrastive Vocal Similarity Modeling
• Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation
• Wasserstein crossover for evolutionary algorithm-based topology optimization
• XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
• Development of Deep Neural Network First-Level Hardware Track Trigger for the Belle II Experiment
• Image Enhancement Based on Pigment Representation
• Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows
• HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
• Multi-task Neural Diffusion Processes
• Image Generation Based on Image Style Extraction
• TabINR: An Implicit Neural Representation Framework for Tabular Data Imputation
• Grid Frequency Stability Support Potential of Data Center: A Quantitative Assessment of Flexibility
• It Takes Two: Your GRPO Is Secretly DPO
• Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
• TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
• Deep learning motion correction of quantitative stress perfusion cardiovascular magnetic resonance
• Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
• Physics-Informed Neural Controlled Differential Equations for Scalable Long Horizon Multi-Agent Motion Forecasting
• Learning Passive Continuous-Time Dynamics with Multistep Port-Hamiltonian Gaussian Processes
• DeMuon: A Decentralized Muon for Matrix Optimization over Graphs
• FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
• Tenyidie Syllabification corpus creation and deep learning applications
• A phase-aware AI car-following model for electric vehicles with adaptive cruise control: Development and validation using real-world data
• Motion In-Betweening for Densely Interacting Characters
• Observer-Usable Information as a Task-specific Image Quality Metric
• To Remember, To Adapt, To Preempt: A Stable Continual Test-Time Adaptation Framework for Remote Physiological Measurement in Dynamic Domain Shifts
• Retrieval-Augmented Generation for Electrocardiogram-Language Models
• Vector boson scattering and anomalous quartic couplings in final states with ℓνqq or ℓℓqq plus jets using proton-proton collisions at √(s) = 13 TeV
• Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
• Neural Network-based Co-design of Output-Feedback Control Barrier Function and Observer
• Neural Network-Based Single-Carrier Joint Communication and Sensing: Loss Design, Constellation Shaping and Precoding
• HANN: Homotopy auxiliary neural network for solving nonlinear algebraic equations
• A Review on Single-Problem Multi-Attempt Heuristic Optimization
• ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
• Event Tokenization and Next-Token Prediction for Anomaly Detection at the Large Hadron Collider
• Items Proxy Bridging: Enabling Frictionless Critiquing in Knowledge Graph Recommendations
• Deep learning CAT bond valuation
• A Physics-Guided Probabilistic Surrogate Modeling Framework for Digital Twins of Underwater Radiated Noise
• Transformer-Based Neural Networks Backflow for Strongly Correlated Electronic Structure
• Field Calibration of Hyperspectral Cameras for Terrain Inference
• Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
• Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN
• Discovery of oxide Li-conducting electrolytes in uncharted chemical space via topology-constrained crystal structure prediction
• SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction
• Neural-Model-Augmented Hybrid NMS-OSD Decoders for Near-ML in Short Block Codes
• Multi-patch isogeometric neural solver for partial differential equations on computer-aided design domains
• Deep Survival Analysis for Competing Risk Modeling with Functional Covariates and Missing Data Imputation
• Quantum process tomography of a compressed time evolution circuit on superconducting quantum processors
• GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis
• Learning Relationships Between Separate Audio Tracks for Creative Applications
• ELPG-DTFS: Prior-Guided Adaptive Time-Frequency Graph Neural Network for EEG Depression Diagnosis
• Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption
• Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations
• SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
• Bundle Network: a Machine Learning-Based Bundle Method
• Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
• Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structure
• RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis
• Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
• Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
• Tumor Synthesis conditioned on Radiomics
• Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification
• From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions
• Plant3R: Fusing 3D feature learning with Gaussian splatting to enhance wheat plant 3D reconstruction precision
• DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph
• A Biophysical-Model-Informed Source Separation Framework For EMG Decomposition
• Cognitive State Inference from VR Motion via Motion Foundation Model
• Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
• An Agent-Based Framework for Automated Higher-Voice Harmony Generation
• Enhancing hyperspectral image prediction with contrastive learning in low-label regimes
• Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
• Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric
• IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting
• Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference
• ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning
• Neural Canonical Transformation for the Spectra of Fluxional Molecule CH5+
• Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
• Multi-Scale Spatial-Temporal Hypergraph Network with Lead-Lag Structures for Stock Time Series Forecasting
• Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
• Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
• StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
• Toward a Holistic Approach to Continual Model Merging
• Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
• Automated design of compound lenses with discrete-continuous optimization
• Node Classification via Simplicial Interaction with Augmented Maximal Clique Selection
• A Hierarchical Structure-Enhanced Personalized Recommendation Model for Traditional Chinese Medicine Formulas Based on KG Diffusion Guidance
• End-to-End Deep Learning for Predicting Metric Space-Valued Outputs
• Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail
• Temporal Generalization: A Reality Check
• DiffTex: Differentiable Texturing for Architectural Proxy Models
• MELCOT: A Hybrid Learning Architecture with Marginal Preservation for Matrix-Valued Regression
• UltraUNet: Real-Time Ultrasound Tongue Segmentation for Diverse Linguistic and Imaging Conditions
• ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
• Effective Quantization of Muon Optimizer States
• Dynamic Trust Calibration Using Contextual Bandits
• Revisiting Multivariate Time Series Forecasting with Missing Values
• Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models
• Overcoming the curse of dimensionality: Enabling multi-layer photon transport with recurrent neural network
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Interpreting Deep Learning: The Machine Learning Rorschach Test?
• Enhancing reconstruction capability of wavelet transform amorphous radial distribution function via machine learning assisted parameter tuning
• MRI-based estimation of physiologically consistent head conductivity and its impact on depth-dependent electric field distributions in transcranial magnetic stimulation
• Ghost poisoning: Making users invisible to speaker verification models
• CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
• MINT-RVAE: Multi-Cues Intention Prediction of Human-Robot Interaction using Human Pose and Emotion Information from RGB-only Camera Data
• Activation Function Design Sustains Plasticity in Continual Learning
• NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use
• Learning to Ball: Composing Policies for Long-Horizon Basketball Moves
• A Multi-Modality Evaluation of the Reality Gap in Autonomous Driving Systems
• MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning
• Reversible GNS for Dissipative Fluids with Consistent Bidirectional Dynamics
• Supervised Machine Learning for Predicting Open Quantum System Dynamics and Detecting Non-Markovian Memory Effects
• DHAGrasp: Synthesizing Affordance-Aware Dual-Hand Grasps with Text Instructions
• Deep learning for interval-censored failure time data from case-cohort studies
• Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
• Reparameterizing 4DVAR with neural fields
• Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
• Physically Plausible Multi-System Trajectory Generation and Symmetry Discovery
• Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration
• DroneFL: Federated Learning for Multi-UAV Visual Target Tracking
• Forecasting Seismic Waveforms: A Deep Learning Approach for Einstein Telescope
• SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips
• \LARGE GMP³: Learning-Driven, Bellman-Guided Trajectory Planning for UAVs in Real-Time on SE(3)
• Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
• PAS-SE: Personalized Auxiliary-Sensor Speech Enhancement for Voice Pickup in Hearables
• LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
• Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity
• Physics of Learning: A Lagrangian perspective to different learning paradigms
• PALQO: Physics-informed Model for Accelerating Large-scale Quantum Optimization
• Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy
• SemSight: Probabilistic Bird's-Eye-View Prediction of Multi-Level Scene Semantics for Navigation
• 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
• PerformSinger: Multimodal Singing Voice Synthesis Leveraging Synchronized Lip Cues from Singing Performance Videos
• Time-adaptive HénonNets for separable Hamiltonian systems
• Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems
• Synergistic Enhancement of Requirement-to-Code Traceability: A Framework Combining Large Language Model based Data Augmentation and an Advanced Encoder
• SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads
• Attention U-Net for all-sky continuous gravitational wave searches
• Learning to Lead Themselves: Agentic AI in MAS using MARL
• Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
• DynaFlow: Dynamics-embedded Flow Matching for Physically Consistent Motion Generation from State-only Demonstrations
• Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies
• A Unified Noise-Curvature View of Loss of Trainability
• Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs
• MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
• SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction
• Adaptive von Mises-Fisher Likelihood Loss for Supervised Deep Time Series Hashing
• Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG
• Look as You Leap: Planning Simultaneous Motion and Perception for High-DOF Robots
• ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
• Improved Frequency Tracking with Adaptive Moments for Narrowband Interference Mitigation in GNSS
• NMINE: Normalized Mutual Information Neural Estimation
• Trainability and Mode Separation of Mixed IQP-QCBMs
• ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring
• 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
• Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting
• Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
• FDDWAN: A Frequency-Decoupled Diffusion Network for Watermarking Attack
• Face and voice cross-modal association with learning convex feature embedding
• Collaborative feature aggregation for face super-resolution and robust re-identification
• ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation
• Convolutional neural shading for high-quality 3D reconstruction from multi-view images
• Graph Neural Multilevel Preconditioners for Iterative Solvers
• Comparison of a Parametric Physics-Informed Neural Network and a Tensorial Reduced-Order Model for the Shallow-Water Dam-Break Problem
• Does EEG Foundation Models Transfer to Speech? A Benchmark on Overt and Imagined Speech Decoding
• LLM-Guided Initialization for Accelerated Hybrid Quantum-Classical Medical Image Classification
• PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
• The Convergence Behavior of Adam under Heavy-Tailed Noise
• Neural network approximation in discrete dual norms with adaptive test spaces
• Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
• Rating for Parents: Predicting Children Suitability Rating for Movies Based on Language of the Movies
• Sparse component analysis: A method that uncovers separable computations within neural population activity
• Spontaneous symmetry breaking and Goldstone modes for deep information propagation
• Training Continuously‐Coupled Reconfigurable Photonic Chips with Quantum Machine Learning
• Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments
• Aligning Recommendations with User Popularity Preferences
• Detecting Positive Selection by Modeling Structure Within Images of Genetic Variation
• Differentiable Stochastic Halo Occupation Distribution with Galaxy Intrinsic Alignments
• Generative modeling with Gaussian Boson Sampling: classically trainable Bosonic Born Machines
• MentorCollab: Selective Large-to-Small Inference-Time Guidance for Efficient Reasoning
• Use What You Know: Causal Foundation Models with Partial Graphs
• Topology Aware Neural Interpolation of Scalar Fields
• DL-QC-fNIRS: a deep learning tool for automated quality control in functional near-infrared spectroscopy signals
• MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
• MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation
• Generating Human-AI Collaborative Design Sequence for 3D Assets via Differentiable Operation Graph
• Evaluating integrative strategies for incorporating phenotypic features in spatial transcriptomics
• EndoUFM: Utilizing Foundation Models for Monocular depth estimation of endoscopic images
• Camera Pose Refinement via 3D Gaussian Splatting
• Vocoder-Projected Feature Discriminator
• FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network
• Multi Resolution LSTM For Long Term Prediction In Neural Activity Video
• Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface
• Context-aware and Scale-insensitive Temporal Repetition Counting
• Learned harmonic mean estimation of the Bayesian evidence with normalizing flows
• Multiple agroecological practices use and climate change mitigation. A review
• Cascaded Text Generation with Markov Transformers
• When Does Preconditioning Help or Hurt Generalization?
• Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods
• Dynamic Upsampling of Smoke through Dictionary-based Learning
• Towards multi-instrument drum transcription
• The Pareto Frontier of Resilient Jet Tagging
• Spectral Signature Mapping from RGB Imagery for Terrain-Aware Navigation
• Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
• Gaussian Process Modeling with Genotype x Environment Kernels for Wheat Performance Prediction
• Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling
• Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks
• Shared-Weights Extender and Gradient Voting for Neural Network Expansion
• FlashGMM: Fast Gaussian Mixture Entropy Model for Learned Image Compression
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for\n Autonomous Driving
• LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis
• One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
• FlowCrypt: Flow-Based Lightweight Encryption with Near-Lossless Recovery for Cloud Photo Privacy
• LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detection
• CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
• Energy minimisation using overlapping tensor-product free-knot B-splines
• PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation
• Rapid Autotuning of a SiGe Quantum Dot into the Single-Electron Regime with Machine Learning and RF-Reflectometry FPGA-Based Measurements
• MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
• Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks
• Zero-shot Monocular Metric Depth for Endoscopic Images
• Machine learning approach to single-shot multiparameter estimation for the non-linear Schrödinger equation
• Financial Risk Relation Identification through Dual-view Adaptation
• A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models
• A convergence framework for energy minimisation of linear self-adjoint elliptic PDEs in nonlinear approximation spaces
• Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions
• M4SER: Multimodal, Multirepresentation, Multitask, and Multistrategy Learning for Speech Emotion Recognition
• Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection
• Replay and Synthetic Speech Detection with Res2net Architecture
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• What Makes You Unique? Attribute Prompt Composition for Object Re-Identification
• Neuromorphic dreaming as a pathway to efficient learning in artificial agents
• Detection of security smells in IaC scripts through semantics-aware code and language processing
• Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
• Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem
• GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
• VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
• Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
• CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
• Cluster Workload Allocation: A Predictive Approach Leveraging Machine Learning Efficiency
• Conditioning in Generative Quantum Denoising Diffusion Models
• Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules
• AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
• Learning Dexterous Manipulation with Quantized Hand State
• On Mutual Information Neural Estimation for Localization
• Compact representation of transonic airfoil buffet flows with observable-augmented machine learning
• Joint Pilot Allocation and Sequence Design for MIMO-OFDM Systems With Channel Sparsity
• Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents
• Pose Estimation of a Cable-Driven Serpentine Manipulator Utilizing Intrinsic Dynamics via Physical Reservoir Computing
• SISMA: Semantic Face Image Synthesis with Mamba
• Estimation of Temporal Muon Signals in Water-Cherenkov Detectors of the Surface Detector of the Pierre Auger Observatory
• Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction
• High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics
• Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification
• Learning Neural Antiderivatives
• Functional effects models: Accounting for preference heterogeneity in panel data with machine learning
• TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation
• On Multi-entity, Multivariate Quickest Change Point Detection
• MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning
• Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning
• Attentive AV-FusionNet: Audio-Visual Quality Prediction with Hybrid Attention
• Parameter-efficient fine-tuning (PEFT) of Vision Foundation Models for Atypical Mitotic Figure Classification
• LVADNet3D: A Deep Autoencoder for Reconstructing 3D Intraventricular Flow from Sparse Hemodynamic Data
• EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks
• Prospective Multi-Graph Cohesion for Multivariate Time Series Anomaly Detection
• Learning Scan-Adaptive MRI Undersampling Patterns with Pre-Optimized Mask Supervision
• A Deep-Learning-Driven Optimization-Based Inverse Solver for Accelerating the Marchenko Method
• MoPE: A Mixture of Password Experts for Improving Password Guessing
• Towards a Transparent and Interpretable AI Model for Medical Image Classifications
• Enhancing Reference-based Sketch Colorization via Separating Reference Representations
• A Proportional-Integral Controller-Incorporated SGD Algorithm for High Efficient Latent Factor Analysis
• No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learning
• ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
• Spectral Compressive Imaging via Chromaticity-Intensity Decomposition
• Variational processing of multimode squeezed light
• LLM-Guided Co-Training for Text Classification
• Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization
• Exploring Efficient Learning of Small BERT Networks with LoRA and DoRA
• TOFLUX: A Differentiable Topology Optimization Framework for Multiphysics Fluidic Problems
• Interpreting the Role of Visemes in Audio-Visual Speech Recognition
• Towards Robust Visual Continual Learning with Multi-Prototype Supervision
• Detecting Photoshopped Faces by Scripting Photoshop
• Empirical Asset Pricing via Machine Learning
• A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations
• CompSpoof: A Dataset and Joint Learning Framework for Component-Level Audio Anti-spoofing Countermeasures
• HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing
• GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading
• Geometric Integration for Neural Control Variates
• AFT: An Exemplar-Free Class Incremental Learning Method for Environmental Sound Classification
• KoopCast: Trajectory Forecasting via Koopman Operators
• MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation
• Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
• AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sports
• Boosting Active Learning with Knowledge Transfer
• Quantum Enhanced Anomaly Detection for ADS-B Data using Hybrid Deep Learning
• Learning Correspondence from the Cycle-Consistency of Time
• Enhancing WSI-Based Survival Analysis with Report-Auxiliary Self-Distillation
• Neural Architecture Search Algorithms for Quantum Autoencoders
• Analysis Plug-and-Play Methods for Imaging Inverse Problems
• OSI-flex: Optimization-Based Shearing Interferometry for Joint Phase and Shear Estimation Using a Flexible Open-Source Framework
• Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
• Communication Efficient Split Learning of ViTs with Attention-based Double Compression
• TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
• Precision Neural Networks: Joint Graph And Relational Learning
• Robust Barycenters of Persistence Diagrams
• Partial Column Generation with Graph Neural Networks for Team Formation and Routing
• Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer
• MeanFlowSE: one-step generative speech enhancement via conditional mean flow
• Graph-Aware Learning Rates for Decentralized Optimization
• Spatial-CLAP: Learning Spatially-Aware audio--text Embeddings for Multi-Source Conditions
• Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models
• FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver
• Pre-training Autoencoder for Acoustic Event Classification via Blinky
• IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorders
• SpeechMLC: Speech Multi-label Classification
• Mitigating Intra-Speaker Variability in Diarization with Style-Controllable Speech Augmentation
• Domain Adaptation for Ulcerative Colitis Severity Estimation Using Patient-Level Diagnoses
• Age of Information Aided Intelligent Grant-Free Massive Access for Heterogeneous mMTC Traffic
• TTSR: A Transformer-Based Topography Neural Network for Digital Elevation Model Super-Resolution
• Online reinforcement learning via sparse Gaussian mixture model Q-functions
• Towards a Robust Machine-Learning Pipeline for 21-cm Cosmology Data Analysis I: A Roadmap for Development and Demonstration of Robustness Against PSF Modeling Errors
• Dynamic Spectrum Matching with One-shot Learning
• Recurrent Neural Networks With Limited Numerical Precision
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation
• Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation
• UTOPY: Unrolling Algorithm Learning via Fidelity Homotopy for Inverse Problems
• Adaptive and Regime-Aware RL for Portfolio Optimization
• A universal machine learning model for the electronic density of states
• ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images
• Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
• Generative AI for Misalignment-Resistant Virtual Staining to Accelerate Histopathology Workflows
• Novel Phase-Noise-Tolerant Variational-Autoencoder-Based Equalization Suitable for Space-Division-Multiplexed Transmission
• Enhancing Time Awareness in Generative Recommendation
• Inverse Design of Amorphous Materials with Targeted Properties
• Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection
• Efficient Quantization-Aware Neural Receivers: Beyond Post-Training Quantization
• Binary Classification of Light and Dark Time Traces of a Transition Edge Sensor Using Convolutional Neural Networks
• Deep Lookup Network
• A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation
• RF-LSCM: Pushing Radiance Fields to Multi-Domain Localized Statistical Channel Modeling for Cellular Network Optimization
• Multimodal Transformer with Multi-View Visual Representation for Image Captioning
• On Tackling High-Dimensional Nonconvex Stochastic Optimization via Stochastic First-Order Methods with Non-smooth Proximal Terms and Variance Reduction
• UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
• Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction
• Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
• AdaptiveK Sparse Autoencoders: Dynamic Sparsity Allocation for Interpretable LLM Representations
• SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation
• Learning Progression-Guided AI Evaluation of Scientific Models To Support Diverse Multi-Modal Understanding in NGSS Classroom
• Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation
• Unified Spatiotemporal Physics-Informed Learning (USPIL): A Framework for Modeling Complex Predator-Prey Dynamics
• Quickly Tuning Foundation Models for Image Segmentation
• High-Dimensional Bayesian Model Comparison in Cosmology with GPU-accelerated Nested Sampling and Neural Emulators
• Importance-Weighted Domain Adaptation for Sound Source Tracking
• Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
• SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data
• Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategy
• Spatiotemporal graph neural process for reconstruction, extrapolation, and classification of cardiac trajectories
• A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System
• AREPAS: Anomaly Detection in Fine-Grained Anatomy with Reconstruction-Based Semantic Patch-Scoring
• Similarity-Distance-Magnitude Activations
• What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
• Deep learning approach for flow visualization in background-oriented schlieren
• A Robust and Precise ConvNet for small non-coding RNA classification\n (RPC-snRC)
• L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems
• Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline
• FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation
• Curvature Learning for Generalization of Hyperbolic Neural Networks
• Multi-Metric Preference Alignment for Generative Speech Restoration
• Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
• End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection
• Joint AoI and Handover Optimization in Space-Air-Ground Integrated Network
• Deep Tensor Learning for Reliable Channel Charting from Incomplete and Noisy Measurements
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
• Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language Models
• Does Calibration Affect Human Actions?
• Geolocation-Aware Robust Spoken Language Identification
• Automatic Network Planning with Digital Radio Twin
• Entanglement and optimization within autoregressive neural quantum states
• Robust Fetal Pose Estimation across Gestational Ages via Cross-Population Augmentation
• Deep Multi-camera People Detection
• Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
• Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis
• Modeling Non-Uniform Hypergraphs Using Determinantal Point Processes
• Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
• Determining the boundary of dynamical chaos in the generalized Chirikov map via machine learning
• Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis
• Know What You Don't Know: Selective Prediction for Early Exit DNNs
• Machine Learning-Driven Predictive Resource Management in Complex Science Workflows
• FR-Net: Learning Robust Quadrupedal Fall Recovery on Challenging Terrains through Mass-Contact Prediction
• Drug Repurposing Using Deep Embedded Clustering and Graph Neural Networks
• K-Level Policy Gradients for Multi-Agent Reinforcement Learning
• When marine radar target detection meets pretrained large language models
• Adaptive Spatial Goodness Encoding: Advancing and Scaling Forward-Forward Learning Without Backpropagation
• Optimizing Quantum Photonic Integrated Circuits using Differentiable Tensor Networks
• Cluster Models for Next-Generation, Machine-Learning-Based Energy Functions for Molecular Simulations
• PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
• SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
• Real-time reinforcement learning for turbulent state-dependent control in a bluff-body wake
• Feature Space Topology Control via Hopkins Loss
• UnLoc: Leveraging Depth Uncertainties for Floorplan Localization
• Probabilistic Temporal Masked Attention for Cross-view Online Action Detection
• Gaze Authentication: Factors Influencing Authentication Performance
• Simulating Sinogram-Domain Motion and Correcting Image-Domain Artifacts Using Deep Learning in HR-pQCT Bone Imaging
• Local Density-Based Anomaly Score Normalization for Domain Generalization
• Optimal message passing for molecular prediction is simple, attentive and spatial
• Gradient Methods with Online Scaling Part II. Practical Aspects
• A Traditional Approach to Symbolic Piano Continuation
• GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction
• Transformer Networks for Continuous Gravitational-wave Searches
• Curve-based slicer for multi-axis DLP 3D printing
• Reinforcement Learning for Quantum Network Control with Application-Driven Objectives
• DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
• Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
• Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Data
• A neural recommender system leveraging transfer learning for property prediction of ionic liquids
• A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss
• Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
• Byte by Byte: Unmasking Browser Fingerprinting at the Function Level Using V8 Bytecode Transformers
• Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification
• Engineering Spatial and Molecular Features from Cellular Niches to Inform Predictions of Inflammatory Bowel Disease
• Gradient-based search of quantum phases: discovering unconventional fractional Chern insulators
• Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization
• Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
• HGEN: Heterogeneous Graph Ensemble Networks
• Deep Neural Networks can eliminate Spiral-wave Turbulence in Cardiac Tissue Models
• Bayesian representation learning with oracle constraints
• Dense U-net for super-resolution with shuffle pooling layer
• Database Views as Explanations for Relational Deep Learning
• NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
• Align 3D Representation and Text Embedding for 3D Content Personalization
• Channel Estimation and Analog Precoding for Pixel-based Fluid-Antenna-Assisted Multiuser MIMO-OFDM Systems
• CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback
• Constructing a Question-Answering Simulator through the Distillation of LLMs
• ProgD: Progressive Multi-scale Decoding with Dynamic Graphs for Joint Multi-agent Motion Forecasting
• GmSLM : Generative Marmoset Spoken Language Modeling
• OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge
• Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
• Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation
• Trends in the Population of Binary Black Holes Following the Fourth Gravitational-Wave Transient Catalog: a Data-Driven Analysis
• Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning
• UM3: Unsupervised Map to Map Matching
• WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
• Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
• Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
• Augmenting Neural Networks-Based Model Approximators in Robotic Force-Tracking Tasks
• Decentor-V: Lightweight ML Training on Low-Power RISC-V Edge Devices
• Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
• Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing
• Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
• Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• LLM-Guided Ansätze Design for Quantum Circuit Born Machines in Financial Generative Modeling
• LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models
• EAST: An Efficient and Accurate Scene Text Detector
• A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions
• Continuous Regularized Wasserstein Barycenters
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Context-Aware Query Refinement for Target Sound Extraction: Handling Partially Matched Queries
• Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
• Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
• An Alternative View: When Does SGD Escape Local Minima?
• Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Data
• Recurrence Meets Transformers for Universal Multimodal Retrieval
• Music Genre Classification using Machine Learning Techniques
• Dynamic Routing Between Capsules
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• DiffPlace: A Conditional Diffusion Framework for Simultaneous VLSI Placement Beyond Sequential Paradigms
• SVN-ICP: Uncertainty Estimation of ICP-based LiDAR Odometry using Stein Variational Newton
• A Multi-resolution Approach to Expression Recognition in the Wild
• DeepMVS: Learning Multi-view Stereopsis
• Comparison of the propulsion of helical microrobots based on hard- and soft-magnetic elements under rotating external magnetic fieldsv
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
• LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors
• SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compression
• Root Mean Square Layer Normalization
• Nonlinear Collaborative Scheme for Deep Neural Networks
• Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
• Improving Quantum Recurrent Neural Networks with Amplitude Encoding
• Using Optimal Transport Aligned Latent Embeddings for Separated Flow Analysis
• SA-OOSC: A Multimodal LLM-Distilled Semantic Communication Framework for Enhanced Coding Efficiency with Scenario Understanding
• AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
• BULL-ODE: Bullwhip Learning with Neural ODEs and Universal Differential Equations under Stochastic Demand
• Disentangling deep neural networks with rectified linear units using duality
• Can Neural Networks Understand Logical Entailment?
• Long Document Ranking with Query-Directed Sparse Transformer
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
• Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
• Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
• SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
• DDNet: A Unified Physics-Informed Deep Learning Framework for Semiconductor Device Modeling
• Feature-map-level Online Adversarial Knowledge Distillation
• CEM-RL: Combining evolutionary and gradient-based methods for policy search
• Learning Generalized Hamiltonian Dynamics with Stability from Noisy Trajectory Data
• 3D Mapping of Defects and Moiré Corrugations via Electron Ptychography Atomic Coordinate Retrieval
• LIMFAST. IV. Learning High-Redshift Galaxy Formation from Multiline Intensity Mapping with Implicit Likelihood Inference
• Towards real-time surrogate-free Bayesian inversion for neutron reflectometry
• Follow Your Path: a Progressive Method for Knowledge Distillation
• Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
• HiPrFlame-An ab initio based real-fluid modeling approach for high-pressure combustion-I. Rationale, methodology, and application to laminar premixed flames
• LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
• Lane Change Intention Prediction of two distinct Populations using a Transformer
• Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
• Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
• Orthogonal Recurrent Neural Networks with Scaled Cayley Transform
• VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval
• Adam⁺: A Stochastic Method with Adaptive Variance Reduction
• RS-Net: Regression-Segmentation 3D CNN for Synthesis of Full Resolution\n Missing Brain MRI in the Presence of Tumours
• Reinforcement learning meets bioprocess control through behaviour cloning: Real-world deployment in an industrial photobioreactor
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Learning Texture Manifolds with the Periodic Spatial GAN
• Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofing
• DNN-based Digital Twin Framework of a DC-DC Buck Converter using Spider Monkey Optimization Algorithm
• Guiding Cascading Failure Search with Interpretable Graph Convolutional Network
• GANS for Sequences of Discrete Elements with the Gumbel-softmax\n Distribution
• Optical field characterization at the fundamental limit of spatial resolution with a trapped ion
• A level-set structural approach for multi-physics joint inversion using full-waveform and gravity data
• Attention U-Net: Learning Where to Look for the Pancreas
• Dividing and Conquering Cross-Modal Recipe Retrieval: from Nearest Neighbours Baselines to SoTA
• Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval
• Deep Learning for Markov Chains: Lyapunov Functions, Poisson's Equation, and Stationary Distributions
• AxelSMOTE: An Agent-Based Oversampling Algorithm for Imbalanced Classification
• Self-Adaptive Training: beyond Empirical Risk Minimization
• Provable Representation Learning for Imitation Learning via Bi-level Optimization
• A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes
• Fooling Computer Vision into Inferring the Wrong Body Mass Index
• Micro-Expression Recognition via Fine-Grained Dynamic Perception
• Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
• Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning
• Dual Reweighting Domain Generalization for Face Presentation Attack Detection
• Detection of E-scooter Riders in Naturalistic Scenes
• An Explicit Scheme for Pathwise XVA Computations
• InfoVAE: Information Maximizing Variational Autoencoders
• Learning to Teach with Dynamic Loss Functions
• VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge
• Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
• On the Utility of Model Learning in HRI
• Fine-grained Video Categorization with Redundancy Reduction Attention
• Deep learning-based phase prediction of high-entropy alloys: Optimization, generation, and explanation
• Passage Re-ranking with BERT
• Contrastive Learning of Structured World Models
• Non-linear cooling and control of a mechanical quantum harmonic oscillator
• Morphological Perceptron with Competitive Layer: Training Using Convex-Concave Procedure
• Clinical Concept Extraction with Contextual Word Embedding
• DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
• Anti-efficient encoding in emergent communication
• End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient
• Motion Retargetting based on Dilated Convolutions and Skeleton‐specific Loss Functions
• New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR
• Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
• Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
• Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
• Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
• Ensemble of Precision-Recall Curve (PRC) Classification Trees with Autoencoders
• Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation
• Deep Keyphrase Generation
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• MelNet: A Generative Model for Audio in the Frequency Domain
• A Multigrid Method for Efficiently Training Video Models
• Graph Connectionist Temporal Classification for Phoneme Recognition
• Deep multi-stations weather forecasting: explainable recurrent convolutional neural networks
• MicroNet for Efficient Language Modeling
• Interpretable machine learning models: a physics-based view
• Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
• Memory-Efficient Network for Large-scale Video Compressive Sensing
• Efficient Video Transformers with Spatial-Temporal Token Selection
• Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN
• Solving Inverse Acoustic Obstacle Scattering Problem with Phaseless Far-Field Measurement Using Deep Neural Network Surrogates
• Beyond I-Con: Exploring New Dimension of Distance Measures in Representation Learning
• Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA
• Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
• Uniform Information Density and Syntactic Reduction: Revisiting that-Mentioning in English Complement Clauses
• A Comparison of Super-Resolution and Nearest Neighbors Interpolation Applied to Object Detection on Satellite Data
• Split Learning for collaborative deep learning in healthcare
• XMUspeech Systems for the ASVspoof 5 Challenge
• Kinetics of Barrier Crossing Events from Temperature Accelerated Sliced Sampling Simulations
• S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
• Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imaging
• Ecologically Valid Benchmarking and Adaptive Attention: Scalable Marine Bioacoustic Monitoring
• Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
• Rethinking PointNet Embedding for Faster and Compact Model
• ML-PWS: Estimating the Mutual Information Between Experimental Time Series Using Neural Networks
• A fast machine learning tool to predict the composition of astronomical ices from infrared absorption spectra
• Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Autonomous construction of parameterizable 3D leaf models from scanned sweet pepper leaves with deep generative networks
• Least Squares Generative Adversarial Networks
• Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
• Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
• What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes
• Stylized Neural Painting
• LibriQuote: A Speech Dataset of Fictional Character Utterances for Expressive Zero-Shot Speech Synthesis
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• Autonomous Time-Optimal Many-Revolution Orbit Raising for Electric Propulsion GEO Satellites via Neural Networks
• Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
• Disentangled Multi-modal Learning of Histology and Transcriptomics for Cancer Characterization
• Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning
• Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
• Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
• Deep Gamblers: Learning to Abstain with Portfolio Theory
• Open Set Domain Adaptation by Backpropagation
• Sample Efficient Certification of Discrete-Time Control Barrier Functions
• 1D convolutional neural networks and applications: A survey
• DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary Supervision
• Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• Optimal Multi-Task Learning at Regularization Horizon for Speech Translation Task
• Critic Regularized Regression
• Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
• Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning
• Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning
• Glioma Classification Using Multimodal Radiology and Histology Data
• Neural Architecture Search via Bregman Iterations
• Tensor Network for Supervised Learning at Finite Temperature
• Conversational Semantic Role Labeling
• Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning
• Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks
• A Useful Motif for Flexible Task Learning in an Embodied Two-Dimensional Visual Environment
• Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
• Deep Intrinsic Coregionalization Multi-Output Gaussian Process Surrogate with Active Learning
• Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields
• Detection of noise correlations in two qubit systems by Machine Learning
• Temporal social network modeling of mobile connectivity data with graph neural networks
• Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
• AutoDetect: Designing an Autoencoder-based Detection Method for Poisoning Attacks on Object Detection Applications in the Military Domain
• PatchNet: A hierarchical approach for neural field-level inference from Quijote Simulations
• Learning to Simulate Complex Physics with Graph Networks
• Putting An End to End-to-End: Gradient-Isolated Learning of Representations
• Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
• TRADI: Tracking deep neural network weight distributions for uncertainty\n estimation
• One-shot emotional voice conversion based on feature separation
• FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization
• A Blended Deep Learning Approach for Predicting User Intended Actions
• Long-Term Vehicle Localization by Recursive Knowledge Distillation
• Information transmission: Inferring change area from change moment in time series remote sensing images
• Human De-occlusion: Invisible Perception and Recovery for Humans
• Temporal Convolutional Networks for Action Segmentation and Detection
• Boundary-Seeking Generative Adversarial Networks
• Under Pressure: Learning to Detect Slip with Barometric Tactile Sensors
• Stochastic versus Deterministic in Stochastic Gradient Descent
• Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
• Learning Particle Dynamics Subject to Rigid Body Manipulations Using Graph Neural Networks
• Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
• Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation
• Bidirectional Tree-Structured LSTM with Head Lexicalization
• MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall
• Simultaneous approximation of multiple degenerate states using a single neural network quantum state
• Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• RiverScope: High-Resolution River Masking Dataset
• Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
• VASSO: Variance Suppression for Sharpness-Aware Minimization
• QUEENS: An Open-Source Python Framework for Solver-Independent Analyses of Large-Scale Computational Models
• Regularising Non-linear Models Using Feature Side-information
• Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks
• Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
• PonderNet: Learning to Ponder
• CLEAR: Contrastive Learning for Sentence Representation
• Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data
• PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction
• Learning to Prove from Synthetic Theorems
• A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• NVIDIA SimNet^TM: an AI-accelerated multi-physics simulation framework
• Enriched Annotations for Tumor Attribute Classification from Pathology Reports with Limited Labeled Data
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Generative Adversarial Frontal View to Bird View Synthesis
• Isolation and Localization of Unknown Faults Using Neural Network-Based\n Residuals
• A deep learning-driven iterative scheme for high-dimensional HJB equations in portfolio selection with exogenous and endogenous costs
• The gap between theory and practice in function approximation with deep neural networks
• NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking
• DivMerge: A divergence-based model merging method for multi-tasking
• Physics-informed deep generative models
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
• TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
• Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes
• Differentially Private Federated Learning on Heterogeneous Data
• FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems
• The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
• prDeep: Robust Phase Retrieval with a Flexible Deep Network
• Robust Small Methane Plume Segmentation in Satellite Imagery
• Vibrational Spectra of Materials and Molecules from Partially-Adiabatic Elevated-Temperature Centroid Molecular Dynamics
• PIANO: Physics Informed Autoregressive Network
• Phenomenological classification of the Zwicky Transient Facility\n astronomical event alerts
• Symmetrical Gaussian Error Linear Units (SGELUs)
• Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
• Continuous Speech Recognition using EEG and Video
• Fully convolutional networks for structural health monitoring through\n multivariate time series classification
• Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation
• Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease
• Latent Gene Diffusion for Spatial Transcriptomics Completion
• EigenBench: A Comparative Behavioral Measure of Value Alignment
• Lightweight Pyramid Networks for Image Deraining
• Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
• Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning
• Frame Averaging for Invariant and Equivariant Network Design
• Deep Learning-Aided Trainable Projected Gradient Decoding for LDPC Codes
• Training GANs with Stronger Augmentations via Contrastive Discriminator
• Augmented KRnet for density estimation and approximation
• Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
• Optimizing Paths for Adaptive Fly-Scan Microscopy: An Extended Version
• INF-3DP: Implicit Neural Fields for Collision-Free Multi-Axis 3D Printing
• DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Minimal Effort Back Propagation for Convolutional Neural Networks
• Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition
• Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport
• Neural Topic Model via Optimal Transport
• Blind Face Restoration via Deep Multi-scale Component Dictionaries
• Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
• FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
• Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
• Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
• EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
• FuXi-TC: A generative framework integrating deep learning and physics-based models for improved tropical cyclone forecasts
• Online learning and continuous model upgrading with data streams through the Kafka-ML framework
• Towards cross-lingual distributed representations without parallel text\n trained with adversarial autoencoders
• A turbulent eddy-viscosity surrogate modeling framework for\n Reynolds-Averaged Navier-Stokes simulations
• Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity
• Theory and Experiments on Vector Quantized Autoencoders
• Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
• Modeling and benchmarking quantum optical neurons for efficient neural computation
• Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference
• Preconditioned Regularized Wasserstein Proximal Sampling
• Entropy-Driven Curriculum for Multi-Task Training in Human Mobility Prediction
• Reinforcement learning for graph theory, Parallelizing Wagner's approach
• Physics-Guided Neural Networks for Constructing Nucleon-Nucleon Inverse Potentials
• High-Precision Mixed Feature Fusion Network Using Hypergraph Computation for Cervical Abnormal Cell Detection
• Pseudo-Encoded Stochastic Variational Inference
• Mapping high-performance RNNs to in-memory neuromorphic chips
• Advanced Torrential Loss Function for Precipitation Forecasting
• Comparison between Supervised and Unsupervised Learning in Deep Unfolded Sparse Signal Recovery
• Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
• An affinity based opinion dynamics model for the evolving pattern of political polarization
• RAMS: Residual-based adversarial-gradient moving sample method for scientific machine learning in solving partial differential equations
• LobRA: Multi-tenant Fine-tuning over Heterogeneous Data
• ADMP-GNN: Adaptive Depth Message Passing GNN
• SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning
• Integral Human Pose Regression
• Separation Guided Speaker Diarization in Realistic Mismatched Conditions
• A fully recurrent feature extraction for single channel speech enhancement
• A general framework for defining and optimizing robustness
• FlauBERT: Unsupervised Language Model Pre-training for French
• The specious art of single-cell genomics
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Leveraging learned representations and multitask learning for lysine methylation site discovery
• Data-driven modeling for flow reconstruction from sparse temperature measurements
• ActionVLAD: Learning spatio-temporal aggregation for action classification
• QUBO-based training for VQAs on Quantum Annealers
• MD-PNOP: Equation-Recast Neural Operators for Minimal-Data Extrapolation and PDE Solver Acceleration
• A Continuous-Time Consistency Model for 3D Point Cloud Generation
• Group-wise Correlation Stereo Network
• Towards Emotional Support Dialog Systems
• PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Clouds
• Anticipatory Fall Detection in Humans with Hybrid Directed Graph Neural Networks and Long Short-Term Memory
• DiffCoord: Differentiable Coordination for Distributed Multi-Agent Trajectory Optimization
• TensorDiffEq: Scalable Multi-GPU Forward and Inverse Solvers for Physics Informed Neural Networks
• GaussianGAN: Real-Time Photorealistic controllable Human Avatars
• Content-Aware Unsupervised Deep Homography Estimation
• Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
• REVELIO -- Universal Multimodal Task Load Estimation for Cross-Domain Generalization
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
• The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
• Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
• Quantum Optimal Control with Geodesic Pulse Engineering
• IS³ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering
• DarkVRAI: Capture-Condition Conditioning and Burst-Order Selective Scan for Low-light RAW Video Denoising
• Convergence Rates of Time Discretization in Extended Mean Field Control
• Assessing the Advantages and Limitations of Quantum Neural Networks in Regression Tasks
• Classification of Audio Segments in Call Center Recordings using\n Convolutional Recurrent Neural Networks
• Learning Slice-Aware Representations with Mixture of Attentions
• A computer vision-based approach to enhance seismic catalogues
• IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects
• Source-Aware Neural Speech Coding for Noisy Speech Compression
• Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with\n Transformers
• Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
• A Goal-Based Movement Model for Continuous Multi-Agent Tasks
• A differential neural network learns stochastic differential equations and the Black-Scholes equation for pricing multi-asset options
• Nash Q-Network for Multi-Agent Cybersecurity Simulation
• IndiaWeatherBench: A Dataset and Benchmark for Data-Driven Regional Weather Forecasting over India
• Missing Data Imputation using Neural Cellular Automata
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
• Automatic airway segmentation from Computed Tomography using robust and efficient 3-D convolutional neural networks
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• Handling Missing Data with Graph Representation Learning
• Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
• Clipping free attacks against artificial neural networks
• Risk‐aware autonomous search and rescue with multiagent reinforcement learning
• Differentiable MPC for End-to-end Planning and Control
• Inductive Biases and Variable Creation in Self-Attention Mechanisms
• The relativistic discriminator: a key element missing from standard GAN
• Estimating and Improving Fairness with Adversarial Learning
• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
• Numerical Simulation of Exchange Option with Finite Liquidity:\n Controlled Variate Model
• Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecasting
• A Deep Learning Framework for Joint Channel Acquisition and Communication Optimization in Movable Antenna Systems
• Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation
• SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning
• Learning Residual Images for Face Attribute Manipulation
• Domain Attention Consistency for Multi-Source Domain Adaptation
• When Shall I Be Empathetic? The Utility of Empathetic Parameter Estimation in Multi-Agent Interactions
• Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencoder
• An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients
• Learning to Synthesize a 4D RGBD Light Field from a Single Image
• Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation
• Reexamining Machine Learning Models on Predicting Thermoelectric Properties
• FNODE: Flow-Matching for data-driven simulation of constrained multibody systems
• Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
• Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
• Learning from Silence and Noise for Visual Sound Source Localization
• Transfer Learning for Minimum Operating Voltage Prediction in Advanced Technology Nodes: Leveraging Legacy Data and Silicon Odometer Sensing
• Bayesian perspectives for quantum states and application to ab initio quantum chemistry
• OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
• Is this chart lying to me? Automating the detection of misleading visualizations
• Dynamic Multi-Level Multi-Task Learning for Sentence Simplification
• Adaptive generative moment matching networks for improved learning of dependence structures
• Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning
• Why flatness does and does not correlate with generalization for deep neural networks
• Neural network gradient-based learning of black-box function interfaces
• Learning Intrinsic Image Decomposition from Watching the World
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
• Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Two Routes to Scalable Credit Assignment without Weight Symmetry
• Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity
• DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors
• Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
• Representation Learning with Adaptive Superpixel Coding
• Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
• Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
• T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
• Reannealing of Decaying Exploration Based On Heuristic Measure in Deep Q-Network
• AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep\n Architecture
• Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
• Towards Improved Speech Recognition through Optimized Synthetic Data Generation
• LIRA: Lifelong Image Restoration from Unknown Blended Distortions
• Correct-and-Memorize: Learning to Translate from Interactive Revisions
• SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
• Physics-Informed Neural Network Modeling and Predictive Control of District Heating Systems
• Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks
• Controllable Invariance through Adversarial Feature Learning
• Adaptive Computation Time for Recurrent Neural Networks
• DeepPhysics: a physics aware deep learning framework for real-time simulation
• Exploring Contextualized Neural Language Models for Temporal Dependency Parsing
• RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval
• Improving Generative Imagination in Object-Centric World Models
• Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Simple Models for Word Formation in English Slang
• Variational zero-inflated Gaussian processes with sparse kernels
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design
• Learning to Remember Rare Events
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
• Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
• Automating the Deep Space Network Data Systems; A Case Study in Adaptive Anomaly Detection through Agentic AI
• Cosmo-Learn: code for learning cosmology using different methods and mock data
• KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
• Data-Free Adversarial Distillation
• Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
• Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
• Web Applicable Computer-aided Diagnosis of Glaucoma Using Deep Learning
• Native Logical and Hierarchical Representations with Subspace Embeddings
• Adversarial Training for Large Neural Language Models
• Reduced-order Deep Learning for Flow Dynamics
• Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning
• CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems
• Data Driven Programming of Photonic Integrated Circuits
• Synthesis and SOS-based Stability Verification of a Neural-Network-Based Controller for a Two-wheeled Inverted Pendulum
• Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
• On fine alignment of transmitted beams for TianQin with far-field wavefront error
• GLaRE: A Graph-based Landmark Region Embedding Network for Emotion Recognition
• Towards Automated EEG-Based Epilepsy Detection Using Deep Convolutional Autoencoders
• Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset
• Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
• Prediction of mortality and resource utilization in critical care: a deep learning approach using multimodal electronic health records with natural language processing techniques
• Graph-Based Uncertainty Modeling and Multimodal Fusion for Salient Object Detection
• BiListing: Modality Alignment for Listings
• Progressive Semantic Residual Quantization for Multimodal-Joint Interest Modeling in Music Recommendation
• Artificial neural network solver for Fokker-Planck and Koopman eigenfunctions
• SimShear: Sim-to-Real Shear-based Tactile Servoing
• Efficient Meta Lifelong-Learning with Limited Memory
• Controllable Open-ended Question Generation with A New Question Type Ontology
• Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
• Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• TempNodeEmb:Temporal Node Embedding considering temporal edge influence matrix
• Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics
• Polynomial Chaos Expansion for Operator Learning
• SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
• FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architecture
• Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks
• Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies
• Disentanglement for Discriminative Visual Recognition
• NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• Scalable Rule-Based Representation Learning for Interpretable Classification
• Finding and Fixing Spurious Patterns with Explanations
• Testing and Learning on Distributions with Symmetric Noise Invariance
• Symplectic convolutional neural networks
• FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
• Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
• Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
• Quantum latent distributions in deep generative models
• Search for Beyond the Standard Model physics with anomaly detection in multilepton final states in pp collisions at √(s)=13 TeV with the ATLAS detector
• Tune My Adam, Please!
• Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception
• Feature Extraction on Synthetic Black Hole Images
• Whitening for Self-Supervised Representation Learning
• Real-time visual tracking by deep reinforced decision making
• A Classifying Variational Autoencoder with Application to Polyphonic Music Generation
• High-Speed FHD Full-Color Video Computer-Generated Holography
• Interact-Custom: Customized Human Object Interaction Image Generation
• Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation
• Early Prediction for Physical Human Robot Collaboration in the Operating Room
• Attention Based Natural Language Grounding by Navigating Virtual Environment
• ELIXIR: Efficient and LIghtweight model for eXplaIning Recommendations
• Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
• Robust Detection of Synthetic Tabular Data under Schema Variability
• Adversarial T-shirt! Evading Person Detectors in A Physical World
• Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram
• Stack Trace-Based Crash Deduplication with Transformer Adaptation
• Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
• Investigating Code-Mixed Modern Standard Arabic-Egyptian to English\n Machine Translation
• Path to Intelligence: Measuring Similarity between Human Brain and Large Language Model Beyond Language Task
• EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
• Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
• Machine Learning with Membership Privacy using Adversarial\n Regularization
• Implicit Regularization in Tensor Factorization
• DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking
• Meta-Learning Representations for Continual Learning
• Improving Local Identifiability in Probabilistic Box Embeddings
• The Riemannian Geometry of Deep Generative Models
• Mini-Batch Robustness Verification of Deep Neural Networks
• Heavy Ball Neural Ordinary Differential Equations
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
• Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Data
• Dial2Desc: End-to-end Dialogue Description Generation
• Dirichlet Variational Autoencoder for Text Modeling
• Sequence-to-sequence Models for Small-Footprint Keyword Spotting
• On the Generalisation of Koopman Representations for Chaotic System Control
• Near-Data Processing for Differentiable Machine Learning Models
• The Functional Neural Process
• Human-Aware Motion Deblurring
• MSC: A Dataset for Macro-Management in StarCraft II
• Learning Trailer Moments in Full-Length Movies
• Why gradient clipping accelerates training: A theoretical justification for adaptivity
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Temperature-Aware Recurrent Neural Operator for Temperature-Dependent Anisotropic Plasticity in HCP Materials
• Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion
• eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
• Revisiting associative recall in modern recurrent models
• Assessment of Reward Functions in Reinforcement Learning for Multi-Modal\n Urban Traffic Control under Real-World limitations
• A Deep Learning Application for Psoriasis Detection
• VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results
• Inter-expert reliability in multi-field-of-view automatic drusen segmentation analysis using optical coherence tomography
• What they do when in doubt: a study of inductive biases in seq2seq learners
• Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach
• Stabilizing Training of Generative Adversarial Networks through Regularization
• AI Safety Gridworlds
• Training Transformers for Mesh-Based Simulations
• Hardware Implementation of a Zero-Prior-Knowledge Approach to Lifelong Learning in Kinematic Control of Tendon-Driven Quadrupeds
• Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
• Differentiable optics with ∂Lux: I—deep calibration of flat field and phase retrieval with automatic differentiation
• Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
• Regex Queries over Incomplete Knowledge Bases
• Generative Hybrid Representations for Activity Forecasting with No-Regret Learning
• Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection
• Deep learning for the semi-classical limit of the Schrödinger equation
• Curriculum Approximate Unlearning for Session-based Recommendation
• Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition
• Hybrid Least Squares/Gradient Descent Methods for DeepONets
• Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching
• Learning Object Relation Graph and Tentative Policy for Visual Navigation
• Detecting anthropogenic cloud perturbations with deep learning
• Audio To Score Matching By Combining Phonetic And Duration Information.
• Lift-the-flap: what, where and when for context reasoning
• Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules
• DualMark: Identifying Model and Training Data Origins in Generated Audio
• Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
• Unifying local and non-local signal processing with graph CNNs
• Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
• Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels
• TOAST: Fast and scalable auto-partitioning based on principled static analysis
• SgSum: Transforming Multi-document Summarization into Sub-graph Selection
• Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze
• Deep Latent-Variable Kernel Learning
• Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
• Reinforcement learning entangling operations on spin qubits
• CUTE-MRI: Conformalized Uncertainty-based framework for Time-adaptivE MRI
• Cross-Modality Controlled Molecule Generation with Diffusion Language Model
• Transplant Then Regenerate: A New Paradigm for Text Data Augmentation
• Sensing Integrated DFT-Spread OFDM Waveform and Deep Learning-powered Receiver Design for Terahertz Integrated Sensing and Communication Systems
• Scaled Signed Averaging Improves In-Context and Early Learning Benchmark Performance in Small Transformers
• Understanding Data Influence with Differential Approximation
• DualNILM: Energy Injection Identification Enabled Disaggregation with Deep Multi-Task Learning
• DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion
• Global-Distribution Aware Scenario-Specific Variational Representation Learning Framework
• RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities
• Supervised Sentiment Classification with CNNs for Diverse SE Datasets
• Preconditioner on Matrix Lie Group for SGD
• Enhancing Contrastive Link Prediction With Edge Balancing Augmentation
• Natural Language Processing to Detect Cognitive Concerns in Electronic Health Records Using Deep Learning
• DeepEmoNet: Building Machine Learning Models for Automatic Emotion Recognition in Human Speeches
• AnchorSync: Global Consistency Optimization for Long Video Editing
• Improved Mapping Between Illuminations and Sensors for RAW Images
• Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment
• An RNN-Survival Model to Decide Email Send Times
• Group Anomaly Detection using Deep Generative Models
• VarNet: Variational Neural Networks for the Solution of Partial Differential Equations
• Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement
• Hierarchical Multitask Learning Approach for BERT
• Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition
• Self-Supervised Reinforcement Learning for Recommender Systems
• Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
• Agent-Centric Representations for Multi-Agent Reinforcement Learning
• Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• End-to-end 3D face reconstruction with deep neural networks
• Computationally efficient cardiac views projection using 3D Convolutional Neural Networks
• Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
• Neural Predictor for Neural Architecture Search
• Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods
• Multi-view Graph Condensation via Tensor Decomposition
• Position-based Content Attention for Time Series Forecasting with\n Sequence-to-sequence RNNs
• An Empirical Comparison of Syllabuses for Curriculum Learning
• Cost-aware Multi-objective Bayesian optimisation
• A Multi-Layer K-means Approach for Multi-Sensor Data Pattern Recognition in Multi-Target Localization
• Learning to Segment 3D Point Clouds in 2D Image Space
• In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
• On Scalable and Efficient Computation of Large Scale Optimal Transport
• Efficient Knowledge Graph Unlearning with Zeroth-order Information
• Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism
• Enhancing Explainability of Neural Networks through Architecture Constraints
• DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Experts
• DGC-Net: Dense Geometric Correspondence Network
• Eliminating Rasterization: Direct Vector Floor Plan Generation with DiffPlanner
• MUFFIN: Mixture of User-Adaptive Frequency Filtering for Sequential Recommendation
• MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning
• Explainable Learning Rate Regimes for Stochastic Optimization
• Seven Basic Expression Recognition Using ResNet-18
• Automation for Interpretable Machine Learning Through a Comparison of Loss Functions to Regularisers
• Weakly Supervised Anomaly Detection in Events with a Higgs Boson and Exotic Physics
• Generative Model-Based Feature Attention Module for Video Action Analysis
• AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration
• Competitive Experience Replay
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing
• Safe Exploration in Continuous Action Spaces
• Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation
• Decentralized Contextual Bandits with Network Adaptivity
• Width Provably Matters in Optimization for Deep Linear Neural Networks
• Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
• BLIPs: Bayesian Learned Interatomic Potentials
• Improving genome-scale metabolic models of incomplete genomes with deep learning
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Replicating Active Appearance Model by Generator Network
• Practical Bayesian Optimization of Objectives with Conditioning\n Variables
• Differentiable Forward and Back-Projector for Rigid Motion Estimation in X-ray Imaging
• Diff-MSM: Differentiable MusculoSkeletal Model for Simultaneous Identification of Human Muscle and Bone Parameters
• Reinforcement and Imitation Learning for Diverse Visuomotor Skills
• BeamSeek: Deep Learning-based DOA Estimation for Low-Complexity mmWave Phased Arrays
• Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical\n Models
• k-Space Deep Learning for Parallel MRI: Application to Time-Resolved MR Angiography
• Fully Automated Segmentation of Fiber Bundles in Anatomic Tracing Data
• Optimization problems for machine learning: A survey
• Semantically Consistent Image Completion with Fine-grained Details
• IQ of Neural Networks
• An Empirical Model of Large-Batch Training
• G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• Adversarial Graph Disentanglement
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• A Survey of Black-Box Adversarial Attacks on Computer Vision Models
• Unsupervised and Supervised Structure Learning for Protein Contact Prediction
• Evolutionary-Neural Hybrid Agents for Architecture Search
• D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal
• Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring
• Lidar-Camera Co-Training for Semi-Supervised Road Detection
• TENT: Tensorized Encoder Transformer for Temperature Forecasting
• Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
• Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in non-equilibrium systems
• SDEC: Semantic Deep Embedded Clustering
• DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
• aims-PAX: Parallel Active eXploration for the automated construction of Machine Learning Force Fields
• MD-split+: Practical Local Conformal Inference in High Dimensions
• A Cost-Effective Framework for Predicting Parking Availability Using Geospatial Data and Machine Learning
• Enhancing high-content imaging for studying microtubule networks at large-scale
• Learning to estimate label uncertainty for automatic radiology report\n parsing
• Boosting Image Recognition with Non-differentiable Constraints
• Emotion Generation and Recognition: A StarGAN Approach
• Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
• BachProp: Learning to Compose Music in Multiple Styles
• Generalization vs. Memorization in Autoregressive Deep Learning: Or, Examining Temporal Decay of Gradient Coherence
• 3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models
• Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance
• The LIG system for the English-Czech Text Translation Task of IWSLT 2019
• Design by adaptive sampling
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional\n Neural Networks
• Neural Segmental Hypergraphs for Overlapping Mention Recognition
• OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
• Learning to Communicate Implicitly By Actions
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Tracking e-cigarette warning label compliance on Instagram with deep\n learning
• Best of both worlds: local and global explanations with human-understandable concepts
• Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
• CEM-Net: Cross-Emotion Memory Network for Emotional Talking Face Generation
• EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos
• Strategies for training point distributions in physics-informed neural networks
• Polarization Reconfigurable Transmit-Receive Beam Alignment with Interpretable Transformer
• Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
• Incorporating Legal Logic into Deep Learning: An Intelligent Approach to Probation Prediction
• Superpixel-informed Continuous Low-Rank Tensor Representation for Multi-Dimensional Data Recovery
• Age of Semantic Information-Aware Wireless Transmission for Remote Monitoring Systems
• Communication-Efficient Distributed Asynchronous ADMM
• Contrastive Multi-View Graph Hashing
• MBMamba: When Memory Buffer Meets Mamba for Structure-Aware Image Deblurring
• Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Root Cause Analysis of Hydrogen Bond Separation in Spatio-Temporal Molecular Dynamics using Causal Models
• DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
• Mesh Processing Non-Meshes via Neural Displacement Fields
• Spinal Stenosis Grading in Magnetic Resonance Imaging Using Deep Convolutional Neural Networks
• Language Models with Transformers
• Deep learning for accelerating Monte Carlo radiation transport simulation in intensity-modulated radiation therapy
• Towards Annotating and Creating Sub-Sentence Summary Highlights
• Wasserstein Distance Guided Cross-Domain Learning
• Accelerating Proximal Gradient-type Algorithms using Damped Anderson Acceleration with Restarts and Nesterov Initialization
• Multi-Modal Drift Forecasting of Leeway Objects via Navier-Stokes-Guided CNN and Sequence-to-Sequence Attention-Based Models
• DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Generalized invariants meet constitutive neural networks: A novel framework for hyperelastic materials
• Text-Free Prosody-Aware Generative Spoken Language Modeling
• Exploring Spatial-Temporal Dynamics in Event-based Facial Micro-Expression Analysis
• Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
• Transfer-Based Strategies for Multi-Target Quantum Optimization
• Consensus-based Sequence Training for Video Captioning
• A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
• Deep Relevance Ranking Using Enhanced Document-Query Interactions
• In-Context Examples Matter: Improving Emotion Recognition in Conversation with Instruction Tuning
• Solving Quadratic Programs via Deep Unrolled Douglas-Rachford Splitting
• Machine learning-based classification of variable stars using phase-folded light curves
• Longformer for MS MARCO Document Re-ranking Task
• Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks
• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting
• An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
• Large Wing Model
• Neural Style Transfer for Audio Spectograms
• Pretrained Conformers for Audio Fingerprinting and Retrieval
• Malware Classification Using Transfer Learning
• Deformable Part Networks
• Saliency-Associated Object Tracking
• TrajSV: A Trajectory-based Model for Sports Video Representations and Applications
• Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
• Subcortical Masks Generation in CT Images via Ensemble-Based Cross-Domain Label Transfer
• Non-Dissipative Graph Propagation for Non-Local Community Detection
• LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution
• Model Interpretability and Rationale Extraction by Input Mask Optimization
• Cost-Effective Active Labeling for Data-Efficient Cervical Cell Classification
• Using Mode Connectivity for Loss Landscape Analysis
• Deep Learning based Estimation of Weaving Target Maneuvers
• Unveiling the Potential: Harnessing Deep Metric Learning to Circumvent Video Streaming Encryption
• ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
• Probing the Representational Power of Sparse Autoencoders in Vision Models
• Graph Neural Diffusion via Generalized Opinion Dynamics
• Mitigating Filter Bubble from the Perspective of Community Detection: A Universal Framework
• Understanding in Artificial Intelligence
• Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
• Adma: A Flexible Loss Function for Neural Networks
• The Value of Information When Deciding What to Learn
• Visuomotor Grasping with World Models for Surgical Robots
• Representation Quantization for Collaborative Filtering Augmentation
• LayoutRectifier: An Optimization-based Post-processing for Graphic Design Layout Generation
• VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
• A Convergent Generalized Krylov Subspace Method for Compressed Sensing MRI Reconstruction with Gradient-Driven Denoisers
• Compressive Meta-Learning
• Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
• Conformal Prediction Intervals for Neural Networks Using Cross Validation
• Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
• Deeply Equal-Weighted Subset Portfolios
• Saliency Prediction with External Knowledge
• Quantum Visual Fields with Neural Amplitude Encoding
• From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals
• Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
• A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
• Counting to Explore and Generalize in Text-based Games
• Estimating Covariance for Global Minimum Variance Portfolio: A Decision-Focused Learning Approach
• Hypercomplex Prompt-aware Multimodal Recommendation
• Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
• Learning from Natural Language Feedback for Personalized Question Answering
• Generating Representative Headlines for News Stories
• EventNet: Asynchronous Recursive Event Processing
• Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
• Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution
• Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
• Pyramid Medical Transformer for Medical Image Segmentation
• A dataset and model for recognition of audiologically relevant environments for hearing aids: AHEAD-DS and YAMNet+
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems
• Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things
• A Benchmark for Lease Contract Review
• MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
• Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
• Learning to Rank for Plausible Plausibility
• Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
• Dropout as a Low-Rank Regularizer for Matrix Factorization
• Indoor GeoNet: Weakly Supervised Hybrid Learning for Depth and Pose Estimation
• Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation
• Improving Robustness and Generality of NLP Models Using Disentangled Representations
• Nematus: a Toolkit for Neural Machine Translation
• DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
• Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
• PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl Spaces
• Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
• Controllable Multi-Character Psychology-Oriented Story Generation
• Speaking Speed Control of End-to-End Speech Synthesis using Sentence-Level Conditioning
• Reconstruct high-resolution multi-focal plane images from a single 2D wide field image
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning
• MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
• TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional Specialization
• Multimodal Sheaf-based Network for Glioblastoma Molecular Subtype Prediction
• Deep Generative Modeling for Scene Synthesis via Hybrid Representations
• Correlative Channel-Aware Fusion for Multi-View Time Series Classification
• Deep Smartphone Sensors-WiFi Fusion for Indoor Positioning and Tracking
• Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
• Continuous Face Aging Generative Adversarial Networks
• MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
• Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
• HIN: Hierarchical Inference Network for Document-Level Relation Extraction
• Source Printer Identification from Document Images Acquired using Smartphone
• AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• Detection of Odor Presence via Deep Neural Networks
• Your Coding Intent is Secretly in the Context and You Should Deliberately Infer It Before Completion
• DeepWKB: Learning WKB Expansions of Invariant Distributions for Stochastic Systems
• Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
• Disentangling Video with Independent Prediction
• Domain-Generalization to Improve Learning in Meta-Learning Algorithms
• Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction
• Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
• HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics
• ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs
• Discovery of energy landscapes towards optimized quantum transport: Environmental effects and long-range tunneling
• Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
• Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
• Arbitrary Marginal Neural Ratio Estimation for Simulation-based\n Inference
• Efficient estimates of optimal transport via low-dimensional embeddings
• A Closer Look at Reference Learning for Fourier Phase Retrieval
• Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering
• EGGCodec: A Robust Neural Encodec Framework for EGG Reconstruction and F0 Extraction
• Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
• Extended parameter shift rules with minimal derivative variance for parameterized quantum circuits
• Novel Video Prediction for Large-scale Scene using Optical Flow
• Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention
• ReQuestNet: A Foundational Learning model for Channel Estimation
• Solving Approximation Tasks with Greedy Deep Kernel Methods
• Interpretable Reward Model via Sparse Autoencoder
• Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
• Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint
• Aryabhata: An exam-focused language model for JEE Math
• A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
• DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
• Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise
• Learning of Discrete Graphical Models with Neural Networks
• Video-based Person Re-identification without Bells and Whistles
• Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech
• EVA: Generating Longitudinal Electronic Health Records Using Conditional\n Variational Autoencoders
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
• Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn from a Digital Twin
• Leveraging Unlabeled Data from Unknown Sources via Dual-Path Guidance for Deepfake Face Detection
• DiffVolume: Diffusion Models for Volume Generation in Limit Order Books
• Developing a Transferable Federated Network Intrusion Detection System
• SelfHVD: Self-Supervised Handheld Video Deblurring
• DLR : Toward a deep learned rhythmic representation for music content analysis
• Meta-Learning for Stochastic Gradient MCMC
• A Deep Probabilistic Model for Customer Lifetime Value Prediction
• Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages
• Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
• Learning Term Weights for Ad-hoc Retrieval
• Point Cloud Registration using Representative Overlapping Points
• Cut2Next: Generating Next Shot via In-Context Tuning
• Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
• Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China
• Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies
• Variational Inference for Shrinkage Priors: The R package vir
• Memory and attention in deep learning
• CD-TVD: Contrastive Diffusion for 3D Super-Resolution with Scarce High-Resolution Time-Varying Data
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
• From Source to Target: Leveraging Transfer Learning for Predictive Process Monitoring in Organizations
• AdaS: Adaptive Scheduling of Stochastic Gradients
• A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images
• Sparse tree-based initialization for neural networks
• Advancing Knowledge Tracing by Exploring Follow-up Performance Trends
• Reinforcement learning for batch bioprocess optimization
• Boosting Image Outpainting with Semantic Layout Prediction
• Industrial Scale Privacy Preserving Deep Neural Network
• Defending Against Image Corruptions Through Adversarial Augmentations
• Learning to Grasp from a Single Demonstration
• Distributional Negative Sampling for Knowledge Base Completion
• An Attention-based Graph Neural Network for Heterogeneous Structural Learning
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning
• Gated Fusion Network for Single Image Dehazing
• Modeling Dynamic Gas-Liquid Interfaces in Underwater Explosions Using Interval-Constrained Physics-Informed Neural Networks
• Towards Comprehensible Recommendation with Large Language Model Fine-tuning
• GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm
• Domain-Aware Machine Learning for Accelerating MILP-Based Motion Planning with Temporal Logic and Chance Constraints
• Dual-stream Maximum Self-attention Multi-instance Learning
• Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
• AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
• Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics
• Enhanced Generative Structure Prior for Chinese Text Image Super-resolution
• Active Learning for Breast Cancer Identification
• Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features
• Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
• Topological Feature Compression for Molecular Graph Neural Networks
• Structured Superposition of Autoencoders for UEP Codes at Intermediate Blocklengths
• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
• InfantNet: A Deep Neural Network for Analyzing Infant Vocalizations
• Image Captioning at Will: A Versatile Scheme for Effectively Injecting Sentiments into Image Descriptions
• KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features
• When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
• SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations
• Prompt Tuning for Few-Shot Continual Learning Named Entity Recognition
• Similarity Matters: A Novel Depth-guided Network for Image Restoration and A New Dataset
• Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment
• Noise-Robust Sound Event Detection and Counting via Language-Queried Sound Separation
• Mastering Rate based Curriculum Learning
• Improved Chord Recognition by Combining Duration and Harmonic Language Models
• PU-Net: Point Cloud Upsampling Network
• Progressive Point Cloud Deconvolution Generation Network
• Embedding Words as Distributions with a Bayesian Skip-gram Model
• Gromov-Wasserstein Factorization Models for Graph Clustering
• RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning
• Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
• Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning
• From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
• Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations
• Content Adaptive Optimization for Neural Image Compression
• Multi-Stage Reinforcement Learning For Object Detection
• SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work
• FlowSE: Flow Matching-based Speech Enhancement
• Mapping fractional vegetation cover in UAS RGB and multispectral imagery in semi-arid Australian ecosystems using CNN-based semantic segmentation
• Speech Enhancement based on cascaded two flow
• CoKE: Contextualized Knowledge Graph Embedding
• Question Answering based Clinical Text Structuring Using Pre-trained Language Model
• Local Diffusion Models and Phases of Data Distributions
• Making Neural Machine Reading Comprehension Faster
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Improved spatial memory in a modular network mimicking the prefrontal-thalamo-hippocampal triangular circuit
• Practical Block-wise Neural Network Architecture Generation
• MTNet: A Multi-Task Neural Network for On-Field Calibration of Low-Cost Air Monitoring Sensors
• Ophthalmic diagnosis using deep learning with fundus images – A critical review
• ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network
• BreastScreening-AI: Evaluating medical intelligent agents for human-AI interactions
• Real-Time Adversarial Attacks
• QUOTIENT: Two-Party Secure Neural Network Training and Prediction
• Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI
• The Physiological Deep Learner: First application of multitask deep learning to predict hypotension in critically ill patients
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• Neural Summarization by Extracting Sentences and Words
• Adaptive Weight Decay for Deep Neural Networks
• Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks
• Deep Object Co-segmentation via Spatial-Semantic Network Modulation
• Comparative study of ensemble-based uncertainty quantification methods for neural network interatomic potentials
• Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems
• Dynamics of Protonated Oxalate from Machine-Learned Simulations and Experiment: Infrared Signatures, Proton Transfer Dynamics and Tunneling Splittings
• Acoustic Non-Stationarity Objective Assessment with Hard Label Criteria for Supervised Learning Models
• MCMI: Multi-Cycle Image Translation with Mutual Information Constraints
• Nonlinear Matrix Approximation with Radial Basis Function Components
• Edge-featured Graph Neural Architecture Search
• Decorrelated feature importance from local sample weighting
• MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks
• Dynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes
• Searching Efficient Model-guided Deep Network for Image Denoising
• Vertex reconstruction in the TAO experiment
• Deepfake Detection that Generalizes Across Benchmarks
• An Embedded Deep Learning based Word Prediction
• DSConv: Dynamic Splitting Convolution for Pansharpening
• Ensemble-Based Graph Representation of fMRI Data for Cognitive Brain State Classification
• GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
• Federated Quantum Kernel-Based Long Short-term Memory for Human Activity Recognition
• Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
• Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
• Hybrid Physics-Machine Learning Models for Quantitative Electron Diffraction Refinements
• Recurrent Deep Differentiable Logic Gate Networks
• EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
• Accelerating Quantum Monte Carlo Calculations with Set-Equivariant Architectures and Transfer Learning
• Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts
• A Study on Regularization-Based Continual Learning Methods for Indic ASR
• Distributed Optimization and Learning for Automated Stepsize Selection with Finite Time Coordination
• NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference
• Optimal Linear Baseline Models for Scientific Machine Learning
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• Deep Multimodal Transfer-Learned Regression in Data-Poor Domains
• Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V\n images for Cloud Detection
• Physically Controllable Relighting of Photographs
• On the Design of Expressive and Trainable Pulse-based Quantum Machine Learning Models
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
• TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog
• Input Invex Neural Network
• Competing Risks: Impact on Risk Estimation and Algorithmic Fairness
• MolSnap: Snap-Fast Molecular Generation with Latent Variational Mean Flow
• The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
• Optimal Corpus Aware Training for Neural Machine Translation
• Generalized Inner Loop Meta-Learning
• Wavelet-Guided Dual-Frequency Encoding for Remote Sensing Change Detection
• SGDFuse: SAM-Guided Diffusion for High-Fidelity Infrared and Visible Image Fusion
• Periodic evaluation of defined-contribution pension fund: A dynamic risk measure approach
• Predicting Unplanned Readmissions with Highly Unstructured Data
• Identification of the nonlinear steering dynamics of an autonomous vehicle
• SpectroStream: A Versatile Neural Codec for General Audio
• Hybrid quantum tensor networks for aeroelastic applications
• Rotation Equivariant Arbitrary-scale Image Super-Resolution
• FCBV-Net: Category-Level Robotic Garment Smoothing via Feature-Conditioned Bimanual Value Prediction
• Community-Aware Social Community Recommendation
• Not all bytes are equal: Neural byte sieve for fuzzing
• Robust and interpretable blind image denoising via bias-free convolutional neural networks
• Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks
• ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos
• Z-Forcing: Training Stochastic Recurrent Networks
• A Markov Decision Process Framework for Early Maneuver Decisions in Satellite Collision Avoidance
• Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows
• Data-driven dust inference at mid-to-high Galactic latitudes using probabilistic machine learning
• CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction
• Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations
• Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices
• Deep Distillation Gradient Preconditioning for Inverse Problems
• Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
• TAG : Type Auxiliary Guiding for Code Comment Generation
• CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series
• Human-centric Relation Segmentation: Dataset and Solution
• LA-CaRe-CNN: Cascading Refinement CNN for Left Atrial Scar Segmentation
• Augmentation-based Domain Generalization and Joint Training from Multiple Source Domains for Whole Heart Segmentation
• Emotion Detection Using Conditional Generative Adversarial Networks (cGAN): A Deep Learning Approach
• GradSTL: Comprehensive Signal Temporal Logic for Neurosymbolic Reasoning and Learning
• Transfer learning of neural surrogates on multifidelity groundwater simulations
• Automated ultrasound doppler angle estimation using deep learning
• Circuit-Aware SAT Solving: Guiding CDCL via Conditional Probabilities
• A machine learning approach for image classification in synthetic aperture RADAR
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation
• Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
• Audio-Assisted Face Video Restoration with Temporal and Identity Complementary Learning
• Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation
• Unsupervised Pairwise Learning Optimization Framework for Cross-Corpus EEG-Based Emotion Recognition Based on Prototype Representation
• Towards Globally Predictable k-Space Interpolation: A White-box Transformer Approach
• Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation
• UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Auto-Encoding Sequential Monte Carlo
• Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm
• Query-based Attention CNN for Text Similarity Map
• Next Generation Equation-Free Multiscale Modelling of Crowd Dynamics via Machine Learning
• Deep learning framework for crater detection and identification on the Moon and Mars
• Super-Resolution of Sentinel-2 Images Using a Geometry-Guided Back-Projection Network with Self-Attention
• Two-dimensional Sparse Parallelism for Large Scale Deep Learning Recommendation Model Training
• Multimodal Generative Models for Scalable Weakly-Supervised Learning
• Scalable neural network-based blackbox optimization
• FairLangProc: A Python package for fairness in NLP
• Exploring Recombination for Efficient Decoding of Neural Machine Translation
• Machine Learning Algorithms for Transplanting Accelerometer Observations in Future Satellite Gravimetry Missions
• Distribution-aware Knowledge Unification and Association for Non-exemplar Lifelong Person Re-identification
• CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation
• Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction
• Differential Description Length for Hyperparameter Selection in Machine Learning
• MURAUER: Mapping Unlabeled Real Data for Label AUstERity
• GaitAdapt: Continual Learning for Evolving Gait Recognition
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• Deep Learning with Gaussian Differential Privacy
• Video Demoireing using Focused-Defocused Dual-Camera System
• Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations
• Deep Shape from Polarization
• WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval
• EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
• Bridging ocean wave physics and deep learning: Physics-informed neural operators for nonlinear wavefield reconstruction in real-time
• BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices
• Online Continual Graph Learning
• Multiple Instance Learning for ECG Risk Stratification
• Permutohedral-GCN: Graph Convolutional Networks with Global Attention
• The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustness
• AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding
• Unifying Locality of KANs and Feature Drift Compensation Projection for Data-free Replay based Continual Face Forgery Detection
• Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling
• Diversified Mutual Learning for Deep Metric Learning
• RoIFusion: 3D Object Detection from LiDAR and Vision
• RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging
• A Markov Decision Process Approach to Active Meta Learning
• RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions
• Aerobatic maneuvers in insect-scale flapping-wing aerial robots via deep-learned robust tube model predictive control
• Urban In-Context Learning: Bridging Pretraining and Inference through Masked Diffusion for Urban Profiling
• From Text to Trajectories: GPT-2 as an ODE Solver via In-Context
• Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
• Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data
• Learning Dynamic Context Augmentation for Global Entity Linking
• Automatic deep learning for trend prediction in time series data
• Topology Optimization through Differentiable Finite Element Solver
• Part-Guided Attention Learning for Vehicle Instance Retrieval
• Model-agnostic Meta-learning for Adaptive Gait Phase and Terrain Geometry Estimation with Wearable Soft Sensors
• SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec
• Signatures of quantum chaos and complexity in the Ising model on random graphs
• Adaptive Knowledge Distillation for Device-Directed Speech Detection
• Breaking the Top-K Barrier: Advancing Top-K Ranking Metrics Optimization in Recommender Systems
• On Hallucination and Predictive Uncertainty in Conditional Language Generation
• A Generative Model for Sampling High-Performance and Diverse Weights for\n Neural Networks
• Residual Switching Network for Portfolio Optimization
• Computationally efficient Gauss-Newton reinforcement learning for model predictive control
• GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
• Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing
• A Memory-Network Based Solution for Multivariate Time-Series Forecasting
• Content-Aware Mamba for Learned Image Compression
• DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal
• Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
• LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
• SGD momentum optimizer with step estimation by online parabola model
• WhiSQA: Non-Intrusive Speech Quality Prediction Using Whisper Encoder Features
• Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting
• Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
• StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion
• A Neural Quality Metric for BRDF Models
• VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling
• Cluster, Classify, Regress: A General Method For Learning Discountinous Functions
• Forecasting West Nile virus with deep graph encoders
• Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
• Fast Gaussian process inference by exact Matérn kernel decomposition
• ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
• A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms
• EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
• Robust Chinese Word Segmentation with Contextualized Word Representations
• A Trainable Optimizer
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation
• Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
• Optical Flow Estimation using a Spatial Pyramid Network
• First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
• Statistical Multiport-Network Modeling and Efficient Discrete Optimization of RIS
• From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation
• Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning
• Asynchronous Federated Learning with non-convex client objective functions and heterogeneous dataset
• DexReMoE:In-hand Reorientation of General Object via Mixtures of Experts
• Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion
• A Missing Information Loss function for implicit feedback datasets
• Experiential Robot Learning with Accelerated Neuroevolution
• Counterfactual Reciprocal Recommender Systems for User-to-User Matching
• PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
• HT-Transformer: Event Sequences Classification by Accumulating Prefix Information with History Tokens
• Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features
• Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation
• Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
• Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks
• Multi-Scale Time-Frequency Attention for Acoustic Event Detection
• From the Token to the Review: A Hierarchical Multimodal approach to\n Opinion Mining
• ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
• SpatioTemporal Difference Network for Video Depth Super-Resolution
• NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection
• Transfer Reward Learning for Policy Gradient-Based Text Generation
• Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
• Perspective from a Broader Context: Can Room Style Knowledge Help Visual Floorplan Localization?
• Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• A Parameter-free Decentralized Algorithm for Composite Convex Optimization
• CM³: Calibrating Multimodal Recommendation
• A graph neural network based on feature network for identifying influential nodes
• TensorHyper-VQC: A Tensor-Train-Guided Hypernetwork for Robust and Scalable Variational Quantum Computing
• Explaining GNN Explanations with Edge Gradients
• Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
• Learning to optimize with guarantees: a complete characterization of linearly convergent algorithms
• Evaluating Angle and Amplitude Encoding Strategies for Variational Quantum Machine Learning: their impact on model's accuracy
• Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
• DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS
• Information-Theoretic Decentralized Secure Aggregation with Collusion Resilience
• Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
• Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
• Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution
• PIF-Net: Ill-Posed Prior Guided Multispectral and Hyperspectral Image Fusion via Invertible Mamba and Fusion-Aware LoRA
• Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning
• Efficient Distributed Hessian Free Algorithm for Large-scale Empirical\n Risk Minimization via Accumulating Sample Strategy
• Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
• RandomOut: Using a convolutional gradient norm to rescue convolutional filters
• A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
• Advancing Welding Defect Detection in Maritime Operations via Adapt-WeldNet and Defect Detection Interpretability Analysis
• Variational Autoencoder-Based Black-Box Adversarial Attack on Collaborative DNN Inference
• Criticality analysis of nuclear binding energy neural networks
• SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
• Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition
• Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment
• Production-Level Facial Performance Capture Using Deep Convolutional\n Neural Networks
• GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search
• Deep 2FBSDEs For Systems With Control Multiplicative Noise
• Melody-Lyrics Matching with Contrastive Alignment Loss
• Improve Retinal Artery/Vein Classification via Channel Couplin
• Thread Reconstruction in Conversational Data using Neural Coherence Models
• Double descent: When do neural quantum states generalize?
• Anomaly detection with spiking neural networks for LHC physics
• Segmenting proto-halos with vision transformers
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting
• Topology Optimization in Medical Image Segmentation with Fast Euler Characteristic
• Search for t tt tW Production at √(s) = 13 TeV Using a Modified Graph Neural Network at the LHC
• Modeling turbulent and self-gravitating fluids with Fourier neural operators
• OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Prediction
• Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation
• Interpretable Deep Convolutional Neural Networks via Meta-learning
• Deep Meta-Learning: Learning to Learn in the Concept Space
• Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
• Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
• KLAN: Kuaishou Landing-page Adaptive Navigator
• Adjustable Spatio-Spectral Hyperspectral Image Compression Network
• Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf\n DLRM Model : 1000\× Compression and 3.1\× Faster Inference
• Importance mixing: Improving sample reuse in evolutionary policy search methods
• Physically constrained short-term vehicle trajectory forecasting with naive semantic maps
• Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning
• Scalable Cross Validation Losses for Gaussian Process Models
• An Approximation Algorithm for Optimal Subarchitecture Extraction
• cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks
• Material Segmentation of Multi-View Satellite Imagery
• Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network
• FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models
• ST-SAM: SAM-Driven Self-Training Framework for Semi-Supervised Camouflaged Object Detection
• Enriching Knowledge Bases with Counting Quantifiers
• Variational Bi-LSTMs
• Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
• An Information Bottleneck Asset Pricing Model
• RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems
• Personalized Education with Ranking Alignment Recommendation
• From Image Captioning to Visual Storytelling
• High-resolution eikonal imaging and uncertainty quantification of the Kilauea caldera
• Learning representations for multivariate time series with missing data\n using Temporal Kernelized Autoencoders
• CARL: Content-Aware Representation Learning for Heterogeneous Networks
• Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
• Consistent Representation Learning for High Dimensional Data Analysis
• MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
• Detection of Glottal Closure Instants from Raw Speech using Convolutional Neural Networks
• Dynamics-Aware Unsupervised Discovery of Skills
• Confidence-aware agglomeration classification and segmentation of 2D microscopic food crystal images
• Popov Mirror-Prox Method for Variational Inequalities
• Basecalling for DNA Storage
• Feature Importance across Domains for Improving Non-Intrusive Speech Intelligibility Prediction in Hearing Aids
• LCA-Net: Light Convolutional Autoencoder for Image Dehazing
• A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
• A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
• Stochastic Adaptive Line Search for Differentially Private Optimization
• AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
• Extended Factorization Machine Annealing for Rapid Discovery of Transparent Conducting Materials
• Physics-Informed PointNets for Modeling Electromagnetic Scattering from All-Dielectric Metasurfaces with Inclined Nanopillars
• Few-Shot Open-Set Recognition using Meta-Learning
• Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
• IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
• PAF-Net: Phase-Aligned Frequency Decoupling Network for Multi-Process Manufacturing Quality Prediction
• Multi-Task Neural Processes
• Exploiting Aliasing for Manga Restoration
• A Graph Convolutional Neural Network based Framework for Estimating\n Future Citations Count of Research Articles
• Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
• Deep Learning of Koopman Representation for Control
• Secure Domain Adaptation with Multiple Sources

Related

• A Novel Convergence Analysis for Algorithms of the Adam Family
• SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer
• Asymptotic stability properties and a priori bounds for Adam and other gradient descent optimization methods
• On Higher-order Moments in Adam
• High Probability Convergence of Adam Under Unbounded Gradients and Affine Variance Noise