LLaMA: Open and Efficient Foundation Language Models

2023/02/27 by Hugo Touvron, Touvron, Hugo, Thibaut Lavril +25 · 1660 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Speech Recognition and Synthesis

paper · pdf · doi:10.48550/arxiv.2302.13971

Abstract

We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.

Cited by

• CoFi-Dec: Hallucination-Resistant Decoding via Coarse-to-Fine Generative Feedback in Large Vision-Language Models
• MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
• Understanding the Mechanisms of Fast Hyperparameter Transfer
• Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis
• Reservoir Computing inspired Matrix Multiplication-free Language Model
• Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
• Argus: Token Aware Distributed LLM Inference Optimization
• CNSight: Evaluation of Clinical Note Segmentation Tools
• Visual Autoregressive Modelling for Monocular Depth Estimation
• M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation
• Learning When Not to Attend Globally
• EmoCtrl: Controllable Emotional Image Content Generation
• VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement
• LLMBoost: Make Large Language Models Stronger with Boosting
• Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection
• MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs
• Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
• Attention Residuals
• MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation
• RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
• ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
• Training Language Models to Cooperate with Inference-Time Controllers
• Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation
• SymStep: Symbolic Step Verification for Logical Reasoning
• Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
• Grevo: A Unified Generative Recommendation Framework with Evolutionary Item Indexing
• SeedFold: Scaling Biomolecular Structure Prediction
• LithoFormer: A Robust Framework for Stratigraphic Inference via Transformers
• Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests
• Real-time Reconstruction of Human Visual Perception from fMRI
• PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models
• Unifying Learning Dynamics and Generalization in Transformers Scaling Law
• Context as a Tool: Context Management for Long-Horizon SWE-Agents
• CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data
• ARdena: Scenario-driven control of real-time LLM agents
• TokenMem: Faithful Knowledge Injection for Frozen LLMs
• TriSP: Tri-Signal Structured Pruning for Large Language Models
• MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models
• StegaFFD: Privacy-preserving Face Forgery Detection via Fine-grained Steganographic Domain Lifting
• Compressing LLMs with MoP: Mixture of Pruners
• PixelGen: Improving Pixel Diffusion with Perceptual Supervision
• GQ-VAE: A gated quantized VAE for learning variable length tokens
• DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
• Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models
• ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
• TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant
• A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning
• Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM
• HELP: Hierarchical Embodied Language Planner for Household Tasks
• MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
• GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs
• AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
• Deadline-Aware Online Scheduling for LLM Fine-Tuning with Spot Market Predictions
• Diving into 3D Parallelism with Heterogeneous Spot Instance GPUs: Design and Implications
• RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
• Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs
• Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference
• VL4Gaze: Unleashing Vision-Language Models for Gaze Following
• Benchmarking LLMs for Predictive Applications in the Intensive Care Units
• Designing Spatial Architectures for Sparse Attention: STAR Accelerator via Cross-Stage Tiling
• Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches
• QuarkAudio Technical Report
• Predictive-LoRA: A Proactive and Fragmentation-Aware Serverless Inference System for LLMs
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• Vehicle-centric Perception via Multimodal Structured Pre-training
• ReasonCD: A Multimodal Reasoning Large Model for Implicit Change-of-Interest Semantic Mining
• Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs
• HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
• SAP: Syntactic Attention Pruning for Transformer-based Language Models
• HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction
• R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression
• CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs
• Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models
• Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction
• Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
• A Theoretical Lens for RL-Tuned Language Models via Energy-Based Models
• A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback
• Phoneme-based speech recognition driven by large language models and sampling marginalization
• HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
• External Hippocampus: Topological Cognitive Maps for Guiding Large Language Model Reasoning
• AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3
• Holistic Evaluation of State-of-the-Art LLMs for Code Generation
• Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks
• Robotic VLA Benefits from Joint Learning with Motion Image Diffusion
• Adversarial Robustness of Vision in Open Foundation Models
• AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning
• Easy Adaptation: An Efficient Task-Specific Knowledge Injection Method for Large Models in Resource-Constrained Environments
• A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
• Vision-Language Model Guided Image Restoration
• Subjective Question Generation and Answer Evaluation using NLP
• LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
• Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
• A systematic assessment of Large Language Models for constructing two-level fractional factorial designs
• LLM-HPC++: Evaluating LLM-Generated Modern C++ and MPI+OpenMP Codes for Scalable Mandelbrot Set Computation
• 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
• Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
• Radiology Report Generation with Layer-Wise Anatomical Attention
• DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
• Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
• A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
• Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
• CKA-Guided Modular Quantization: Beyond Bit-Width to Algorithmic Diversity
• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
• Sigma-MoE-Tiny Technical Report
• Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
• The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models
• An Information-Theoretic Framework for Robust Large Language Model Editing
• Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
• Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference
• Sceniris: A Fast Procedural Scene Generation Framework
• Cross-Language Bias Examination in Large Language Models
• Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models
• Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning
• In-Context Semi-Supervised Learning
• Large Video Planner Enables Generalizable Robot Control
• FAME: Fictional Actors for Multilingual Erasure
• Null-LoRA: Low-Rank Adaptation on Null Space
• Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
• An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models
• The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
• Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
• Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models
• Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis
• VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
• TEMP: A Memory Efficient Physical-aware Tensor Partition-Mapping Framework on Wafer-scale Chips
• Georeferencing complex relative locality descriptions with large language models
• Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously
• SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models
• CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models
• OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
• Toward Agentic Environments: GenAI and the Convergence of AI, Sustainability, and Human-Centric Spaces
• Do Reviews Matter for Recommendations in the Era of Large Language Models?
• Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systems
• FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
• Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection
• Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance
• STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning
• SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference
• Fine-Grained Energy Prediction For Parallellized LLM Inference With PIE-P
• Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping
• SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems
• PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation
• Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding
• CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence
• GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
• Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
• Low-Rank Compression of Language Models via Differentiable Rank Selection
• Supervised Contrastive Frame Aggregation for Video Representation Learning
• WATOS: Efficient LLM Training Strategies and Architecture Co-exploration for Wafer-scale Chip
• Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective
• VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
• Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
• Fully Inductive Node Representation Learning via Graph View Transformation
• CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop
• Exploring MLLM-Diffusion Information Transfer with MetaCanvas
• Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis
• Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery: Sublinear Memory Growth for Efficient LLM Inference
• BAID: A Benchmark for Bias Assessment of AI Detectors
• CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare
• Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
• CAPTURE: A Benchmark and Evaluation for LVLMs in CAPTCHA Resolving
• TAO-Net: Two-stage Adaptive OOD Classification Network for Fine-grained Encrypted Traffic Classification
• Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning
• Stronger Normalization-Free Transformers
• BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
• Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats
• ESS: An Offload-Centric Latent-Cache Management Architecture for DeepSeek-V3.2-Exp
• The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation
• CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
• EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
• Design Space Exploration of DMA based Finer-Grain Compute Communication Overlap
• Scaling Behavior of Discrete Diffusion Language Models
• DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations
• DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components
• Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning
• Chasing Shadows: Pitfalls in LLM Security Research
• View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs
• Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval
• SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing
• InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
• WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp
• Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation
• Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning
• NeurIDA: Dynamic Modeling for Effective In-Database Analytics
• Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
• Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox
• Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model
• Chat with UAV -- Human-UAV Interaction Based on Large Language Models
• PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection
• CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning
• Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
• HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs
• Flash Multi-Head Feed-Forward Network
• Persian-Phi: Efficient Cross-Lingual Adaptation of Compact LLMs via Curriculum Learning
• M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach
• When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing
• VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
• Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph
• Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
• Large Language Model-Based Generation of Discharge Summaries
• Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving
• VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
• Small Language Models Can Use Nuanced Reasoning For Health Science Research Classification: A Microbial-Oncogenesis Case Study
• Teaching Language Models Mechanistic Explainability Through Arrow-Pushing
• Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
• Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup
• Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety
• Empathy by Design: Aligning Large Language Models for Healthcare Dialogue
• BeLLA: End-to-End Birds Eye View Large Language Assistant for Autonomous Driving
• Compass: Co-Exploration of Mapping and Hardware for Heterogeneous Multi-Chiplet Accelerators Targeting LLM Inference Service Workloads
• LLM Harms: A Taxonomy and Discussion
• HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
• Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias
• Fast SceneScript: Accurate and Efficient Structured Language Model via Multi-Token Prediction
• Structured Reasoning with Tree-of-Thoughts for Bengali Math Word Problems
• Automated Identification of Incidentalomas Requiring Follow-Up: A Multi-Anatomy Evaluation of LLM-Based and Supervised Approaches
• Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning
• ShaRP: SHAllow-LayeR Pruning for Video Large Language Models Acceleration
• Text Rationalization for Robust Causal Effect Estimation
• David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
• LLMs Know More Than Words: A Genre Study with Syntax, Metaphor & Phonetics
• Bridging Traditional Machine Learning and Large Language Models: A Two-Part Course Design for Modern AI Education
• STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
• Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding
• SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
• CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution
• AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
• DeRA: Decoupled Representation Alignment for Video Tokenization
• Solving LLM Repetition Problem in Production: A Comprehensive Study of Multiple Solutions
• Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5
• AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
• Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks
• FFTrainer: Fast Failover in Large-Language Model Training with Almost-Free State Management
• Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
• KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing
• EEA: Exploration-Exploitation Agent for Long Video Understanding
• NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation
• YOLOA: Real-Time Affordance Detection via LLM Adapter
• Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
• CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models
• Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
• TokenPowerBench: Benchmarking the Power Consumption of LLM Inference
• Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in \± 1, ± i\
• PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding
• RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence
• PopSim: Social Network Simulation for Social Media Popularity Prediction
• Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
• VACoT: Rethinking Visual Data Augmentation with VLMs
• promptolution: A Unified, Modular Framework for Prompt Optimization
• Decentralized Multi-Agent System with Trust-Aware Communication
• VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
• DETAIL Matters: Measuring the Impact of Prompt Specificity on Reasoning in Large Language Models
• Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
• LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
• Low-Rank Prehab: Preparing Neural Networks for SVD Compression
• Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding
• DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
• LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
• SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation
• FishDetector-R1: Unified MLLM-Based Framework with Reinforcement Fine-Tuning for Weakly Supervised Fish Detection, Segmentation, and Counting
• DefenSee: Dissecting Threat from Sight and Text -- A Multi-View Defensive Pipeline for Multi-modal Jailbreaks
• Financial Instruction Following Evaluation (FIFE)
• M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis
• OmniFD: A Unified Model for Versatile Face Forgery Detection
• ChartAnchor: Chart Grounding with Structural-Semantic Fidelity
• FOM-Nav: Frontier-Object Maps for Object Goal Navigation
• HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
• Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization
• IRPO: Boosting Image Restoration via Post-training GRPO
• Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation
• Preventing Model Collapse via Contraction-Conditioned Neural Filters
• ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for Recommendation
• Financial Text Classification Based On rLoRA Finetuning On Qwen3-8B model
• SelfAI: Building a Self-Training AI System with LLM Agents
• Breaking It Down: Domain-Aware Semantic Segmentation for Retrieval Augmented Generation
• ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning
• Teleportation-Based Defenses for Privacy in Approximate Machine Unlearning
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models
• TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies
• SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models
• LUMOS: Large User MOdels for User Behavior Prediction
• Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication
• A Customer Journey in the Land of Oz: Leveraging the Wizard of Oz Technique to Model Emotions in Customer Service Interactions
• Chart2Code-MoLA: Efficient Multi-Modal Code Generation via Adaptive Expert Routing
• Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
• AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
• Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
• AI/ML Model Cards in Edge AI Cyberinfrastructure: towards Agentic AI
• SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
• Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data
• How to Correctly Report LLM-as-a-Judge Evaluations
• GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision
• CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
• Graph-O1 : Monte Carlo Tree Search with Reinforcement Learning for Text-Attributed Graph Reasoning
• Towards a Foundation Model for Partial Differential Equations Across Physics Domains
• EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens
• From Words to Wisdom: Discourse Annotation and Baseline Models for Student Dialogue Understanding
• HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation
• Fluid Intelligence: A Forward Look on AI Foundation Models in Computational Fluid Dynamics
• AudioScene: Integrating Object-Event Audio into 3D Scenes
• CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
• More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
• Operator Learning at Machine Precision
• Boosting Reasoning in Large Multimodal Models via Activation Replay
• CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
• MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
• A Systematic Analysis of Large Language Models with RAG-enabled Dynamic Prompting for Medical Error Detection and Correction
• Mosaic Pruning: A Hierarchical Framework for Generalizable Pruning of Mixture-of-Experts Models
• Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs
• In-Context Compositional Learning via Sparse Coding Transformer
• Terminal Velocity Matching
• Gender Bias in Emotion Recognition by Large Language Models
• LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti
• Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
• DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
• LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models
• FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
• Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
• Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
• Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM
• Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
• LLMAID: Identifying AI Capabilities in Android Apps with LLMs
• IRSDA: An Agent-Orchestrated Framework for Enterprise Intrusion Response
• Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search
• TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
• Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI
• A Systematic Study of Compression Ordering for Large Language Models
• ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering
• UFO: Unfair-to-Fair Evolving Mitigates Unfairness in LLM-based Recommender Systems via Self-Play Fine-tuning
• Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis
• DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition
• ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning
• MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
• ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
• RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
• FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection
• PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer
• Equivalence of Context and Parameter Updates in Modern Transformer Blocks
• Plan-X: Instruct Video Generation via Semantic Planning
• Towards Efficient LLM-aware Heterogeneous Graph Learning
• EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants
• PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese
• MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
• The Rapid Growth of AI Foundation Model Usage in Science
• Selective Rotary Position Embedding
• Large Language Models for Sentiment Analysis to Detect Social Challenges: A Use Case with South African Languages
• Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
• R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization
• VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation
• ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
• Geometric-disentangelment Unlearning
• Spanning Tree Autoregressive Visual Generation
• MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
• SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion
• Predicting one-year clinical instability and mortality in heart failure patients using sequence modeling
• AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser
• ELPO: Ensemble Learning Based Prompt Optimization for Large Language Models
• SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning
• Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning
• On 10x Better Scalability: KV Stores Scale Up KV Cache
• ILoRA: Federated Learning with Low-Rank Adaptation for Heterogeneous Client Aggregation
• Boosting Medical Visual Understanding From Multi-Granular Language Learning
• An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs
• LLaVA³: Representing 3D Scenes like a Cubist Painter to Boost 3D Scene Understanding of VLMs
• Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization
• PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations
• Neo: Real-Time On-Device 3D Gaussian Splatting with Reuse-and-Update Sorting Acceleration
• Standardising the NLP Workflow: A Framework for Reproducible Linguistic Analysis
• Automatic Pruning Discovery for Large Language Models
• Parameter Importance-Driven Continual Learning for Foundation Models
• PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
• GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation
• UniSER: A Foundation Model for Unified Soft Effects Removal
• What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning
• Strategic Innovation Management in the Age of Large Language Models Market Intelligence, Adaptive R&D, and Ethical Governance
• Bias in, Bias out: Annotation Bias in Multilingual Large Language Models
• Gradient-descent methods for quantum detector tomography
• Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generation, and Agentic Planning
• MiAD: Mirage Atom Diffusion for De Novo Crystal Generation
• Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution
• Semantic Context Matters: Improving Conditioning for Autoregressive Models
• 10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training
• Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
• MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging
• RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
• Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
• Comparative Analysis of Large Language Model Inference Serving Systems: A Performance Study of vLLM and HuggingFace TGI
• ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks
• MedSumGraph: enhancing GraphRAG for medical QA with summarization and optimized prompts
• Performance and interpretability analysis of code generation large language models
• Text Annotation via Inductive Coding: Comparing Human Experts to LLMs in Qualitative Data Analysis
• Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
• Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk
• HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA
• Medical Knowledge Intervention Prompt Tuning for Medical Image Classification
• Can Small GenAI Language Models Rival Large Language Models in Understanding Application Behavior?
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• Adaptive Focus Memory for Language Models
• MMSense: Adapting Vision-based Foundation Model for Multi-task Multi-modal Wireless Sensing
• Suppressing VLM Hallucinations with Spectral Representation Filtering
• Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
• BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
• GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
• NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks
• Structured Definitions and Segmentations for Legal Reasoning in LLMs: A Study on Indian Legal Data
• BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages
• Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy
• Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model
• Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
• Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization
• GraphPilot: Grounded Scene Graph Conditioning for Language-Based Autonomous Driving
• Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots
• POTSA: A Cross-Lingual Speech Alignment Framework for Low Resource Speech-to-Text Translation
• STAGE: A Symbolic Tensor grAph GEnerator for distributed AI system co-design
• Mastering Olympiad-Level Physics with Artificial Intelligence
• From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance
• Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
• Making Every Head Count: Sparse Attention Without the Speed-Performance Trade-off
• End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
• iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
• Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
• BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generation
• The Path Not Taken: RLVR Provably Learns Off the Principals
• The Open Syndrome Definition as a Machine-Readable Standard for Public Health: Design and Implementation Study
• A mathematical theory of balancing relational generalization and memorization
• General Intelligence-based Fragmentation (GIF): A framework for peak-labeled spectra simulation
• Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speaking
• Mitigating Negative Flips via Margin Preserving Training
• Adaptive Multi-Agent Response Refinement in Conversational Systems
• Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
• Prompt Tuning for Natural Language to SQL with Embedding Fine-Tuning and RAG
• SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
• Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detection
• Testing Question Answering Software with Context-Driven Question Generation
• Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
• Revisiting MLLM Based Image Quality Assessment: Errors and Remedy
• Endpoint Security Agent: A Comprehensive Approach to Real-time System Monitoring and Threat Detection
• Smart but Costly? Benchmarking LLMs on Functional Accuracy and Energy Efficiency
• Cortex AISQL: A Production SQL Engine for Unstructured Data
• Adaptation of Foundation Models for Medical Image Analysis: Strategies, Challenges, and Future Directions
• Importance-Aware Data Selection for Efficient LLM Instruction Tuning
• DIMO: Diverse 3D Motion Generation for Arbitrary Objects
• Voice-Interactive Surgical Agent for Multimodal Patient Data Control
• Selecting Auxiliary Data via Neural Tangent Kernels for Low-Resource Domains
• StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
• E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
• TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-Tuning
• P3-LLM: An Integrated NPU-PIM Accelerator for LLM Inference Using Hybrid Numerical Formats
• Rethinking Parameter Sharing as Graph Coloring for Structured Compression
• SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
• AUTO-Explorer: Automated Data Collection for GUI Agent
• Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
• BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models
• ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning
• LLM³-DTI: A Large Language Model and Multi-modal data co-powered framework for Drug-Target Interaction prediction
• 10 Open Challenges Steering the Future of Vision-Language-Action Models
• VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving
• DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities
• Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
• A Remarkably Efficient Paradigm to Multimodal Large Language Models for Sequential Recommendation
• VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models
• Adaptation and Fine-tuning with TabPFN for Travelling Salesman Problem
• MIMIC-SR-ICD11: A Dataset for Narrative-Based Diagnosis
• S²LM: Towards Semantic Steganography via Large Language Models
• Order-Level Attention Similarity Across Language Models: A Latent Commonality
• Dynamic Residual Encoding with Slide-Level Contrastive Learning for End-to-End Whole Slide Image Representation
• Scientific judgment drifts over time in AI ideation
• A benchmark multimodal oro-dental dataset for large vision-language models
• The Future of Fully Homomorphic Encryption System: from a Storage I/O Perspective
• BudgetMem: Learning Selective Memory Policies for Cost-Efficient Long-Context Processing in Language Models
• Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid
• Cambrian-S: Towards Spatial Supersensing in Video
• ScaleDL: Towards Scalable and Efficient Runtime Prediction for Distributed Deep Learning Workloads
• Are We Aligned? A Preliminary Investigation of the Alignment of Responsible AI Values between LLMs and Human Judgment
• E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce
• DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
• CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
• SynQuE: Estimating Synthetic Dataset Quality Without Annotations
• Principled Coarse-Grained Acceptance for Speculative Decoding in Speech
• GUIDES: Guidance Using Instructor-Distilled Embeddings for Pre-trained Robot Policy Enhancement
• IndicSuperTokenizer: An Optimized Tokenizer for Indic Multilingual LLMs
• Learning When to Quit in Sales Conversations
• AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
• Credit Network Modeling and Analysis via Large Language Models
• Dynamic Reflections: Probing Video Representations with Text Alignment
• ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
• CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
• Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
• RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning
• An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM
• Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
• VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
• BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring
• Random Initialization of Gated Sparse Adapters
• LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models
• GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction
• HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models
• Assessing Factual Music Comprehension in Large Audio Language Models
• Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
• Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation
• AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
• Automated Invoice Data Extraction: Using LLM and OCR
• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
• Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus
• Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models
• Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
• On Selecting Few-Shot Examples for LLM-based Code Vulnerability Detection
• Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization
• Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing
• Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments
• Synergistic Tensor and Pipeline Parallelism
• Identifying the Periodicity of Information in Natural Language
• Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
• Elastic Architecture Search for Efficient Language Models
• The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
• LLMs Process Lists With General Filter Heads
• Cross-Platform Evaluation of Reasoning Capabilities in Foundation Models
• An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning
• Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models
• Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model
• OmniEduBench: A Comprehensive Chinese Benchmark for Evaluating Large Language Models in Education
• Chain-of-Thought Hijacking
• UniTok-Audio: A Unified Audio Generation Framework via Generative Modeling on Discrete Codec Tokens
• MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data
• RCScore: Quantifying Response Consistency in Large Language Models
• Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking
• QuantumBench: A Benchmark for Quantum Problem Solving
• Predicate Renaming via Large Language Models
• Revisiting Multilingual Data Mixtures in Language Model Pretraining
• SoK: Honeypots & LLMs, More Than the Sum of Their Parts?
• π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
• Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
• PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large Models
• TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
• CARE: A Multimodal Corpus for Studying Speech and Non-Verbal Communication Across Multiple Medical Conditions
• SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies
• ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
• Factuality challenges in the era of large language models and opportunities for fact-checking
• Beyond the “Wow” Factor: Using Generative AI for Increasing Generative Sense-Making
• AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
• Emission-Forecasting-Based Spatial-Temporal Carbon Response: A Multi-Agent Attention-Enhanced Deep Learning Framework
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers
• Mixture-of-Depths Attention
• A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models
• ExplainRec: Towards Explainable Multi-Modal Zero-Shot Recommendation with Preference Attribution and Large Language Models
• Self-driving laboratories in Japan
• Exploring large language models for the generation of synthetic training samples for aspect-based sentiment analysis in low resource settings
• Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
• RWGBench: Evaluating Scholarly Positioning in Related Work Generation
• Flows: Building Blocks of Reasoning and Collaborating AI
• TweetyBERT: Automated parsing of birdsong through self-supervised machine learning
• Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
• Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
• Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
• Why Open Source? A Game-Theoretic Analysis of the AI Race
• Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
• SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
• SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
• Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models
• RL makes MLLMs see better than SFT
• MIN-Merging: Merge the Important Neurons for Model Merging
• BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training
• Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning
• Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts
• IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
• GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
• DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
• Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead
• Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
• Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms
• Suzume-chan: Your Personal Navigator as an Embodied Information Hub
• Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
• STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
• What Limits Agentic Systems Efficiency?
• Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
• LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data
• zFLoRA: Zero-Latency Fused Low-Rank Adapters
• Synergizing chemical and AI communities for advancing laboratories of the future
• SALS: Sparse Attention in Latent Space for KV cache Compression
• MC-SJD : Maximal Coupling Speculative Jacobi Decoding for Autoregressive Visual Generation Acceleration
• BLM₁: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
• Leveraging LLMs for Early Alzheimer's Prediction
• MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
• Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs
• ChessQA: Evaluating Large Language Models for Chess Understanding
• Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins
• Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints
• Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures
• RoboOmni: Proactive Robot Manipulation in Omni-modal Context
• Larger and more instructable language models become less reliable
• Education Paradigm Shift To Maintain Human Competitive Advantage Over AI
• AutoStreamPipe: LLM Assisted Automatic Generation of Data Stream Processing Pipelines
• EMTSF:Extraordinary Mixture of SOTA Models for Time Series Forecasting
• MAP4TS: A Multi-Aspect Prompting Framework for Time-Series Forecasting with Large Language Models
• Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs
• Fast-MIA: Efficient and Scalable Membership Inference for LLMs
• Can Language Models Compose Skills In-Context?
• MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
• Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
• SALSA: Single-pass Autoregressive LLM Structured Classification
• Frustratingly Easy Task-aware Pruning for Large Language Models
• Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model
• Mitigating Coordinate Prediction Bias from Positional Encoding Failures
• Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
• Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents: Pathways and Paradigms
• Normalization in Attention Dynamics
• Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
• RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models
• REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
• A Unified Model for Multi-Task Drone Routing in Post-Disaster Road Assessment
• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Efficient semantic uncertainty quantification in language models via diversity-steered sampling
• MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
• Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings
• Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
• Understanding Network Behaviors through Natural Language Question-Answering
• LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)
• Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
• Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators
• Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answering
• Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
• ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
• Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
• GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs
• Addressing Corner Cases in Autonomous Driving: A World Model-based Approach with Mixture of Experts and LLMs
• UniSE: A Unified Framework for Decoder-only Autoregressive LM-based Speech Enhancement
• HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
• Context-level Language Modeling by Learning Predictive Context Embeddings
• Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
• RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
• Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency
• From Masks to Worlds: A Hitchhiker's Guide to World Models
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
• Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning)
• GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models
• On Interaction Effects in Greybox Fuzzing
• Data-Centric Lessons To Improve Speech-Language Pretraining
• Review of Tools for Zero-Code LLM Based Application Development
• Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
• CircuitGuard: Mitigating LLM Memorization in RTL Code Generation Against IP Leakage
• From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
• PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models
• KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
• Restoring Pruned Large Language Models via Lost Component Compensation
• AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation
• Unified Reinforcement and Imitation Learning for Vision-Language Models
• From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
• Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization
• Semantic World Models
• SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
• RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training
• C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search
• XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security
• QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models
• ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
• Large language models in medicine
• Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
• Automated urban waterlogging assessment and early warning through a mixture of foundation models
• SegTune: Structured and Fine-Grained Control for Song Generation
• BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks
• Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection
• Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
• Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations
• NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
• Identity-Aware Large Language Models require Cultural Reasoning
• Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
• Planned Diffusion
• MEG-GPT: A transformer-based foundation model for magnetoencephalography data
• Language Models as Semantic Augmenters for Sequential Recommenders
• From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
• Using natural language processing to analyse text data in behavioural science
• Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
• DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
• Strengthening LLMs for Tabular Prediction with Structural Priors
• TaxoAlign: Scholarly Taxonomy Generation Using Language Models
• Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
• Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models
• Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
• Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
• Graph4MM: Weaving Multimodal Learning with Structural Information
• Back to Bytes: Revisiting Tokenization Through UTF-8
• SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
• L-MoE: End-to-End Training of a Lightweight Mixture of Low-Rank Adaptation Experts
• Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios
• Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?
• Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
• QuanBench: Benchmarking Quantum Code Generation with Large Language Models
• MuonBP: Faster Muon via Block-Periodic Orthogonalization
• Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
• Prompt Optimization via Retrieved Reasoning Assets and Multi-Agent Analysis
• Robust Layerwise Scaling Rules by Proper Weight Decay Tuning
• Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions
• Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
• Learning to Answer from Correct Demonstrations
• The 3rd Place Solution of CCIR CUP 2025: A Framework for Retrieval-Augmented Generation in Multi-Turn Legal Conversation
• TeamFormer: Shallow Parallel Transformers with Progressive Approximation
• SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling
• Attention Is All You Need for KV Cache in Diffusion LLMs
• ChangingGrounding: 3D Visual Grounding in Changing Scenes
• Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
• Cross-Scenario Unified Modeling of User Interests at Billion Scale
• Tawa: Automatic Warp Specialization for Modern GPUs with Asynchronous References
• Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling
• Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction
• First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training
• Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback
• MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
• Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
• Spatial Preference Rewarding for MLLMs Spatial Understanding
• CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering
• Vision-Centric Activation and Coordination for Multimodal Large Language Models
• A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
• Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation
• Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signals
• IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection
• Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training
• David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation
• Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks
• CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
• F-BFQ: Flexible Block Floating-Point Quantization Accelerator for LLMs
• MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation
• BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure
• GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
• NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models
• Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
• Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference
• Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
• MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
• Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
• DSCD: Large Language Model Detoxification with Self-Constrained Decoding
• RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
• A Survey on Evaluation of Large Language Models
• Litespark Technical Report: High-Throughput, Energy-Efficient LLM Training Framework
• Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models
• A Survey on Parallel Reasoning
• Single chip 1 Tb/s optical transmitter with inverse designed input and output couplers
• Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models
• Toward LLM-Supported Automated Assessment of Critical Thinking Subskills
• Indoor Localization using Compact, Telemetry-Agnostic, Transfer-Learning Enabled Decoder-Only Transformer
• ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty
• Scaling Language-Centric Omnimodal Representation Learning
• BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis
• MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
• Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding
• Automated Skill Decomposition Meets Expert Ontologies: Bridging the Granularity Gap with LLMs
• FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks
• FedLoRA-Optimizer: Federated LoRA Fine-Tuning with Global and Local Optimization in Heterogeneous Data Scenarios
• XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
• CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
• FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
• Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
• Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
• ShishuLM: Lightweight Language Model with Hybrid Decoder-MLP Architecture and Paired Weight Sharing
• APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport
• Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank
• Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval
• Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval
• PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
• PAGE: Prompt Augmentation for text Generation Enhancement
• Cognitive Load Traces as Symbolic and Visual Accounts of Deep Model Cognition
• Direct Multi-Token Decoding
• Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
• RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
• High-Fidelity Speech Enhancement via Discrete Audio Tokens
• UniCoD: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
• HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
• Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications
• Enhancing Long-Term Welfare in Recommender Systems: An Information Revelation Approach
• Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
• SoundReactor: Frame-level Online Video-to-Audio Generation
• High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
• Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning
• UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
• ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
• Embodiment in multimodal large language models
• Are Video Models Emerging as Zero-Shot Learners and Reasoners in Medical Imaging?
• PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
• PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
• Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
• Complementary and Contrastive Learning for Audio-Visual Segmentation
• Automated Glaucoma Report Generation via Dual-Attention Semantic Parallel-LSTM and Multimodal Clinical Data Integration
• MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
• Unpacking Hateful Memes: Presupposed Context and False Claims
• Shaping History, Responsibly: Seven Principles to Guide the Design of Archival AI Assistants for Cultural Heritage Collections
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis
• GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design
• Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA
• Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning
• Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors
• Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
• OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models
• Accelerating Attention with Basis Decomposition
• Small edits, large models: How Wikipedia advocacy shapes LLM values
• Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio
• Holistic Order Prediction in Natural Scenes
• Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
• Can We Reliably Rank Model Performance across Domains without Labeled Data?
• StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
• Provable Watermarking for Data Poisoning Attacks
• SynthID-Image: Image watermarking at internet scale
• DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
• AdaPM: a Partial Momentum Algorithm for LLM Training
• Efficient Resource-Constrained Training of Vision Transformers via Subspace Optimization
• Users as Annotators: LLM Preference Learning from Comparison Mode
• Preference-Aware Memory Update for Long-Term LLM Agents
• Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
• Web Crawler Restrictions, AI Training Datasets & Political Biases
• Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
• SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
• PlatformX: An End-to-End Transferable Platform for Energy-Efficient Neural Architecture Search
• Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search
• Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
• Provable Training Data Identification for Large Language Models
• When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
• GRETEL: A Goal-driven Retrieval and Execution-based Trial Framework for LLM Tool Selection Enhancing
• PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
• Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization
• NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
• Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
• Agent Learning via Early Experience
• To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
• AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
• Past, Present, and Future of Bug Tracking in the Generative AI Era
• VoiceAgentBench: Are Voice Assistants ready for agentic tasks?
• From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses
• Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
• Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention
• OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
• NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
• Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking
• RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models
• ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
• RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models
• D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
• Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
• Search-R3: Unifying Reasoning and Embedding in Large Language Models
• Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
• Growing Visual Generative Capacity for Pre-Trained MLLMs
• Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models
• Mid-Training of Large Language Models: A Survey
• AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
• Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
• Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
• The Framework That Survives Bad Models: Human-AI Collaboration For Clinical Trials
• Training Dynamics Impact Post-Training Quantization Robustness
• Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
• lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models
• DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization
• Mixture of Neuron Experts
• Primal-Dual Direct Preference Optimization for Constrained LLM Alignment
• Membership Inference Attacks on Tokenizers of Large Language Models
• YpathRAG:A Retrieval-Augmented Generation Framework and Benchmark for Pathology
• vAttention: Verified Sparse Attention
• AutoPentester: An LLM Agent-based Framework for Automated Pentesting
• FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation
• MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation
• The New Quant: A Survey of Large Language Models in Financial Prediction and Trading
• Prototype-Based Dynamic Steering for Large Language Models
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
• Operational Risks in Grid Integration of Large Data Center Loads: Characteristics, Stability Assessments, and Sensitivity Studies
• Staircase Streaming for Low-Latency Multi-Agent Inference
• Resource-Efficient Fine-Tuning of LLaMA-3.2-3B for Medical Chain-of-Thought Reasoning
• Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
• Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
• ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
• SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba
• NLD-LLM: A systematic framework for evaluating small language transformer models on natural language description
• Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
• DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
• Self Speculative Decoding for Diffusion Large Language Models
• Evaluation of Clinical Trials Reporting Quality using Large Language Models
• The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
• Small Language Models for Emergency Departments Decision Support: A Benchmark Study
• Spectral Alignment as Predictor of Loss Explosion in Neural Network Training
• MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering
• Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text
• Towards Sampling Data Structures for Tensor Products in Turnstile Streams
• Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs
• Efficient Test-Time Scaling for Small Vision-Language Models
• Know Thyself? On the Incapability and Implications of AI Self-Recognition
• IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context
• TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs
• Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
• AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
• AgenticRAG: Tool-Augmented Foundation Models for Zero-Shot Explainable Recommender Systems
• Geolog-IA: Conversational System for Academic Theses
• Deep Generative Continual Learning using Functional LoRA: FunLoRA
• Model-Agnostic Correctness Assessment for LLM-Generated Code via Dynamic Internal Representation Selection
• MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
• Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
• Backdoor Attacks Against Speech Language Models
• Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer
• SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
• Visual Self-Refinement for Autoregressive Models
• The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs
• Automated Structured Radiology Report Generation with Rich Clinical Context
• SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
• Generative AI for subgrid turbulence in large-eddy simulations
• TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
• Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
• Retrieval-Augmented Framework for LLM-Based Clinical Decision Support
• Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
• Glaucoma Detection and Structured OCT Report Generation via a Fine-tuned Multimodal Large Language Model
• Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
• Judging with Confidence: Calibrating Autoraters to Preference Distributions
• Instruction‐Tuned Large‐Language Models for Quality Control in Automatic Item Generation: A Feasibility Study
• LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
• Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
• Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
• SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
• Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
• The silence of the weights: an investigation of structural pruning strategies for attention-based audio signal architectures
• Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models
• MUVLA: Learning to Explore Object Navigation via Map Understanding
• ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
• HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis
• RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
• Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition
• Better with Less: Small Proprietary Models Surpass Large Language Models in Financial Transaction Understanding
• ScheduleMe: Multi-Agent Calendar Assistant
• Layer-wise dynamic rank for compressing large language models
• LMOD+: A Comprehensive Multimodal Dataset and Benchmark for Developing and Evaluating Multimodal Large Language Models in Ophthalmology
• Effective Model Pruning
• OceanGym: A Benchmark Environment for Underwater Embodied Agents
• PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
• VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
• MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
• EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal Circuit
• Towards Structured Knowledge: Advancing Triple Extraction from Regional Trade Agreements using Large Language Models
• VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning
• MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
• OIG-Bench: A Multi-Agent Annotated Benchmark for Multimodal One-Image Guides Understanding
• MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
• Vision Function Layer in Multimodal LLMs
• SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
• UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
• ISSE: An Instruction-Guided Speech Style Editing Dataset And Benchmark
• Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
• AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
• Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
• ELASTIQ: EEG-Language Alignment with Semantic Task Instruction and Querying
• Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports
• When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs
• VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
• Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
• World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
• NeMo: Needle in a Montage for Video-Language Understanding
• Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct
• Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
• Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
• Reinforcement Mid-Training
• Autoregressive Video Generation beyond Next Frames Prediction
• Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
• Sequential Diffusion Language Models
• The Hidden Costs of Translation Accuracy: Distillation, Quantization, and Environmental Impact
• Detecting and Rectifying Noisy Labels: A Similarity-based Approach
• ColLab: A Collaborative Spatial Progressive Data Engine for Referring Expression Comprehension and Generation
• HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models
• Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
• Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception
• Spiral of Silence in Large Language Model Agents
• Aligning LLMs for Multilingual Consistency in Enterprise Applications
• Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
• Timber: Training-free Instruct Model Refining with Base via Effective Rank
• Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales
• RIV: Recursive Introspection Mask Diffusion Vision Language Model
• QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
• The Impact of Role Design in In-Context Learning for Large Language Models
• GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models
• NeuroBridge: Using Generative AI to Bridge Cross-neurotype Communication Differences through Neurotypical Perspective-taking
• SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size
• A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
• Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Models
• Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin
• Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
• Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration
• Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
• PT²-LLM: Post-Training Ternarization for Large Language Models
• ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View
• Data-Efficient Training by Evolved Sampling
• Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
• BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
• XGC-AVis: Towards Audio-Visual Content Understanding with a Multi-Agent Collaborative System
• d²Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
• MindCraft: How Concept Trees Take Shape In Deep Models
• MMPB: It's Time for Multi-Modal Personalization
• VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
• Voice user interfaces for effortless navigation in medical virtual reality environments
• Ethische Betrachtungen der automatisierten Textanalyse <b>: Fortschritte, Risiken und die Notwendigkeit eines Gleichgewichts</b>
• UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration
• Activation Function Design Sustains Plasticity in Continual Learning
• Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
• Investigating Faithfulness in Large Audio Language Models
• Stochastic activations
• SoDaDE: Solvent Data-Driven Embeddings with Small Transformer Models
• Unlocking the Power of Mixture-of-Experts for Task-Aware Time Series Analytics
• Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
• Multi-Agent Path Finding via Offline RL and LLM Collaboration
• Multilingual Vision-Language Models, A Survey
• Mind the Missing: Variable-Aware Representation Learning for Irregular EHR Time Series using Large Language Models
• COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
• Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
• From Bias to Balance: Exploring and Mitigating Spatial Bias in LVLMs
• Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration
• A High-Capacity and Secure Disambiguation Algorithm for Neural Linguistic Steganography
• AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
• Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues
• On the Complexity Theory of Masked Discrete Diffusion: From poly(1/ε) to Nearly ε-Free
• Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference
• Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling
• An LLM-Powered Agent for Real-Time Analysis of the Vietnamese IT Job Market
• Tiny-QMoE
• InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?
• Filtering with Confidence: When Data Augmentation Meets Conformal Prediction
• SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips
• Go With The Flow: Churn-Tolerant Decentralized Training of Large Language Models
• PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models
• A short survey on almost orthogonal vectors in a few specific large dimensions
• ArchGPT: Understanding the World's Architectures with Large Multimodal Models
• SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
• Generative AI for FFRDCs
• ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation
• GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models
• Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
• Instruction Boundary: Quantifying Biases in LLM Reasoning under Various Coverage
• One Filters All: A Generalist Filter for State Estimation
• Embodied AI: From LLMs to World Models
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
• WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction
• SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding
• Eliminating stability hallucinations in llm-based tts models via attention guidance
• BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens
• WEE-Therapy: A Mixture of Weak Encoders Framework for Psychological Counseling Dialogue Analysis
• Thinking While Listening: Simple Test Time Scaling For Audio Classification
• Learning Contextual Retrieval for Robust Conversational Search
• Boosting Zero-Shot VLN via Abstract Obstacle Map-Based Waypoint Prediction with TopoGraph-and-VisitInfo-Aware Prompting
• Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports
• LOCA: Logical Chain Augmentation for Scientific Corpus Cleaning
• Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
• AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
• Uncertainty in Semantic Language Modeling with PIXELS
• epiGPTope: A Machine Learning-Based Epitope Generator and Classifier
• GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference
• Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings
• AgentClinic: a multimodal benchmark for tool-using clinical AI agents
• Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models
• VIG-RL: Learning to Search and Insert for Verified Image Grounding
• The potential and limitations of large language models for automatic classification of teachers' motivational messages in educational research
• Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
• Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
• Divergence Decoding: Training-Free Capability Fusion
• Reading Between the Signs: Predicting Future Suicidal Ideation from Adolescent Social Media Texts
• SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
• Training Compute-Optimal Protein Language Models
• From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency
• Chatbot Epistemology
• AI for social science and social science of AI: A survey
• Navigating the AI era: university communication strategies and perspectives on generative AI tools
• Multi-Robot system environmental constraint analysis by petri nets
• Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method
• VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
• ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
• Enhancing Speech Large Language Models through Reinforced Behavior Alignment
• Layerwise Importance Analysis of Feed-Forward Networks in Transformer-based Language Models
• LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
• MAPO: Mixed Advantage Policy Optimization
• COLT: Enhancing Video Large Language Models with Continual Tool Usage
• Steering Multimodal Large Language Models Decoding for Context-Aware Safety
• OmniBridge: Unified Multimodal Understanding, Generation, and Retrieval via Latent Space Alignment
• Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
• Code Driven Planning with Domain-Adaptive Critic
• Advances in Large Language Models for Medicine
• Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
• ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
• CorefInst: Leveraging LLMs for Multilingual Coreference Resolution
• Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning
• Scale-free Characteristics of Multilingual Legal Texts and the Limitations of LLMs
• Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill
• UIPro: Unleashing Superior Interaction Capability For GUI Agents
• AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning
• AccessEval: Benchmarking Disability Bias in Large Language Models
• How Persuasive is Your Context?
• Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
• SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
• LIMI: Less is More for Agency
• nDNA -- the Semantic Helix of Artificial Cognition
• PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
• MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification
• VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
• MCTS-EP: Empowering Embodied Planning with Online Preference Optimization
• ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation
• Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
• Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
• Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions
• \boldsymbolλ-Orthogonality Regularization for Compatible Representation Learning
• Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever
• DoubleGen: Debiased Generative Modeling of Counterfactuals
• Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
• HERO: Hierarchical Extrapolation and Refresh for Efficient World Models
• ENSAM: an efficient foundation model for interactive segmentation of 3D medical images
• REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting
• Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
• VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
• Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition
• Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models
• Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval
• Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
• Defining and Monitoring Complex Robot Activities via LLMs and Symbolic Reasoning
• Efficient Multimodal Dataset Distillation via Generative Models
• Real, Fake, or Manipulated? Detecting Machine-Influenced Text
• Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
• OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
• What Matters in LLM-Based Feature Extractor for Recommender? A Systematic Analysis of Prompts, Models, and Adaptation
• Benchmarking and Improving LLM Robustness for Personalized Generation
• MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
• Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
• Rationality Check! Benchmarking the Rationality of Large Language Models
• Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction
• Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
• OpenViGA: Video Generation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data
• AToken: A Unified Tokenizer for Vision
• A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts
• AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
• Enhancing Time Awareness in Generative Recommendation
• TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates
• Neural Speech Separation with Parallel Amplitude and Phase Spectrum Estimation
• StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs
• Learning the natural history of human disease with generative transformers
• GestOS: Advanced Hand Gesture Interpretation via Large Language Models to control Any Type of Robot
• Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
• Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
• Benchmarking ChatGPT and DeepSeek in April 2025: A Novel Dual Perspective Sentiment Analysis Using Lexicon-Based and Deep Learning Approaches
• Evaluating LLM Alignment on Personality Inference from Real-World Interview Data
• Validating Solidity Code Defects using Symbolic and Concrete Execution powered by Large Language Models
• HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference
• Toward PDDL Planning Copilot
• Sparse Training Scheme for Multimodal LLM
• Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
• Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
• Beyond Data Privacy: New Privacy Risks for Large Language Models
• EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer
• Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach
• The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
• Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning
• KoSEL: Knowledge subgraph enhanced large language model for medical question answering
• A comparison of pipelines for the translation of a low resource language based on transformers
• RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing
• Exploring Conversational Design Choices in LLMs for Pedagogical Purposes: Socratic and Narrative Approaches for Improving Instructor's Teaching Practice
• Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training
• Token Homogenization under Positional Bias
• LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
• Uncertainty in Authorship: Why Perfect AI Detection Is Mathematically Impossible
• Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding
• NeuroStrike: Neuron-Level Attacks on Aligned LLMs
• Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation
• A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detection
• AssemMate: Graph-Based LLM for Robotic Assembly Assistance
• ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
• Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
• Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer
• Does Language Model Understand Language?
• FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
• Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations
• BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization
• Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
• We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism
• PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits
• From Parameters to Performance: A Data-Driven Study on LLM Structure and Development
• OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
• Adapting Public Personas: A Multimodal Study of U.S. Legislators' Cross-Platform Social Media Strategies
• CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction
• LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
• No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
• Compartmentalised Agentic Reasoning for Clinical NLI
• Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
• Large Language Models Meet Legal Artificial Intelligence: A Survey
• Beyond Token Limits: Assessing Language Model Performance on Long Text Classification
• Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching
• WALL: A Web Application for Automated Quality Assurance using Large Language Models
• Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization
• Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis
• Prompting the Market? A Large-Scale Meta-Analysis of GenAI in Finance NLP (2022-2025)
• Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
• ENSI: Efficient Non-Interactive Secure Inference for Large Language Models
• Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
• LightAgent: Production-level Open-source Agentic AI Framework
• Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
• DATE: Dynamic Absolute Time Enhancement for Long Video Understanding
• GmSLM : Generative Marmoset Spoken Language Modeling
• HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning
• Character-Level Perturbations Disrupt LLM Watermarks
• TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla
• Meta-Learning Reinforcement Learning for Crypto-Return Prediction
• SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds
• CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio
• COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation
• BRoverbs -- Measuring how much LLMs understand Portuguese proverbs
• Augmenting speech transcripts of VR recordings with gaze, pointing, and visual context for multimodal coreference resolution
• Multimodal LLMs See Sentiment
• QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments
• PICO: Performance Insights for Collective Operations
• TraceRAG: A LLM-Based Framework for Explainable Android Malware Detection and Behavior Analysis
• Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism
• Recurrence Meets Transformers for Universal Multimodal Retrieval
• RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation
• Bias after Prompting: Persistent Discrimination in Large Language Models
• Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning
• Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
• Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment
• BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment
• Language Self-Play For Data-Free Training
• Towards Post-mortem Data Management Principles for Generative AI
• AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
• AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
• Causal Attention with Lookahead Keys
• Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
• Testing chatbots on the creation of encoders for audio conditioned image generation
• Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
• Large language models surpass domain-specific architectures for antepartum electronic fetal monitoring analysis
• Reconstruction Alignment Improves Unified Multimodal Models
• Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
• Electricity Demand and Grid Impacts of AI Data Centers: Challenges and Prospects
• The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
• SoK: Security and Privacy of AI Agents for Blockchain
• UniSearch: Rethinking Search System with a Unified Generative Architecture
• Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
• Contrastive Self-Supervised Network Intrusion Detection using Augmented Negative Pairs
• FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations
• LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection
• Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
• Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
• Text4Seg++: Advancing Image Segmentation via Generative Language Modeling
• AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution
• D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning -- A Benchmark Dataset and Method
• Augmented Fine-Tuned LLMs for Enhanced Recruitment Automation
• From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
• Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
• LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
• Few-Shot Query Intent Detection via Relation-Aware Prompt Learning
• CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
• Semantic-guided LoRA Parameters Generation
• Masked Diffusion Language Models with Frequency-Informed Training
• OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
• PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
• Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts
• Reverse Browser: Vector-Image-to-Code Generator
• A Study of Large Language Models for Patient Information Extraction: Model Architecture, Fine-Tuning Strategy, and Multi-task Instruction Tuning
• Towards Open World Detection: A Survey
• Shared Autonomy through LLMs and Reinforcement Learning for Applications to Ship Hull Inspections
• Delta Activations: A Representation for Finetuned Large Language Models
• Towards a Unified View of Large Language Model Post-Training
• Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition
• PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
• RL's Razor: Why Online Reinforcement Learning Forgets Less
• SMooGPT: Stylized Motion Generation using Large Language Models
• SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
• Weakly-Supervised Learning of Dense Functional Correspondences
• VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
• Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki
• Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model
• Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
• PediatricsMQA: a Multi-modal Pediatrics Question Answering Benchmark
• Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects
• E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition
• LLM-GUARD: Large Language Model-Based Detection and Repair of Bugs and Security Vulnerabilities in C++ and Python
• SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala
• PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs
• MedQARo: A Large-Scale Benchmark for Medical Question Answering in Romanian
• AIVA: An AI-based Virtual Companion for Emotion-aware Interaction
• TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum
• Advancing SLM Tool-Use Capability using Reinforcement Learning
• Scaling behavior of large language models in emotional safety classification across sizes and tasks
• DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off
• MoPEQ: Mixture of Mixed Precision Quantized Experts
• Generative AI for Crystal Structures: A Review
• Implicit Reasoning in Large Language Models: A Comprehensive Survey
• CMRAG: Co-modality-based visual document retrieval and question answering
• From Confidence to Collapse in LLM Factual Robustness
• Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization
• HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
• FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data
• Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving
• Deep Reinforcement Learning for Drone Route Optimization in Post-Disaster Road Assessment
• Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
• Upcycling Candidate Tokens of Large Language Models for Query Expansion
• 2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
• Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models
• Benchmarking and Studying the LLM-based Code Review
• CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-commerce Markets
• Cloud-Device Collaborative Agents for Sequential Recommendation
• Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection
• The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
• LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving
• MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction
• Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping
• Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation
• Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief
• GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model
• Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition
• Efficient Large Language Models with Zero-Shot Adjustable Acceleration
• Unraveling LLM Jailbreaks Through Safety Knowledge Neurons
• X-Troll: eXplainable Detection of State-Sponsored Information Operations Agents
• TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering
• A User-centric Kubernetes-based Architecture for Green Cloud Computing
• Efficient Graph Understanding with LLMs via Structured Context Injection
• OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
• MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
• Neuro-Symbolic Predictive Process Monitoring
• Spotlighter: Revisiting Prompt Tuning from a Representative Mining View
• MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework
• Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
• Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
• BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
• COMET: A Framework for Modeling Compound Operation Dataflows with Explicit Collectives
• Entropy-based Coarse and Compressed Semantic Speech Representation Learning
• Universal Properties of Activation Sparsity in Modern Large Language Models
• The Resurgence of GCG Adversarial Attacks on Large Language Models
• Visually Grounded Narratives: Reducing Cognitive Burden in Researcher-Participant Interaction
• Intelligent Spectrum Management in Satellite Communications
• Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference
• Data Auctions for Retrieval Augmented Generation
• Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments
• EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics
• Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards
• RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
• VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
• Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
• Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study
• Rethinking Layer-wise Model Merging through Chain of Merges
• Generalizable Object Re-Identification via Visual In-Context Prompting
• HyperFlexis: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling
• WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration
• PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance
• Signs of Struggle: Spotting Cognitive Distortions across Language and Register
• Can News Predict the Direction of Oil Price Volatility? A Language Model Approach with SHAP Explanations
• SemSR: Semantics aware robust Session-based Recommendations
• Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio
• AWorld: Orchestrating the Training Recipe for Agentic AI
• MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever
• Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
• Foundation Models for Cross-Domain EEG Analysis Application: A Survey
• Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
• Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
• OneRec-V2 Technical Report
• Automated Bug Triaging using Instruction-Tuned Large Language Models
• Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
• Beyond Transcription: Mechanistic Interpretability in ASR
• OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
• A Novel Framework for Automated Explain Vision Model Using Vision-Language Models
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
• CataractSurg-80K: Knowledge-Driven Benchmarking for Structured Reasoning in Ophthalmic Surgery Planning
• GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
• Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization
• Self-supervised structured object representation learning
• Ego-centric Predictive Model Conditioned on Hand Trajectories
• Scalable Object Detection in the Car Interior With Vision Foundation Models
• FinCast: A Foundation Model for Financial Time-Series Forecasting
• How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
• Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
• SynthCoder: A Synthetical Strategy to Tune LLMs for Code Completion
• Ensemble Debates with Local Large Language Models for AI Alignment
• Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC
• GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification
• SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version
• An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
• An Investigation on Group Query Hallucination Attacks
• MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution
• Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units
• Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
• Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
• Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
• DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models
• SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
• WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
• Exploring Scaling Laws of CTR Model for Online Performance Improvement
• AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation
• VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
• SyGra: A Unified Graph-Based Framework for Scalable Generation, Quality Tagging, and Management of Synthetic Data
• RETAIL: Towards Real-world Travel Planning for Large Language Models
• An Empirical Study of Knowledge Distillation for Code Understanding Tasks
• Influence-driven Curriculum Learning for Pre-training on Limited Data
• Survey of Vision-Language-Action Models for Embodied Manipulation
• Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation
• Identifying and Answering Questions with False Assumptions: An Interpretable Approach
• Fine-tuning and prompt engineering for large language models-based code review automation
• Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
• GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
• Long-Context Speech Synthesis with Context-Aware Memory
• SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
• LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa
• Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper
• Comparing energy consumption and accuracy in text classification inference
• Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
• Democratizing News Recommenders: Modeling Multiple Perspectives for News Candidate Generation with VQ-VAE
• Online Conformal Selection with Accept-to-Reject Changes
• PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
• MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
• From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models
• AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
• Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models
• ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
• FLAIR: Feedback Learning for Adaptive Information Retrieval
• Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
• REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks
• Maximum Score Routing For Mixture-of-Experts
• CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
• Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods
• MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation
• Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models
• RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
• A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation
• CC-Time: Cross-Model and Cross-Modality Time Series Forecasting
• GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding
• VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine
• TBGRecall: A Generative Retrieval Model for E-commerce Recommendation Scenarios
• UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting
• Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
• AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment
• Reference Points in LLM Sentiment Analysis: The Role of Structured Context
• Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse
• Retrieval-augmented reasoning with lean language models
• Feedback Indicators: The Alignment between Llama and a Teacher in Language Learning
• Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric
• Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
• GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
• Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation
• Modeling Human Responses to Multimodal AI Content
• Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
• Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
• REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations
• AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models
• SemPT: Semantic Prompt Tuning for Vision-Language Models
• Increasing the Utility of Synthetic Images through Chamfer Guidance
• HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
• Empowering Multimodal LLMs with External Tools: A Comprehensive Survey
• Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning
• XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
• Flexible Personalized Split Federated Learning for On-Device Fine-Tuning of Foundation Models
• Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
• Inductive Bias Extraction and Matching for LLM Prompts
• Failures to Surface Harmful Contents in Video Large Language Models
• Meta-Metrics and Best Practices for System-Level Inference Performance Benchmarking
• MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
• Bridging Modality Gaps in e-Commerce Products via Vision-Language Alignment
• Stable Diffusion Models are Secretly Good at Visual In-Context Learning
• Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation
• LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
• GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
• Teaching LLMs to Speak Spectroscopy
• Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorld
• MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
• Preacher: Paper-to-Video Agentic System
• The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
• Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
• Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach
• NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
• Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
• Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses
• Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
• DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models
• InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
• SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)
• Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
• A Survey on Training-free Alignment of Large Language Models
• LLaMA-Based Models for Aspect-Based Sentiment Analysis
• Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment
• Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
• DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives
• KFFocus: Highlighting Keyframes for Enhanced Video Understanding
• Street-Level AI: Are Large Language Models Ready for Real-World Judgments?
• ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model
• DiffractGPT: Atomic Structure Determination from X-ray Diffraction Patterns using Generative Pre-trained Transformer
• Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model
• Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
• UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
• Grouped Speculative Decoding for Autoregressive Image Generation
• LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
• From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users
• MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling
• Large Language Models for Subjective Language Understanding: A Survey
• Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements
• MolmoAct: Action Reasoning Models that can Reason in Space
• Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity
• UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games
• Semantic-Enhanced Time-Series Forecasting via Large Language Models
• ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering
• AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation
• Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond
• A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation
• Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment
• Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models
• Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative
• AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning
• Tasa: Thermal-aware 3D-Stacked Architecture Design with Bandwidth Sharing for LLM Inference
• AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning
• QuiZSF: An efficient data-model interaction framework for zero-shot time-series forecasting
• Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges
• Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning
• CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
• Bridging Classical and Quantum Computing for Next-Generation Language Models
• Whisfusion: Parallel ASR Decoding with Masked Diffusion
• Confidence Estimation for Text-to-SQL in Large Language Models
• HapticLLaMA: A Multimodal Sensory Language Model for Haptic Captioning
• Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning
• Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis
• Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
• AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance
• MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging
• Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
• When a Paper Has 1000 Authors: Rethinking Citation Metrics in the Era of LLMs
• NEP: Autoregressive Image Editing via Next Editing Token Prediction
• Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
• LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
• Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education
• Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
• LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients
• Adapting Vision-Language Models Without Labels: A Comprehensive Survey
• PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
• Streamlining Admission with LOR Insights: AI-Based Leadership Assessment in Online Master's Program
• UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
• mKG-RAG: Multimodal Knowledge Graph-Enhanced RAG for Visual Question Answering
• Pruning Large Language Models by Identifying and Preserving Functional Networks
• QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering
• AI-assisted JSON Schema Creation and Mapping
• A Survey on Video Temporal Grounding with Multimodal Large Language Model
• FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models
• ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos
• An Effective Approach for Node Classification in Textual Graphs
• VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence
• Multimodal RAG Enhanced Visual Description
• Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
• X-SAM: From Segment Anything to Any Segmentation
• Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
• Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation
• RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection
• SVGen: Interpretable Vector Graphics Generation with Large Language Models
• TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models
• FlexQ: Efficient Post-training INT6 Quantization for LLM Serving via Algorithm-System Co-Design
• DRAMA: A Dynamic and Robust Allocation-based Multi-Agent System for Changing Environments
• StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
• Leveraging large language models for SQL behavior-based database intrusion detection
• From eye to AI: studying rodent social behavior in the era of machine Learning
• DP-GPT4MTS: Dual-Prompt Large Language Model for Textual-Numerical Time Series Forecasting
• Parallel GPT: Harmonizing the Independence and Interdependence of Acoustic and Semantic Information for Zero-Shot Text-to-Speech
• COPO: Consistency-Aware Policy Optimization
• AquaChat++: LLM-Assisted Multi-ROV Inspection for Aquaculture Net Pens with Integrated Battery Management and Thruster Fault Tolerance
• Efficient Scaling for LLM-based ASR
• PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
• MiDashengLM: Efficient Audio Understanding with General Audio Captions
• Confidence-Weighted Token Set Cover for Early Hypothesis Pruning in Self-Consistency
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
• GP and LLMs for Program Synthesis: No Clear Winners
• Sotopia-RL: Reward Design for Social Intelligence
• An Entity Linking Agent for Question Answering
• MegaWika 2: A More Comprehensive Multilingual Collection of Articles and their Sources
• Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs
• Can Large Vision-Language Models Understand Multimodal Sarcasm?
• Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling
• VQA support to Arabic Language Learning Educational Tool
• Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes
• IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
• VLMQ: Efficient Post-Training Quantization for Large Vision-Language Models via Hessian Augmentation
• SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
• Survey of Large Language Models in Extended Reality: Technical Paradigms and Application Frontiers
• Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs
• CTTS: Collective Test-Time Scaling
• LOST: Low-rank and Sparse Pre-training for Large Language Models
• TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs
• Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
• VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
• Balancing Information Accuracy and Response Timeliness in Networked LLMs
• Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference
• VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
• S-RRG-Bench: Structured Radiology Report Generation with Fine-Grained Evaluation Framework
• TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
• Evaluating Position Bias in Large Language Model Recommendations
• Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
• LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing
• Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving
• SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
• Large Language Model Guided Decoding for Self-Supervised Speech Recognition
• Zero-shot Compositional Action Recognition with Neural Logic Constraints
• GlaBoost: A multimodal Structured Framework for Glaucoma Risk Stratification
• Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language
• Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment
• StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding
• LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
• Empowering Tabular Data Preparation with Language Models: Why and How?
• MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning
• T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval
• Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
• CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
• Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler
• Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan
• KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs
• MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
• Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models
• CarbonScaling: Extending Neural Scaling Laws for Carbon Footprint in Large Language Models
• FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
• SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation
• T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
• Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data
• A Note on Code Quality Score: LLMs for Maintainable Large Codebases
• How LLMs are Shaping the Future of Virtual Reality
• PaPaformer: Language Model from Pre-trained Parallel Paths
• AutoDebias: Automated Framework for Debiasing Text-to-Image Models
• From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
• ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation
• Uncovering Latent Connections in Indigenous Heritage: Semantic Pipelines for Cultural Preservation in Brazil
• Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation
• ART: Adaptive Relation Tuning for Generalized Relation Prediction
• A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving
• Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
• PixNerd: Pixel Neural Field Diffusion
• OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction
• Your Spending Needs Attention: Modeling Financial Habits with Transformers
• Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space
• H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation
• Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
• On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
• Failures Are the Stepping Stones to Success: Enhancing Few-Shot In-Context Learning by Leveraging Negative Samples
• ChatVis: Large Language Model Agent for Generating Scientific Visualizations
• SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity
• KLLM: Fast LLM Inference with K-Means Quantization
• Automatically discovering heuristics in a complex SAT solver with large language models
• TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
• Real-time News Story Identification
• MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention
• What is Beneath Misogyny: Misogynous Memes Classification and Explanation
• DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception
• A Foundation Model for Material Fracture Prediction
• Context-aware Rotary Position Embedding
• Generative Recommendation with Semantic IDs: A Practitioner's Handbook
• X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
• See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
• Improving Generative Ad Text on Facebook using Reinforcement Learning

Related

• Code Llama: Open Foundation Models for Code
• The Llama 3 Herd of Models
• LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• JetMoE: Reaching Llama2 Performance with 0.1M Dollars