mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 22 May 2025

635 papers

  1. ACCORD: Autoregressive Constraint-satisfying Generation for COmbinatorial Optimization with Routing and Dynamic attentionLLM reasoning → Mathematical reasoning
  2. Can ChatGPT Perform Image Splicing Detection? A Preliminary StudyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  3. Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
  4. Reasoning in Neurosymbolic AILLM reasoning → Reasoning benchmarks and evaluation
  5. Let's Get You Hired: A Job Seeker's Perspective on Multi-Agent Recruitment Systems for Explaining Hiring DecisionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  6. Manalyzer: End-to-end Automated Meta-analysis with Multi-agent SystemLLM agents and tool use → Web, search, and research agents
  7. Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMsMechanistic interpretability → Steering and probing for LLM safety
  8. Towards medical AI misalignment: a preliminary studyLLM safety and security → Safety alignment, refusal and guardrails
  9. DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic LogicLLM reasoning → Test-time compute and efficient thinking
  10. VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question AnsweringRetrieval-augmented generation → Conversational and speech RAG
  11. From Compression to Expression: A Layerwise Analysis of In-Context LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  12. Control of Renewable Energy Communities using AI and Real-World DataDeep reinforcement learning methods → RL for energy, networks and operations
  13. Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in ReasoningLLM reasoning → Test-time compute and efficient thinking
  15. AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  16. Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing UncertaintyLLM reasoning → Knowledge- and tool-augmented reasoning +2
  17. Zebra-Llama: Towards Extremely Efficient Hybrid ModelsEfficient LLM inference and serving → Serving systems and request scheduling
  18. GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and CitationsLLM reasoning → Reasoning for agents, planning and code
  19. Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  20. JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation ModelMixture-of-experts → MoE large language models
  21. ExpertGen: Training-Free Expert Guidance for Controllable Text-to-Face GenerationDiffusion models → Image generation, text-to-image and editing
  22. ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  23. Where You Go is Who You Are: Behavioral Theory-Guided LLMs for Inverse Reinforcement LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
  24. Backdoors in DRL: Four Environments Focusing on In-distribution TriggersDeep reinforcement learning methods → Adversarial robustness and RL in finance
  25. ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  26. Optimal Policy Minimum Bayesian RiskLLM reasoning → Reinforcement learning for reasoning
  27. Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)Retrieval-augmented generation → Agentic RAG, agents and memory +1
  28. ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL DialectsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  29. Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning ModelsLLM reasoning → Mathematical reasoning
  30. Effective Reinforcement Learning for Reasoning in Language ModelsLLM reasoning → Reinforcement learning for reasoning
  31. Mitigating Gender Bias via Fostering Exploratory Thinking in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  32. LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving ScenariosEnd-to-end autonomous driving → Large language models for driving
  33. FB-RAG: Improving RAG with Forward and Backward LookupRetrieval-augmented generation → RAG pipeline design and evaluation
  34. CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  35. Shape it Up! Restoring LLM Safety during FinetuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  36. Tropical Attention: Neural Algorithmic Reasoning for Combinatorial AlgorithmsLLM reasoning → Test-time compute and efficient thinking
  37. Next Token Perception Score: Analytical Assessment of your LLM Perception SkillsMechanistic interpretability → SAE features and their applications
  38. OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image ReasoningLLM reasoning → Multimodal reasoning
  39. DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World ChangesRetrieval-augmented generation → RAG robustness and adaptive retrieval
  40. Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial PromptingLLM safety and security → Machine unlearning
  41. TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  42. Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFNLLM reasoning → Prompting and chain-of-thought reasoning
  43. LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector SearchRetrieval-augmented generation → Vector search and ANN indexes
  44. MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  45. MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  46. RAP: Runtime Adaptive Pruning for LLM InferenceEfficient LLM inference and serving → Early exit and edge inference
  47. Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial RelationsLLM reasoning → Spatial and embodied reasoning
  48. Dynamic Token Reweighting for Robust Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  49. GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement LearningLLM reasoning → Multimodal reasoning
  50. ARB: A Comprehensive Arabic Multimodal Reasoning BenchmarkLLM reasoning → Multimodal reasoning +1
  51. CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention MechanismsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  52. Let Androids Dream of Electric Sheep: A Human-Inspired Image Implication Understanding and Reasoning FrameworkLLM reasoning → Multimodal reasoning
  53. SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking RewardLLM reasoning → Reinforcement learning for reasoning +2
  54. Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPOLLM reasoning → Reinforcement learning for reasoning +1
  55. Interactive Post-Training for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  56. Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  57. When Are Concepts Erased From Diffusion Models?Diffusion models → Robustness, privacy and adversarial aspects
  58. SpatialScore: Towards Comprehensive Evaluation for Spatial IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement LearningRetrieval-augmented generation → Agentic RAG, agents and memory
  60. Guided Diffusion Sampling on Function Spaces with Applications to PDEsDiffusion models → Inverse problems and image restoration
  61. Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?LLM reasoning → Reasoning benchmarks and evaluation
  62. X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference OptimizationLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  64. R2ec: Towards Large Recommender Models with ReasoningLLM reasoning → LLM reasoning for recommendation
  65. Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel DecodingMultimodal LLMs / vision-language models → Image editing and quality assessment +2
  66. MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic PlanningLLM agents and tool use → Tool learning and function calling
  68. UFT: Unifying Supervised and Reinforcement Fine-TuningLLM reasoning → Reinforcement learning for reasoning
  69. Beyond Correlation: Towards Causal Large Language Model Agents in BiomedicineLLM agents and tool use → Medical and scientific domain agents
  70. Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose InteractionDiffusion models → 3D, point cloud and scene generation
  71. Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
  72. Incorporating Visual Correspondence into Diffusion Model for Virtual Try-OnDiffusion models → 3D, point cloud and scene generation
  73. Creatively Upscaling Images with Global-Regional PriorsDiffusion models → Diffusion foundations and sampling
  74. OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual ReasoningLLM reasoning → Multimodal reasoning
  75. 3D Equivariant Visuomotor Policy Learning via Spherical ProjectionDiffusion models → Diffusion and flow policies for robotics
  76. MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  77. Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  78. Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language ModelsLLM safety and security → Prompt injection and agent security
  79. On Multilingual Encoder Language Model Compression for Low-Resource LanguagesKnowledge distillation → Knowledge distillation for LLMs
  80. Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  81. MixAT: Combining Continuous and Discrete Adversarial Training for LLMsLLM safety and security → Jailbreaking
  82. AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic ScenariosLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. In-Context Watermarks for Large Language ModelsLLM safety and security → Watermarking generated content and models
  84. LLaDA-V: Large Language Diffusion Models with Visual Instruction TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  85. Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context ReasoningLLM reasoning → Spatial and embodied reasoning
  86. Latent Principle Discovery for Language Model Self-ImprovementSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  87. Risk-Averse Reinforcement Learning with Itakura-Saito LossDeep reinforcement learning methods → RL theory and sample complexity
  88. Backdoor Cleaning without External Guidance in MLLM Fine-tuningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  89. RealEngine: Simulating Autonomous Driving in Realistic ContextWorld models → World models for autonomous driving +1
  90. FlashBack: Consistency Model-Accelerated Shared AutonomyDiffusion models → Diffusion and flow policies for robotics
  91. Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?LLM reasoning → Knowledge- and tool-augmented reasoning
  92. T2I-ConBench: Text-to-Image Benchmark for Continual Post-trainingDiffusion models → Image generation, text-to-image and editing
  93. MPO: Multilingual Safety Alignment via Reward Gap OptimizationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  94. Training-Free Efficient Video Generation via Dynamic Token CarvingDiffusion models → Video generation
  95. Efficient Online RL Fine Tuning with Offline Pre-trained Policy OnlyOffline RL and imitation learning from data → Offline RL algorithms +1
  96. Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  97. Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph WalksLLM reasoning → Knowledge- and tool-augmented reasoning +1
  98. LaViDa: A Large Diffusion Language Model for Multimodal UnderstandingLLM reasoning → Multimodal reasoning +3
  99. R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and SearchLLM reasoning → Test-time compute and efficient thinking
  100. SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory SynthesisLLM reasoning → Knowledge- and tool-augmented reasoning +1
All 635
  1. Strategically Linked Decisions in Long-Term Planning and Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  2. From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical VisualizationLLM reasoning → Multimodal reasoning +2
  3. Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMsLLM safety and security → Machine unlearning
  4. GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI AgentLLM agents and tool use → GUI and mobile agents
  5. KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  6. DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based RecommendationLLM reasoning → LLM reasoning for recommendation
  7. Two-way Evidence self-Alignment based Dual-Gated Reasoning EnhancementLLM reasoning → Reasoning benchmarks and evaluation
  8. SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  9. A modular framework for automated evaluation of procedural content generation in serious games with deep reinforcement learning agentsDeep reinforcement learning methods → RL for games and combinatorial optimization
  10. Learning Beyond Limits: Multitask Learning and Synthetic Data for Low-Resource Canonical Morpheme SegmentationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  11. SEED: Speaker Embedding Enhancement Diffusion ModelDiffusion models → Audio, speech and music
  12. REOBench: Benchmarking Robustness of Earth Observation Foundation ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  13. REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion TrainingDiffusion models → Diffusion foundations and sampling
  14. Learning Flexible Forward Trajectories for Masked Molecular DiffusionDiffusion models → Flow matching, time series and science
  15. Enter the Void - Planning to Seek Entropy When Reward is ScarceWorld models → Latent dynamics models and model-based RL +1
  16. CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  17. Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  18. RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal OutputsLLM reasoning → Multimodal reasoning
  19. Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM JailbreaksLLM safety and security → Jailbreaking
  20. Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  21. Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-TuningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  22. PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning ProjectsOffline RL and imitation learning from data → Offline RL algorithms
  23. Meta-reinforcement learning with minimum attentionDeep reinforcement learning methods → Deep RL algorithms and representations
  24. Secure LLM Fine-Tuning via Safety-Aware ProbingLLM safety and security → Safety alignment, refusal and guardrails
  25. Maximum Total Correlation Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  26. Efficient Image Restoration with State-Dependent Forward DiffusionDiffusion models → Inverse problems and image restoration
  27. LLM Fingerprinting via Semantically Conditioned WatermarksLLM safety and security → Watermarking generated content and models
  28. Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  29. MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language ModelsLLM agents and tool use → Tool learning and function calling
  30. One-Step Diffusion-Based Image Compression with Semantic DistillationDiffusion models → Diffusion for compression and wireless
  31. SPaRC: A Spatial Pathfinding Reasoning ChallengeLLM reasoning → Spatial and embodied reasoning
  32. R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOLLM reasoning → Multimodal reasoning +1
  33. CoNav: Collaborative Cross-Modal Reasoning for Embodied NavigationLLM reasoning → Spatial and embodied reasoning
  34. Can reasoning models comprehend mathematical problems in Chinese ancient texts? An empirical study based on data from Suanjing ShishuLLM reasoning → Mathematical reasoning
  35. Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  36. Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  37. From Evaluation to Defense: Advancing Safety in Video Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
  38. BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled OptimizationVision-language-action models → Safety and adversarial attacks +1
  39. SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine TranslationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training +1
  40. Steering Large Language Models for Machine Translation PersonalizationMechanistic interpretability → Activation steering methods
  41. From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference AlignmentLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  42. O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question AnsweringLLM agents and tool use → Web, search, and research agents
  43. How Ensembles of Distilled Policies Improve Generalisation in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  44. Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  45. EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human ActionsLLM agents and tool use → Web, search, and research agents
  46. Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM FinetuningLLM safety and security → Jailbreaking
  47. ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic ContextsLLM reasoning → Reasoning benchmarks and evaluation
  48. CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-TuningLLM safety and security → Safety alignment, refusal and guardrails
  49. Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel PlanningLLM agents and tool use → Agent threats, guardrails and governance
  50. Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning ChainsLLM reasoning → Test-time compute and efficient thinking
  51. SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent DiffusionDiffusion models → 3D, point cloud and scene generation
  52. DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionLLM safety and security → Watermarking generated content and models
  53. Joint Relational Database Generation via Graph-Conditional Diffusion ModelsDiffusion models → Flow matching, time series and science
  54. EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic MaintenanceMechanistic interpretability → Activation steering methods
  55. CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  56. ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  57. Recursive Offloading for LLM Serving in Multi-tier NetworksEfficient LLM inference and serving → Serving systems and request scheduling
  58. Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language ModelsEnd-to-end autonomous driving → Large language models for driving
  59. ALTo: Adaptive-Length Tokenizer for Autoregressive Mask GenerationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  60. Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  61. Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  62. Benchmarking Retrieval-Augmented Multimodal Generation for Document Question AnsweringRetrieval-augmented generation → Multimodal RAG
  63. MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and ReasoningLLM reasoning → Multimodal reasoning +1
  64. PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLMDiffusion models → Video generation
  65. Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster EventsLLM agents and tool use → Social simulation and multi-agent debate
  66. The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  67. Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language ModelsLLM reasoning → Reasoning for agents, planning and code +2
  68. Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender SystemsLLM agents and tool use → Agentic recommender systems
  69. Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution ApproachWorld models → World models for language agents
  70. WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
  71. Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  72. Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  73. Mitigating Hallucinations in Vision-Language Models through Image-Guided Head SuppressionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  74. Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  75. FREESON: Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTSLLM reasoning → Knowledge- and tool-augmented reasoning +1
  76. From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  77. Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario GamesLLM reasoning → Reinforcement learning for reasoning
  78. AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  79. Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)World models → World models for autonomous driving +3
  80. VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous DrivingWorld models → World models for autonomous driving +2
  81. PCMamba: Physics-Informed Cross-Modal State Space Model for Dual-Camera Compressive Hyperspectral ImagingState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  82. SATURN: SAT-based Reinforcement Learning to Unleash LLMs ReasoningLLM reasoning → Reinforcement learning for reasoning
  83. Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation SystemsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  84. A collaborative constrained graph diffusion model for the generation of realistic synthetic moleculesDiffusion models → Flow matching, time series and science
  85. Style Transfer with Diffusion Models for Synthetic-to-Real Domain AdaptationDiffusion models → Image generation, text-to-image and editing
  86. Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory UtilizationLLM agents and tool use → Agent memory systems
  87. ChemMLLM: Chemical Multimodal Large Language ModelMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  88. AdaSTaR: Adaptive Data Sampling for Training Self-Taught ReasonersLLM reasoning → Test-time compute and efficient thinking +1
  89. Incentivizing Dual Process Thinking for Efficient Large Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
  90. EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action PruningLLM reasoning → Test-time compute and efficient thinking
  91. SAMba-UNet: SAM2-Mamba UNet for Cardiac MRI in Medical Robotic PerceptionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  92. Flow Matching based Sequential Recommender ModelDiffusion models → Diffusion recommenders
  93. ToDi: Token-wise Distillation via Fine-Grained Divergence ControlKnowledge distillation → Knowledge distillation for LLMs
  94. Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QALLM reasoning → Knowledge- and tool-augmented reasoning +1
  95. No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal DiscoveryLLM agents and tool use → Medical and scientific domain agents
  96. ARPO:End-to-End Policy Optimization for GUI Agents with Experience ReplayLLM agents and tool use → GUI and mobile agents
  97. HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  98. DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous DrivingVision-language-action models → VLA for autonomous driving +2
  99. Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  100. IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm DetectionLLM reasoning → Multimodal reasoning
  101. Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language ModelsLLM safety and security → Machine unlearning
  102. Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization StrategiesOffline RL and imitation learning from data → Safe offline RL
  103. Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked CiphersLLM reasoning → Reasoning for agents, planning and code +1
  104. DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  105. Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  106. LIFEBench: Evaluating Length Instruction Following in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  107. Reward-Aware Proto-Representations in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  108. Memorization or Reasoning? Exploring the Idiom Understanding of LLMsLLM reasoning → Reasoning benchmarks and evaluation
  109. NQKV: A KV Cache Quantization Scheme Based on Normal Distribution CharacteristicsEfficient LLM inference and serving → KV cache quantization
  110. An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception CapabilityMultimodal LLMs / vision-language models → Multimodal emotion understanding
  111. VLM-R3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-ThoughtLLM reasoning → Multimodal reasoning
  112. SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language ModelsMechanistic interpretability → SAE features and their applications
  113. SafeKey: Amplifying Aha-Moment Insights for Safety ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  114. Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  115. Erased or Dormant? Rethinking Concept Erasure Through ReversibilityDiffusion models → Robustness, privacy and adversarial aspects
  116. Tactile-based Reinforcement Learning for Adaptive Grasping under Observation UncertaintiesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  117. TRAIL: Transferable Robust Adversarial Images via Latent diffusionDiffusion models → Robustness, privacy and adversarial aspects
  118. KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set OptimizationEfficient LLM inference and serving → Speculative decoding
  119. Training-Free Reasoning and Reflection in MLLMsLLM reasoning → Multimodal reasoning
  120. When VLMs Meet Image Classification: Test Sets Renovation via Missing Label IdentificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  121. Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley ValueLLM safety and security → Machine unlearning
  122. Steering LVLMs via Sparse Autoencoder for Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  123. RLKD: Distilling LLMs' Reasoning via Reinforcement LearningLLM reasoning → Prompting and chain-of-thought reasoning +1
  124. Sudoku-Bench: Evaluating creative reasoning with Sudoku variantsLLM reasoning → Reasoning benchmarks and evaluation
  125. HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  126. LLMs Are Not Scorers: Rethinking MT Evaluation with Generation-Based MethodsLLM reasoning → Reasoning benchmarks and evaluation
  127. Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  128. Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  129. LLM-Powered AI Agent Systems and Their Applications in IndustryLLM agents and tool use → General LLM agent frameworks and benchmarks
  130. Source Separation by Flow MatchingDiffusion models → Audio, speech and music
  131. Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural LanguageLLM reasoning → Reasoning benchmarks and evaluation
  132. Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use ToolsLLM agents and tool use → General LLM agent frameworks and benchmarks
  133. Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  134. Continually Self-Improving Language Models for Bariatric Surgery Question--AnsweringSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  135. BioDSA-1K: Benchmarking Data Science Agents for Biomedical ResearchLLM agents and tool use → Medical and scientific domain agents
  136. Reinforcement Learning for Stock TransactionsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  137. Cosmos: A CXL-Based Full In-Memory System for Approximate Nearest Neighbor SearchRetrieval-augmented generation → Vector search and ANN indexes
  138. OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratesDiffusion models → Diffusion for compression and wireless
  139. Date Fragments: A Hidden Bottleneck of Tokenization for Temporal ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  140. Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software DevelopmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  141. CDST: Color Disentangled Style Transfer for Universal Style Reference Customization
  142. MARch'e: Fast Masked Autoregressive Image Generation with Cache-Aware Attention
  143. Human-like Forgetting Curves in Deep Neural Networks
  144. EMERGENT: Efficient and Manipulation-resistant Matching using GFlowNets
  145. Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelines
  146. Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset
  147. Impact, Causation and Prediction of Socio-Academic and Economic Factors in Exam-centric Student Evaluation Measures using Machine Learning and Causal Analysis
  148. Physics-Informed Neural Networks for Vessel Trajectory Prediction: Learning Time-Discretized Kinematic Dynamics via Finite Differences
  149. Constant Bit-size Transformers Are Turing Complete
  150. STRCMP: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
  151. xInv: Explainable Optimization of Inverse Problems
  152. PolyMicros: Bootstrapping a Foundation Model for Polycrystalline Material Structure
  153. Adaptive Composition of Machine Learning as a Service (MLaaS) for IoT Environments
  154. Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data
  155. NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs
  156. Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation
  157. Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
  158. Applying MambaAttention, TabPFN, and TabTransformers to Classify SAE Automation Levels in Crashes
  159. Learning Normal Patterns in Musical Loops
  160. Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
  161. Do DeepFake Attribution Models Generalize?
  162. Cold Start Problem: An Experimental Study of Knowledge Tracing Models with New Students
  163. AIDRIN 2.0: A Framework to Assess Data Readiness for AI
  164. BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text
  165. The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models
  166. A Multi-Head Attention Soft Random Forest for Interpretable Patient No-Show Prediction
  167. Ocular Authentication: Fusion of Gaze and Periocular Modalities
  168. A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety
  169. TI-DeepONet: Learnable Time Integration for Stable Long-Term Extrapolation
  170. Conformal Predictive Distributions for Order Fulfillment Time Forecasting
  171. Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering
  172. Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis
  173. SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use
  174. ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training
  175. FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding
  176. Transformer brain encoders explain human high-level visual responses
  177. Game-invariant Features Through Contrastive and Domain-adversarial Learning
  178. GPT Editors, Not Authors: The Stylistic Footprint of LLMs in Academic Preprints
  179. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
  180. Comparative Evaluation of Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2
  181. Optimizing Image Capture for Computer Vision-Powered Taxonomic Identification and Trait Recognition of Biodiversity Specimens
  182. Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays
  183. Decoupling Representation and Learning in Genetic Programming: the LaSER Approach
  184. Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
  185. Wavelet Probabilistic Recurrent Convolutional Network for Multivariate Time Series Classification
  186. Refusal Direction is Universal Across Safety-Aligned Languages
  187. Understanding the Implicit Regularization of Gradient Descent in Over-parameterized Models
  188. Statistical Inference for Online Algorithms
  189. SELF: Self-Extend the Context Length With Logistic Growth Function
  190. Graph Data Selection for Domain Adaptation: A Model-Free Approach
  191. Optimal Transport with Heterogeneously Missing Data
  192. Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation
  193. Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine
  194. Attention with Trained Embeddings Provably Selects Important Tokens
  195. Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
  196. Comparator-Adaptive Phi-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games
  197. CaseReportBench: An LLM Benchmark Dataset for Dense Information Extraction in Clinical Case Reports
  198. The Rise of Parameter Specialization for Knowledge Storage in Large Language Models
  199. Approach to Finding a Robust Deep Learning Model
  200. Extending Dataset Pruning to Object Detection: A Variance-based Approach
  201. Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis
  202. CHAOS: Chart Analysis with Outlier Samples
  203. Semantic-Aware Interpretable Multimodal Music Auto-Tagging
  204. Automated Capability Evaluation of Foundation Models
  205. Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation
  206. REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge
  207. Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts
  208. MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph
  209. Assessing the generalization performance of SAM for ureteroscopy scene understanding
  210. Content Moderation in TV Search: Balancing Policy Compliance, Relevance, and User Experience
  211. Liouville PDE-based sliced-Wasserstein flow
  212. Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
  213. A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data
  214. LengthLogD: A Length-Stratified Ensemble Framework for Enhanced Peptide Lipophilicity Prediction via Multi-Scale Feature Integration
  215. CRG Score: A Distribution-Aware Clinical Metric for Radiology Report Generation
  216. A Toolkit for Compliance, a Toolkit for Justice: Drawing on Cross-sectoral Expertise to Develop a Pro-justice EU AI Act Toolkit
  217. PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG
  218. Can Large Language Models Design Biological Weapons? Evaluating Moremi Bio
  219. Bayesian Optimization for Enhanced Language Models: Optimizing Acquisition Functions
  220. Efficient Training of Neural SDEs Using Stochastic Optimal Control
  221. Large Language Models for Predictive Analysis: How Far Are They?
  222. LLM Agents for Interactive Exploration of Historical Cadastre Data: Framework and Application to Venice
  223. LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
  224. Evaluating the Performance of Nigerian Lecturers using Multilayer Perceptron
  225. MetaSTH-Sleep: Towards Effective Few-Shot Sleep Stage Classification for Health Management with Spatial-Temporal Hypergraph Enhanced Meta-Learning
  226. Fashion Industry in the Age of Generative Artificial Intelligence and Metaverse: A systematic Review
  227. Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMs
  228. EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs
  229. Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands
  230. When can isotropy help adapt LLMs' next word prediction to numerical domains?
  231. LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
  232. Learning Probabilities of Causation with Mask-Augmented Data
  233. Relative Bias: A Comparative Framework for Quantifying Bias in LLMs
  234. Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space
  235. Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  236. Deep mineralogical segmentation of thin section images based on QEMSCAN maps
  237. CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
  238. Sufficient conditions for offline reactivation in recurrent neural networks
  239. PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association
  240. Seeing through Satellite Images at Street Views
  241. Critical Points of Random Neural Networks
  242. A Unified Framework for Simultaneous Parameter and Function Discovery in Differential Equations
  243. Native Segmentation Vision Transformers
  244. PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
  245. An Effective Training Framework for Light-Weight Automatic Speech Recognition Models
  246. Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
  247. LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding
  248. HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
  249. SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
  250. VeriFastScore: Speeding up long-form factuality evaluation
  251. From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
  252. UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
  253. CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark
  254. Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
  255. BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation
  256. ICYM2I: The illusion of multimodal informativeness under missingness
  257. FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
  258. NY Real Estate Racial Equity Analysis via Applied Machine Learning
  259. Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
  260. FoMoH: A clinically meaningful foundation model evaluation for structured electronic health records
  261. InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
  262. SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing
  263. The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm
  264. PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues
  265. TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation
  266. UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation
  267. Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype
  268. DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
  269. Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
  270. Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting
  271. Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
  272. Power-Law Decay Loss for Large Language Model Finetuning: A Theory Perspective
  273. Identifying, Evaluating, and Mitigating Risks of AI Thought Partnerships
  274. Structure-Aligned Protein Language Model
  275. Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs
  276. Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference
  277. PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
  278. Tracking the Flight: Exploring a Computational Framework for Analyzing Escape Responses in Plains Zebra (Equus quagga)
  279. CASTILLO: Characterizing Response Length Distributions of Large Language Models
  280. How high is `high'? Rethinking the roles of dimensionality in topological data analysis and manifold learning
  281. Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings
  282. A Multi-Step Comparative Framework for Anomaly Detection in IoT Data Streams
  283. Comparative analysis of subword tokenization approaches for Indian languages
  284. Conditional Panoramic Image Generation via Masked Autoregressive Modeling
  285. GCAL: Adapting Graph Models to Evolving Domain Shifts
  286. Redefining Clustered Federated Learning for System Identification: The Path of ClusterCraft
  287. Nested Named Entity Recognition as Single-Pass Sequence Labeling
  288. ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning
  289. Understanding and Analyzing Inappropriately Targeting Language in Online Discourse: A Comparative Annotation Study
  290. Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
  291. Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
  292. Contextual Learning for Stochastic Optimization
  293. LLM-Based Emulation of the Radio Resource Control Layer: Towards AI-Native RAN Protocols
  294. Character-Centered Dialogue Generation from Scene-Level Prompts
  295. Image Quality Assessment for Embodied AI
  296. Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?
  297. Dynamic Reservoir Computing with Physical Neuromorphic Networks
  298. Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining
  299. Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalities
  300. V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation
  301. Cohort-Based Active Modality Acquisition
  302. Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
  303. FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
  304. Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
  305. Fuzzy Information Evolution with Three-Way Decision in Social Network Group Decision-Making
  306. Single Domain Generalization for Few-Shot Counting via Universal Representation Matching
  307. IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models
  308. Mitigating Overfitting in Medical Imaging: Self-Supervised Pretraining vs. ImageNet Transfer Learning for Dermatological Diagnosis
  309. Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review
  310. Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval
  311. Multi-Output Gaussian Processes for Graph-Structured Data
  312. Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation
  313. Revenue Optimization with Price-Sensitive and Interdependent Demand
  314. TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
  315. Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
  316. Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
  317. Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting
  318. Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
  319. Masked Conditioning for Deep Generative Models
  320. Advancing Brainwave Modeling with a Codebook-Based Foundation Model
  321. Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification
  322. The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
  323. Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor
  324. Improved generalization bounds for binary linear classification via isoperimetry
  325. Training Long-Context LLMs Efficiently via Chunk-wise Optimization
  326. SEDD-PCC: A Single Encoder-Dual Decoder Framework For End-To-End Learned Point Cloud Compression
  327. KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
  328. An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
  329. Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
  330. EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
  331. Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
  332. On the use of Graphs for Satellite Image Time Series
  333. Learning Genomic Structure from k-mers
  334. Semantic Compression of 3D Objects for Open and Collaborative Virtual Worlds
  335. On the Out-of-Distribution Generalization of Self-Supervised Learning
  336. Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge
  337. Quantum Feature Optimization for Enhanced Clustering of Blockchain Transaction Data
  338. BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
  339. ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming
  340. HyBattNet: Hybrid Framework for Predicting the Remaining Useful Life of Lithium-Ion Batteries
  341. A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP
  342. SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images
  343. Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control
  344. Unsupervised Network Anomaly Detection with Autoencoders and Traffic Images
  345. Stochastic Forward-Forward Learning through Representational Dimensionality Compression
  346. Collaboration among Multiple Large Language Models for Medical Question Answering
  347. SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving
  348. Learning non-equilibrium diffusions with Schr"odinger bridges: from exactly solvable to simulation-free
  349. Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity
  350. Multivariate Latent Recalibration for Conditional Normalizing Flows
  351. WikiDBGraph: A Data Management Benchmark Suite for Collaborative Learning over Database Silos
  352. Towards Texture- And Shape-Independent 3D Keypoint Estimation in Birds
  353. MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries
  354. SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding
  355. Background Matters: A Cross-view Bidirectional Modeling Framework for Semi-supervised Medical Image Segmentation
  356. Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports
  357. CausalDynamics: A large-scale benchmark for structural discovery of dynamical causal models
  358. Open and Sustainable AI: challenges, opportunities and the road ahead in the life sciences (October 2025 -- Version 2)
  359. MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation
  360. Decoupled Geometric Parameterization and its Application in Deep Homography Estimation
  361. Safe Uncertainty-Aware Learning of Robotic Suturing
  362. Temporal Object Captioning for Street Scene Videos from LiDAR Tracks
  363. What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse
  364. Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering
  365. Training on Plausible Counterfactuals Removes Spurious Correlations
  366. Large Language Model-Empowered Interactive Load Forecasting
  367. From Local Patterns to Global Understanding: Cross-Stock Trend Integration for Enhanced Predictive Modeling
  368. URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
  369. M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion
  370. A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices
  371. Auto-nnU-Net: Towards Automated Medical Image Segmentation
  372. Towards Coordinate- and Dimension-Agnostic Machine Learning for Partial Differential Equations
  373. Incremental Sequence Classification with Temporal Consistency
  374. Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulation
  375. TextureSAM: Towards a Texture Aware Foundation Model for Segmentation
  376. Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
  377. Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
  378. HOFT: Householder Orthogonal Fine-tuning
  379. Large Language Models Are Still Misled by Simple Bias Ensembles
  380. Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs
  381. CUB: Benchmarking Context Utilisation Techniques for Language Models
  382. Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
  383. AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios
  384. Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting
  385. Beyond Face Swapping: A Diffusion-Based Digital Human Benchmark for Multimodal Deepfake Detection
  386. Edge-First Language Model Inference: Models, Metrics, and Tradeoffs
  387. Relevance for Stability of Verification Status of a Set of Arguments in Incomplete Argumentation Frameworks (with Proofs)
  388. Sparse Activation Editing for Reliable Instruction Following in Narratives
  389. Smaller, Smarter, Closer: The Edge of Collaborative Generative AI
  390. Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
  391. Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority Topics
  392. LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing
  393. Generative Prior-Guided Neural Interface Reconstruction for 3D Electrical Impedance Tomography
  394. InspectionV3: Enhancing Tobacco Quality Assessment with Deep Convolutional Neural Networks for Automated Workshop Management
  395. Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
  396. Minimizing the energy depletion in wireless rechargeable sensor networks using bi-level metaheuristic charging schemes
  397. Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
  398. Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration
  399. Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery
  400. ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
  401. Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
  402. Conf-GNNRec: Quantifying and Calibrating the Prediction Confidence for GNN-based Recommendation Methods
  403. AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer
  404. University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection
  405. CMRINet: Joint Groupwise Registration and Segmentation for Cardiac Function Quantification from Cine-MRI
  406. TAT-VPR: Ternary Adaptive Transformer for Dynamic and Efficient Visual Place Recognition
  407. MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection
  408. Ranked Entropy Minimization for Continual Test-Time Adaptation
  409. Joint Flow And Feature Refinement Using Attention For Video Restoration
  410. AutoMCQ -- Automatically Generate Code Comprehension Questions using GenAI
  411. I2G: Generating Instructional Illustrations via Text-Conditioned Diffusion
  412. Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment
  413. Exploring the Relationship Between Diversity and Quality in Ad Text Generation
  414. Pose-invariant face recognition via feature-space pose frontalization
  415. On the reliability of feature attribution methods for speech classification
  416. Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach
  417. AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systems
  418. Sketchy Bounding-box Supervision for 3D Instance Segmentation
  419. Resource for Error Analysis in Text Simplification: New Taxonomy and Test Collection
  420. Serious Games: Human-AI Interaction, Evolution, and Coevolution
  421. Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space
  422. Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models
  423. MAGE: A Multi-task Architecture for Gaze Estimation with an Efficient Calibration Module
  424. PaTH Attention: Position Encoding via Accumulating Householder Transformations
  425. Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey
  426. DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
  427. Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition
  428. AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training
  429. Neuromorphic-based metaheuristics: A new generation of low power, low latency and small footprint optimization algorithms
  430. Admission Control of Quasi-Reversible Queueing Systems: Optimization and Reinforcement Learning
  431. Dysfluent WFST: A Framework for Zero-Shot Speech Dysfluency Transcription and Detection
  432. Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization
  433. Graph Attention Network for Optimal User Association in Wireless Networks
  434. A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning
  435. Improving Chemical Understanding of LLMs via SMILES Parsing
  436. Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification
  437. FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design
  438. Panoptic Captioning: An Equivalence Bridge for Image and Text
  439. Understanding Differential Transformer Unchains Pretrained Self-Attentions
  440. Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing
  441. SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers
  442. High-Dimensional Private Linear Regression with Optimal Rates
  443. CLEAR: A Clinically-Grounded Tabular Framework for Radiology Report Evaluation
  444. From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
  445. Efficient Motion Prompt Learning for Robust Visual Tracking
  446. Learning novel representations of variable sources from multi-modal textitGaia data via autoencoders
  447. FreshRetailNet-50K: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
  448. SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models
  449. NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
  450. Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
  451. Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions
  452. Paired and Unpaired Image to Image Translation using Generative Adversarial Networks
  453. Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
  454. PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
  455. Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
  456. Large-Scale Bayesian Tensor Reconstruction via Approximate Message Passing
  457. INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
  458. Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Space
  459. Self-Classification Enhancement and Correction for Weakly Supervised Object Detection
  460. Fairness under Competition
  461. Multimodal Generative AI for Story Point Estimation in Software Development
  462. Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse
  463. Efficient Prototype Consistency Learning in Medical Image Segmentation via Joint Uncertainty and Data Augmentation
  464. MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing
  465. Spontaneous Speech Variables for Evaluating LLMs Cognitive Plausibility
  466. How do Scaling Laws Apply to Knowledge Graph Engineering Tasks? The Impact of Model Size on Large Language Model Performance
  467. Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
  468. LINEA: Fast and Accurate Line Detection Using Scalable Transformers
  469. All You Need is "Leet": Evading Hate-speech Detection AI
  470. Small-to-Large Generalization: Data Influences Models Consistently Across Scale
  471. Dialogue in Resonance: An Interactive Music Piece for Piano and Real-Time Automatic Transcription System
  472. Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics
  473. DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor
  474. Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces
  475. Graph-Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry
  476. Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control
  477. Graph Neural Network-Based Collaborative Perception for Adaptive Scheduling in Distributed Systems
  478. Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models
  479. Generalized Power Priors for Improved Bayesian Inference with Historical Data
  480. MuseScorer: Idea Originality Scoring At Scale
  481. CT-Agent: A Multimodal-LLM Agent for 3D CT Radiology Question Answering
  482. A Shape-Aware Total Body Photography System for In-focus Surface Coverage Optimization
  483. Explain Less, Understand More: Data-Efficient Personalization of Reader-Dependent Jargons
  484. Realistic Evaluation of TabPFN v2 in Open Environments
  485. MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
  486. MADCluster: Model-agnostic Anomaly Detection with Self-supervised Clustering Network
  487. Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
  488. LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead
  489. Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning
  490. A Scalable Hierarchical Intrusion Detection System for Internet of Vehicles
  491. Large Language Models based ASR Error Correction for Child Conversations
  492. AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
  493. MedCFVQA: A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering
  494. Using Echo-State Networks to Reproduce Rare Events in Chaotic Systems
  495. Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
  496. Velocity Completion Task and Method for Event-based Player Positional Data in Soccer
  497. SEM: Enhancing Spatial Understanding for Robust Robot Manipulation
  498. SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet
  499. Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare
  500. The Language of Interoception: Examining Embodiment and Emotion Through a Corpus of Body Part Mentions
  501. EasyInsert: A Data-Efficient and Generalizable Insertion Policy
  502. Understanding Generative AI Capabilities in Everyday Image Editing Tasks
  503. Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation
  504. Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
  505. Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression
  506. QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
  507. Automated Feedback Loops to Protect Text Simplification with Generative AI from Information Loss
  508. When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction
  509. RE-TRIP : Reflectivity Instance Augmented Triangle Descriptor for 3D Place Recognition
  510. Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task
  511. Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
  512. EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios
  513. Why Can Accurate Models Be Learned from Inaccurate Annotations?
  514. Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention
  515. Integral Imprecise Probability Metrics
  516. BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
  517. Compressing Human Body Video with Interactive Semantics: A Generative Approach
  518. NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
  519. Exponential Convergence of CAVI for Bayesian PCA
  520. GMatch: A Lightweight, Geometry-Constrained Keypoint Matcher for Zero-Shot 6DoF Pose Estimation in Robotic Grasp Tasks
  521. Multimodal Online Federated Learning with Modality Missing in Internet of Things
  522. Interpretable Machine Learning for Macro Alpha: A News Sentiment Case Study
  523. Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs
  524. Machine Learning the 6d Supergravity Landscape
  525. Generative Graph Pattern Machine
  526. Robust Invariant Representation Learning by Distribution Extrapolation
  527. KoBALT: Korean Benchmark For Advanced Linguistic Tasks
  528. Semiotic Reconstruction of Destination Expectation Constructs An LLM-Driven Computational Paradigm for Social Media Tourism Analytics
  529. A Generic Framework for Conformal Fairness
  530. MPL: Multiple Programming Languages with Large Language Models for Information Extraction
  531. Towards Trustworthy Keylogger detection: A Comprehensive Analysis of Ensemble Techniques and Feature Selections through Explainable AI
  532. Dimension-adapted Momentum Outscales SGD
  533. Developing Large Language Models for Clinical Research Using One Million Clinical Trials
  534. A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization
  535. Can AI Read Between The Lines? Benchmarking LLMs On Financial Nuance