mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 29 Jan 2026

655 papers

  1. Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic ToolchainsLLM reasoning → Multimodal reasoning +2
  2. Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  3. PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot ReadingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  4. Towards Agentic Intelligence for Materials ScienceLLM agents and tool use → Medical and scientific domain agents
  5. Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical StudyLLM agents and tool use → Software engineering coding agents
  6. ProDCARL: Reinforcement Learning-Aligned Diffusion Models for De Novo Antimicrobial Peptide DesignDiffusion models → Flow matching, time series and science +1
  7. ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  8. Reversible Diffusion Decoding for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  9. Jailbreaks on Vision Language Model via Multimodal ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  10. SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  11. Specialists or Generalists? Multi-Agent and Single-Agent LLMs for Essay GradingLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. SP^2DPO: An LLM-assisted Semantic Per-Pair DPO GeneralizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. Purely Agent-Driven Black-Box Optimization for Biological DesignLLM agents and tool use → Medical and scientific domain agents
  14. MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity AssessmentLLM reasoning → Reasoning benchmarks and evaluation +1
  15. The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed SamplesLLM safety and security → Machine unlearning
  16. Recoverability Has a Law: The ERR Measure for Tool-Augmented AgentsLLM agents and tool use → Tool learning and function calling
  17. Quantum-Inspired Reinforcement Learning for Secure and Sustainable AIoT-Driven Supply Chain SystemsDeep reinforcement learning methods → Quantum reinforcement learning
  18. From Retrieving Information to Reasoning with AI: Exploring Different Interaction Modalities to Support Human-AI Coordination in Clinical Decision-MakingLLM reasoning → Clinical and biomedical applications
  19. Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?LLM reasoning → Reasoning benchmarks and evaluation
  20. Automatic Construction of Clinical Scoring Systems with LLM AgentsLLM agents and tool use → Medical and scientific domain agents
  21. Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc ReasoningLLM reasoning → Test-time compute and efficient thinking
  22. SCALAR: Quantifying Structural Hallucination, Consistency, and Reasoning Gaps in Materials Foundation ModelsLLM reasoning → Clinical and biomedical applications
  23. Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  24. BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow GenerationLLM agents and tool use → Software engineering coding agents
  25. Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent DebateLLM reasoning → Reasoning for agents, planning and code +1
  26. The Six Sigma Agent: Achieving Enterprise-Grade Reliability in LLM Systems Through Consensus-Driven Decomposed ExecutionLLM agents and tool use → Software engineering coding agents
  27. PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design ResearchLLM agents and tool use → Social simulation and multi-agent debate
  28. SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) ModelsDiffusion models → Diffusion foundations and sampling
  29. VMonarch: Efficient Video Diffusion Transformers with Structured AttentionDiffusion models → Video generation
  30. JAF: Judge Agent ForestLLM reasoning → Reasoning for agents, planning and code +1
  31. FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code GenerationLLM reasoning → Reasoning for agents, planning and code +1
  32. MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM WatermarkingLLM safety and security → Watermarking generated content and models
  33. Aligning Microscopic Vehicle and Macroscopic Traffic Statistics: Reconstructing Driving Behavior from Partial DataEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  34. A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST TaxonomyLLM safety and security → Jailbreaking
  35. Geometry without Position? When Positional Embeddings Help and Hurt Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  36. DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code GenerationLLM reasoning → Reasoning for agents, planning and code
  37. Lost in Space? Vision-Language Models Struggle with Relative Camera Pose EstimationLLM reasoning → Spatial and embodied reasoning +1
  38. What Lies Beneath: A Call for Distribution-based Visual Question & Answer DatasetsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  39. Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial ActionsDeep reinforcement learning methods → RL with diffusion and flow models
  40. Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause AnalysisLLM reasoning → Reasoning for agents, planning and code
  41. Causal Imitation Learning Under Measurement Error and Distribution ShiftOffline RL and imitation learning from data → Imitation learning methods
  42. Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with GengramRetrieval-augmented generation → Medical and biomedical RAG
  43. UEval: A Benchmark for Unified Multimodal GenerationLLM reasoning → Multimodal reasoning
  44. Exploring Reasoning Reward Model for AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  45. DynamicVLA: A Vision-Language-Action Model for Dynamic Object ManipulationVision-language-action models → 3D and spatial-aware VLA
  46. Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual IllusionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  47. DynaWeb: Model-Based Reinforcement Learning of Web AgentsWorld models → World models for language agents +2
  48. FineInstructions: Scaling Synthetic Instructions to Pre-Training ScaleSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  49. Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive InquirersLLM reasoning → Reasoning benchmarks and evaluation
  50. StepShield: When, Not Whether to Intervene on Rogue AgentsLLM safety and security → Prompt injection and agent security
  51. PI-Light: Physics-Inspired Diffusion for Full-Image RelightingDiffusion models → 3D, point cloud and scene generation
  52. World of Workflows: A Benchmark for Bringing World Models to Enterprise SystemsWorld models → World models for language agents
  53. SWE-Replay: Efficient Test-Time Scaling for Software Engineering AgentsLLM reasoning → Reasoning for agents, planning and code +1
  54. The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHRWorld models → Medical and surgical world models +1
  55. EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion TransformersDiffusion models → Audio, speech and music
  56. Creative Image Generation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  57. Prior-Informed Flow Matching for Graph ReconstructionDiffusion models → Flow matching, time series and science
  58. ECO: Quantized Training without Full-Precision Master WeightsMixture-of-experts → MoE large language models
  59. Boosting CVaR Policy Optimization with Quantile GradientsDeep reinforcement learning methods → RL theory and sample complexity
  60. RefAny3D: 3D Asset-Referenced Diffusion Models for Image GenerationDiffusion models → 3D, point cloud and scene generation
  61. Learning Transient Convective Heat Transfer with Geometry Aware World ModelsWorld models → Latent predictive world models
  62. Latent Adversarial Regularization for Offline Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  63. VTC-R1: Vision-Text Compression for Efficient Long-Context ReasoningLLM reasoning → Multimodal reasoning
  64. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  65. Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  66. G2-Reader: Dual Evolving Graphs for Multimodal Document QARetrieval-augmented generation → Multimodal RAG
  67. Learning to Dial-a-Ride: A Deep Graph Reinforcement Learning Approach to the Electric Dial-a-Ride ProblemDeep reinforcement learning methods → RL for energy, networks and operations
  68. SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network ControlDeep reinforcement learning methods → RL for energy, networks and operations
  69. Optimizing Agentic Workflows using Meta-toolsLLM agents and tool use → Software engineering coding agents
  70. Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  71. Holographic generative flows with AdS/CFTDiffusion models → Flow matching, time series and science
  72. Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End DrivingEnd-to-end autonomous driving → Generative simulation for driving
  73. Causal Autoregressive Diffusion Language ModelDiffusion models → Discrete and text diffusion
  74. Per-parameter Task Arithmetic for Unlearning in Large Language ModelsLLM safety and security → Machine unlearning
  75. Contrastive Representation Shaping for LLM UnlearningLLM safety and security → Machine unlearning
  76. CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World UncertaintyLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  78. Visual-Guided Key-Token Regularization for Multimodal Large Language Model UnlearningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  79. PocketDP3: Efficient Pocket-Scale 3D Visuomotor PolicyDiffusion models → Diffusion and flow policies for robotics
  80. Putting a Face to Forgetting: Continual Learning meets Mechanistic InterpretabilityMechanistic interpretability → SAE features and their applications
  81. Exploring Diverse Generation Paths via Inference-time Stiefel Activation SteeringMechanistic interpretability → Activation steering methods
  82. LANCER: LLM Reranking for Nugget CoverageRetrieval-augmented generation → Generation and context integration
  83. Causal World Modeling for Robot ControlWorld models → Embodied and robot world models +1
  84. Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM UnitsMechanistic interpretability → Knowledge and representations inside LLMs
  85. Geometry of Drifting MDPs with Path-Integral Stability CertificatesDeep reinforcement learning methods → RL theory and sample complexity
  86. Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force FieldsDiffusion models → Flow matching, time series and science
  87. Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  88. Learning Decentralized LLM Collaboration with Multi-Agent Actor CriticLLM agents and tool use → Reinforcement learning for LLM agents
  89. Supervised Mixture-of-Experts for Surgical Grasping and RetractionMixture-of-experts → MoE in reinforcement learning and robotics +1
  90. OVD: On-policy Verbal DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  91. How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design FactorsLLM agents and tool use → Web, search, and research agents
  92. ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language ModelsLLM agents and tool use → Tool learning and function calling
  93. Entropy-Based Dimension-Free Convergence and Loss-Adaptive Schedules for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  94. Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning CapabilitiesLLM reasoning → Knowledge- and tool-augmented reasoning
  95. AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision MakingLLM reasoning → Reasoning for agents, planning and code +1
  96. Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion ModelsDiffusion models → Inverse problems and image restoration
  97. Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  98. JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAGRetrieval-augmented generation → Agentic RAG, agents and memory +1
  99. VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment
  100. ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented GenerationLLM reasoning → Reinforcement learning for reasoning +1
All 655
  1. From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  2. TraceRouter: Robust Safety for Large Foundation Models via Path-Level InterventionMechanistic interpretability → Steering and probing for LLM safety
  3. Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video DiffusionDiffusion models → Video generation +1
  4. Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
  5. Improving Classifier-Free Guidance of Flow Matching via Manifold ProjectionDiffusion models → Diffusion foundations and sampling
  6. astra-langchain4j: Experiences Combining LLMs and Agent ProgrammingLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. LLM-Driven Scenario-Aware Planning for Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving
  8. WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web AgentsLLM reasoning → Reasoning for agents, planning and code +2
  9. On Forgetting and Stability of Score-based Generative modelsDiffusion models → Diffusion foundations and sampling
  10. MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-ExpertsMixture-of-experts → MoE for time series and graphs
  11. Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic ForgettingLLM agents and tool use → Multimodal and embodied agents
  12. Trajectory-Guided Diffusion for Foreground-Preserving Background Generation in Multi-Layer DocumentsDiffusion models → Image generation, text-to-image and editing
  13. Constrained Meta Reinforcement Learning with Provable Test-Time SafetyDeep reinforcement learning methods → Safe and constrained RL
  14. Embodied Task Planning via Graph-Informed Action Generation with Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  15. Test-Time Compute GamesLLM reasoning → Test-time compute and efficient thinking
  16. Generative Modeling of Discrete Data Using Geometric Latent SubspacesDiffusion models → Diffusion foundations and sampling
  17. Mil-SCORE: Benchmarking Long-Context Geospatial Reasoning and Planning in Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  18. CORE:Toward Ubiquitous 6G Intelligence Through Collaborative Orchestration of Large Language Model Agents Over Hierarchical EdgeLLM reasoning → Reasoning for agents, planning and code +1
  19. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric MethodsLLM reasoning → Multimodal reasoning +1
  20. Nonparametric LLM Evaluation from Preference DataLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  21. A Decomposable Forward Process in Diffusion Models for Time-Series ForecastingDiffusion models → Flow matching, time series and science
  22. Distribution-Aware Reward Estimation for Test-Time Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  23. Quantifying Retriever-Generator Alignment in RAG with Local ExplanationsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  24. BioAgent Bench: An AI Agent Evaluation Suite for BioinformaticsLLM agents and tool use → Medical and scientific domain agents
  25. CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  26. Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  27. Zonkey: A Hierarchical Diffusion Language Model with Differentiable Tokenization and Probabilistic AttentionDiffusion models → Discrete and text diffusion
  28. Language-based Trial and Error Falls Behind in the Era of ExperienceLLM agents and tool use → General LLM agent frameworks and benchmarks
  29. Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. When Does Predictive Inverse Dynamics Outperform Behavior Cloning?Offline RL and imitation learning from data → Imitation learning methods
  31. E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent MemoryLLM reasoning → Reasoning for agents, planning and code +1
  32. CoFreeVLA: Short-Horizon Collision-Free Dual-Arm Manipulation via Vision-Language-Action Model and Risk EstimationVision-language-action models → Human-video and latent-action pretraining
  33. TACLer: Tailored Curriculum Reinforcement Learning for Efficient ReasoningLLM reasoning → Reinforcement learning for reasoning
  34. Why Attention Patterns Exist: A Unifying Temporal Perspective AnalysisEfficient LLM inference and serving → KV cache optimization
  35. Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and CapabilitiesLLM safety and security → Machine unlearning
  36. Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
  37. Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained AgentsLLM reasoning → Knowledge- and tool-augmented reasoning
  38. AtPatch: Debugging Transformers via Hot-Fixing Over-AttentionLLM safety and security → Backdoor and data poisoning attacks
  39. TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-TuningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  40. Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifoldEfficient LLM inference and serving → KV cache optimization
  41. Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  42. FIT to Forget: Robust Continual Unlearning for Large Language ModelsLLM safety and security → Machine unlearning
  43. BAP-SRL: Bayesian Adaptive Priority Safe Reinforcement Learning for Vehicle Motion Planning at Mixed Traffic IntersectionsDeep reinforcement learning methods → RL for autonomous driving and traffic
  44. Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability ScalingDeep reinforcement learning methods → Deep RL algorithms and representations
  45. SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  46. Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow MatchingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  47. SWE-Spot: Building Small Repo-Experts with Repository-Centric LearningLLM agents and tool use → Software engineering coding agents
  48. CAF-Mamba: Mamba-Based Cross-Modal Adaptive Attention Fusion for Multimodal Depression DetectionState-space sequence models (S4, Mamba) → Speech and audio SSMs
  49. ILRR: Inference-Time Steering Method for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  50. Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting TransformersMixture-of-experts → MoE for time series and graphs
  51. OCRVerse: Towards Holistic OCR in End-to-End Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  52. RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  53. A Tilted Seesaw: Revisiting Autoencoder Trade-off for Controllable DiffusionDiffusion models → Diffusion foundations and sampling
  54. Reinforcement Learning for Adaptive Composition of Quantum Circuit Optimisation PassesDeep reinforcement learning methods → Quantum reinforcement learning
  55. Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial NoiseDiffusion models → Robustness, privacy and adversarial aspects +1
  56. On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample EfficiencyLLM reasoning → Test-time compute and efficient thinking
  57. PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy OptimizationLLM reasoning → Clinical and biomedical applications +1
  58. Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce RelevanceLLM reasoning → Knowledge- and tool-augmented reasoning +1
  59. WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  60. RecNet: Self-Evolving Preference Propagation for Agentic Recommender SystemsLLM agents and tool use → Agentic recommender systems +1
  61. AIR-VLA: Vision-Language-Action Systems for Aerial ManipulationVision-language-action models → Aerial and drone VLA
  62. CORE: Collaborative Reasoning via Cross TeachingLLM reasoning → Test-time compute and efficient thinking
  63. Beyond Imitation: Reinforcement Learning for Active Latent PlanningLLM reasoning → Test-time compute and efficient thinking
  64. Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution SharpeningLLM reasoning → Reinforcement learning for reasoning
  65. Chain Of Thought Compression: A Theoretical AnalysisLLM reasoning → Test-time compute and efficient thinking
  66. Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural NetworksDeep reinforcement learning methods → Spiking and neuromorphic RL
  67. From Digital to Physical: Digital Agents as Autonomous Coaches for Physical IntelligenceLLM agents and tool use → Multimodal and embodied agents
  68. Representation Unlearning: Forgetting through Information CompressionLLM safety and security → Machine unlearning
  69. ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement ArenasLLM agents and tool use → Reinforcement learning for LLM agents
  70. Meta Context Engineering via Agentic Skill EvolutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  71. Training slow silicon neurons to control extremely fast robots with spiking reinforcement learningDeep reinforcement learning methods → Spiking and neuromorphic RL
  72. Multi-Modal Time Series Prediction via Mixture of Modulated ExpertsMixture-of-experts → MoE for time series and graphs
  73. ShardMemo: Scope-Before-Routing for Agentic Memory RetrievalLLM agents and tool use → Agent memory systems
  74. Bi-Anchor Interpolation Solver for Accelerating Generative ModelingDiffusion models → Flow matching, time series and science
  75. Opinion Consensus Formation Among Networked Large Language ModelsLLM agents and tool use → Social simulation and multi-agent debate
  76. ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision MakingLLM reasoning → Reasoning for agents, planning and code
  77. On the Adversarial Robustness of Large Vision-Language Models under Visual Token CompressionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  78. HERS: Hidden-Pattern Expert Learning for Risk-Specific Vehicle Damage Adaptation in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  79. The Effectiveness of Style Vectors for Steering Large Language Models: A Human EvaluationMechanistic interpretability → Activation steering methods
  80. The Path of Least Resistance: Guiding LLM Reasoning Trajectories with Prefix ConsensusLLM reasoning → Test-time compute and efficient thinking
  81. ETS: Energy-Guided Test-Time Scaling for Training-Free RL AlignmentLLM reasoning → Reinforcement learning for reasoning +1
  82. Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood DistributionsDeep reinforcement learning methods → RL for games and combinatorial optimization
  83. Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMsLLM reasoning → Reinforcement learning for reasoning
  84. ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory ManagementLLM agents and tool use → Software engineering coding agents
  85. Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code GenerationLLM reasoning → Reasoning for agents, planning and code +1
  86. MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon ReasoningLLM agents and tool use → Agent memory systems
  87. Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-EvaluationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  88. L3: Large Lookup LayersMixture-of-experts → MoE large language models
  89. HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingLLM reasoning → Reasoning benchmarks and evaluation
  90. SAGE: Sequence-level Adaptive Gradient Evolution for Generative RecommendationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  91. APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate AttentionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  92. Accurate Network Traffic Matrix Prediction via LEAD: a Large Language Model-Enhanced Adapter-Based Conditional Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
  93. From Consistency to Complementarity: Aligned and Disentangled Multi-modal Learning for Time Series Understanding and ReasoningLLM reasoning → Time series reasoning +1
  94. ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute AllocationMixture-of-experts → MoE large language models
  95. Revisiting Diffusion Model Predictions Through DimensionalityDiffusion models → Diffusion foundations and sampling
  96. Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking
  97. DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data AnalysisLLM agents and tool use → Web, search, and research agents
  98. Towards Space-Based Environmentally-Adaptive GraspingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  99. Intrinsic Reward Policy Optimization for Sparse-Reward EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
  100. Learning to Optimize Job Shop Scheduling Under Structural UncertaintyDeep reinforcement learning methods → RL for energy, networks and operations
  101. RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM RoutingLLM safety and security → Mixture-of-experts routing safety
  102. Towards Geometry-Aware and Motion-Guided Video Human Mesh RecoveryState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  103. NEMO: Execution-Aware Optimization Modeling via Autonomous Coding AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  104. Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based ApproachLLM reasoning → Knowledge- and tool-augmented reasoning
  105. Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  106. Latent Chain-of-Thought as Planning: Decoupling Reasoning from VerbalizationLLM reasoning → Prompting and chain-of-thought reasoning
  107. BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI AgentsLLM agents and tool use → GUI and mobile agents
  108. Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic WorkloadsEfficient LLM inference and serving → KV cache optimization
  109. Factored Causal Representation Learning for Robust Reward Modeling in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  110. L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
  111. Memorization Control in Diffusion Models from Denoising-centric PerspectiveDiffusion models → Diffusion foundations and sampling
  112. Self-Improving Pretraining: using post-trained models to pretrain better modelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  113. Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail StoresMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  114. EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  115. Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior RecommendationLLM reasoning → LLM reasoning for recommendation
  116. LLM-Assisted Op-Amp Behavioral-Level Design via Agentic Human-Mimicking ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  117. Heterogeneous Vertiport Selection Optimization for On-Demand Air Taxi Services: A Deep Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
  118. Few-Shot Learning for Dynamic Operations of Automated Electric Taxi Fleets under Evolving Charging Infrastructure: A Meta-Deep Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  119. The Surprising Difficulty of Search in Model-Based Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  120. Achieving varepsilon-2 Dependence for Average-Reward Q-Learning with a New Contraction PrincipleDeep reinforcement learning methods → RL theory and sample complexity
  121. Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  122. PILD: Physics-Informed Learning via DiffusionDiffusion models → Flow matching, time series and science
  123. DUET: Distilled LLM Unlearning from an Efficiently Contextualized TeacherLLM safety and security → Machine unlearning +1
  124. WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics ConceptsWorld models → Latent predictive world models
  125. EGAM: Extended Graph Attention Model for Solving Routing ProblemsDeep reinforcement learning methods → RL for games and combinatorial optimization
  126. GeoRC: A Benchmark for Geolocation Reasoning ChainsLLM reasoning → Spatial and embodied reasoning +1
  127. More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull RequestsLLM agents and tool use → Software engineering coding agents
  128. CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document EmbeddingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  129. CovAgent: Overcoming the 30% Curse of Mobile Application Coverage with Agentic AI and Dynamic InstrumentationLLM agents and tool use → GUI and mobile agents
  130. Lossless Copyright Protection via Intrinsic Model FingerprintingDiffusion models → Robustness, privacy and adversarial aspects +1
  131. Abstracting Robot Manipulation Skills via Mixture-of-Experts Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  132. NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image RestorationDiffusion models → Inverse problems and image restoration
  133. Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction PurificationLLM reasoning → Reinforcement learning for reasoning
  134. Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU NetworksDiffusion models → Diffusion foundations and sampling
  135. PHDME: Physics-Informed Diffusion Models without Explicit Governing EquationsDiffusion models → Flow matching, time series and science
  136. Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMsLLM agents and tool use → Agent threats, guardrails and governance
  137. MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning EvaluationLLM reasoning → Mathematical reasoning
  138. LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  139. Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  140. Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic VerificationLLM reasoning → Causal reasoning in LLMs
  141. When should I search more: Adaptive Complex Query Optimization with Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  142. Scaling Embeddings Outperforms Scaling Experts in Language ModelsMixture-of-experts → MoE large language models +1
  143. Provably Reliable Classifier Guidance via Cross-Entropy ControlDiffusion models → Diffusion foundations and sampling
  144. Thinker: A vision-language foundation model for embodied intelligenceLLM reasoning → Spatial and embodied reasoning +1
  145. ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity SchedulingMixture-of-experts → Efficient MoE training and inference systems
  146. Human-Agent versus Human Pull Requests: A Testing-Focused Characterization and ComparisonLLM agents and tool use → Software engineering coding agents
  147. Do Reasoning Models Enhance Embedding Models?LLM reasoning → Reinforcement learning for reasoning
  148. FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  149. Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  150. MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  151. FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific TasksLLM reasoning → Knowledge- and tool-augmented reasoning
  152. Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem SolvingLLM reasoning → Spatial and embodied reasoning
  153. A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable ReasoningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  154. Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial ReasoningLLM reasoning → Reasoning for agents, planning and code
  155. BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language DecodingMixture-of-experts → Medical and biomedical MoE
  156. Structural Segmentation of the Minimum Set Cover Problem: Exploiting Universe Decomposability for Metaheuristic Optimization
  157. Focus360: Guiding User Attention in Immersive Videos for VR
  158. Attention Guidance through Video Script: A Case Study of Object Focusing on 360deg VR Video Tours
  159. Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
  160. CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis
  161. Securing SIM-Assisted Wireless Networks via Quantum Reinforcement Learning
  162. NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models
  163. MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Critic
  164. YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation
  165. Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints
  166. Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
  167. Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders
  168. LLM Compression by Block Removal with Constrained Binary Optimization
  169. Sheaf Neural Networks and biomedical applications
  170. RAPTOR: Ridge-Adaptive Logistic Probes
  171. See Without Decoding: Motion-Vector-Based Tracking in Compressed Video
  172. Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusion
  173. Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency
  174. SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehicles
  175. Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
  176. DensiThAI, A Multi-View Deep Learning Framework for Breast Density Estimation using Infrared Images
  177. Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers
  178. Early warning prediction: Onsager-Machlup vs Schr"odinger
  179. Comparison of Image Processing Models in Quark Gluon Jet Classification
  180. MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning
  181. Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture
  182. Word-Centered Semantic Graphs for Interpretable Diachronic Sense Tracking
  183. Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks
  184. Minimal-Action Discrete Schr"odinger Bridge Matching for Peptide Sequence Design
  185. Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization
  186. Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the ErdHos Problems
  187. Spectral Filtering for Complex Linear Dynamical Systems
  188. Score-based Integrated Gradient for Root Cause Explanations of Outliers
  189. Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
  190. Graph is a Substrate Across Data Modalities
  191. SPLA: Block Sparse Plus Linear Attention for Long Context Modeling
  192. It's all In the (Exponential) Family: An Equivalence between Maximum Likelihood Estimation and Control Variates for Sketching Algorithms
  193. FlexMap: Robust HD Map Construction under Flexible Camera Configurations
  194. Stability-Aware Prompt Optimization for Clinical Data Abstraction
  195. FIRE: Multi-fidelity Regression with Distribution-conditioned In-context Learning using Tabular Foundation Models
  196. Learning Provably Correct Distributed Protocols Without Human Knowledge
  197. Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
  198. Towards Solving the Gilbert-Pollak Conjecture via Large Language Models
  199. Context Structure Reshapes the Representational Geometry of Language Models
  200. Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use
  201. Small Talk, Big Impact: The Energy Cost of Thanking AI
  202. PoSafeNet: Safe Learning with Poset-Structured Neural Nets
  203. Relative Wasserstein Angle and the Problem of the W2-Nearest Gaussian Distribution
  204. Learning Policy Representations for Steerable Behavior Synthesis
  205. Pushing the Limits of Block Rotations in Post-Training Quantization
  206. Failing to Explore: Language Models on Interactive Tasks
  207. Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models
  208. Knowledge Gradient for Preference Learning
  209. DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training
  210. Scalable Batch Correction for Cell Painting via Batch-Dependent Kernels and Adaptive Sampling
  211. Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations
  212. Molecular Representations in Implicit Functional Space via Hyper-Networks
  213. Label-Efficient Monitoring of Classification Models via Stratified Importance Sampling
  214. Spatially-Adaptive Conformal Graph Transformer for Indoor Localization in Wi-Fi Driven Networks
  215. Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacy
  216. Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
  217. FlowSymm: Physics Aware, Symmetry Preserving Graph Attention for Network Flow Completion
  218. Gaussian Process Bandit Optimization with Machine Learning Predictions and Application to Hypothesis Generation
  219. Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
  220. Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
  221. Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
  222. Sylber 2.0: A Universal Syllable Embedding
  223. ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning
  224. Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes
  225. Toward all-optical unsupervised Hebbian learning in deep photonic neuromorphic networks
  226. Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation
  227. ParalESN: Enabling parallel information processing in Reservoir Computing
  228. Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas
  229. Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
  230. Riemannian Lyapunov Optimizer: A Unified Framework for Optimization
  231. Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer
  232. Privacy-Preserving Sensor-Based Human Activity Recognition for Low-Resource Healthcare Using Classical Machine Learning
  233. Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models
  234. Tabular Foundation Models Can Do Survival Analysis
  235. Symmetry Breaking in Transformers for Efficient and Interpretable Training
  236. AI Narrative Breakdown. A Critical Assessment of Power and Promise
  237. Is Hierarchical Quantization Essential for Optimal Reconstruction?
  238. Learning to Recommend Multi-Agent Subgraphs from Calling Trees
  239. FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
  240. A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications
  241. Adaptive Benign Overfitting (ABO): Overparameterized RLS for Online Learning in Non-stationary Time-series
  242. Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey
  243. Neural Signals Generate Clinical Notes in the Wild
  244. Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network
  245. Practical Evaluation of Quantum Kernel Methods for Radar Micro-Doppler Classification on Noisy Intermediate-Scale Quantum (NISQ) Hardware
  246. SCENE: Semantic-aware Codec Enhancement with Neural Embeddings
  247. RedSage: A Cybersecurity Generalist LLM
  248. One-step Latent-free Image Generation with Pixel Mean Flows
  249. Discovering Hidden Gems in Model Repositories
  250. Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
  251. Late Breaking Results: Conversion of Neural Networks into Logic Flows for Edge Computing
  252. JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
  253. Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
  254. PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
  255. Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography
  256. Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference
  257. SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization
  258. Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation
  259. Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
  260. Alpha Discovery via Grammar-Guided Learning and Search
  261. Defining Operational Conditions for Safety-Critical AI-Based Systems from Data
  262. SINA: A Circuit Schematic Image-to-Netlist Generator Using Artificial Intelligence
  263. Diverse Approaches to Optimal Execution Schedule Generation
  264. Physics Informed Reconstruction of Four-Dimensional Atmospheric Wind Fields Using Multi-UAS Swarm Observations in a Synthetic Turbulent Environment
  265. Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining
  266. GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization
  267. Investigating Associational Biases in Inter-Model Communication of Large Generative Models
  268. Where Do the Joules Go? Diagnosing Inference Energy Consumption
  269. Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
  270. BLO-Inst: Bi-Level Optimization Based Alignment of YOLO and SAM for Robust Instance Segmentation
  271. MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
  272. MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs
  273. On the Paradoxical Interference between Instruction-Following and Task Solving
  274. PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
  275. Urban Neural Surface Reconstruction from Constrained Sparse Aerial Imagery with 3D SAR Fusion
  276. Learning to Communicate Across Modalities: Perceptual Heterogeneity in Multi-Agent Systems
  277. Leviathan: Decoupling Input and Output Representations in Language Models
  278. Understanding Multimodal Complementarity for Single-Frame Action Anticipation
  279. Cross-Fusion Distance: A Novel Metric for Measuring Fusion and Separability Between Data Groups in Representation Space
  280. Inverse Problems Conditioned on Observation Ensembles: Applications and Methods
  281. Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive Anatomy
  282. When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications
  283. TBDFiltering: Sample-Efficient Tree-Based Data Filtering
  284. Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video
  285. MEIDNet: Multimodal generative AI framework for inverse materials design
  286. Hierarchy of discriminative power and complexity in learning quantum ensembles
  287. Efficient Stochastic Optimisation via Sequential Monte Carlo
  288. Understanding Rate-Distortion Performance in Distributed Transformer Inference
  289. Heterogeneous Computing: The Key to Powering the Future of AI Agent Inference
  290. Negatives-Dominant Contrastive Learning for Generalization in Imbalanced Domains
  291. Liquid Interfaces: A Dynamic Ontology for the Interoperability of Autonomous Systems
  292. Batched First-Order Methods for Parallel LP Solving in MIP
  293. Generalized Information Gathering Under Dynamics Uncertainty
  294. PowerGenie: Analytically-Guided Evolutionary Discovery of Superior Reconfigurable Power Converters
  295. Investigating Batch Inference in a Sequential Monte Carlo Framework for Neural Networks
  296. VERSA: Verified Event Data Format for Reliable Soccer Analytics
  297. Evaluating the trustworthiness of the Fr'echet Inception Distance with stochastic embedding representations
  298. From Particles to Agents: Hallucination as a Metric for Cognitive Friction in Spatial Simulation
  299. Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
  300. Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
  301. The Energy Impact of Domain Model Design in Classical Planning
  302. From Tokens to Blocks: A Block-Diffusion Perspective on Molecular Generation
  303. Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems
  304. Near-Optimal Private Tests for Simple and MLR Hypotheses
  305. PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
  306. Uncertainty-Aware Data-Based Method for Fast and Reliable Shape Optimization
  307. From Generative Modeling to Clinical Classification: A GPT-Based Architecture for EHR Notes
  308. Diffusion Path Samplers via Sequential Monte Carlo
  309. Embracing Aleatoric Uncertainty in Medical Multimodal Learning with Missing Modalities
  310. Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding
  311. Dependence of Equilibrium Propagation Training Success on Network Architecture
  312. Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models
  313. Clustering in Deep Stochastic Transformers
  314. Robust Multimodal Representation Learning in Healthcare
  315. BookNet: Book Image Rectification via Cross-Page Attention Network
  316. Just Noticeable Difference Modeling for Deep Visual Features
  317. LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
  318. SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
  319. One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
  320. From Future of Work to Future of Workers: Addressing Asymptomatic AI Harms for Dignified Human-AI Interaction
  321. On Approximate Computation of Critical Points
  322. Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning
  323. Hardware-Triggered Backdoors
  324. Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting
  325. Making Models Unmergeable via Scaling-Sensitive Loss Landscape
  326. A Low-Complexity Plug-and-Play Deep Learning Model for Generalizable Massive MIMO Precoding
  327. Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
  328. VSE: Variational state estimation of complex model-free process
  329. Managing Solution Stability in Decision-Focused Learning with Cost Regularization
  330. How Expressive Are Graph Neural Networks in the Presence of Node Identifiers?
  331. Transfer Denoising of Low-Rank Plus Sparse Matrices under Ambient and Rank Growth
  332. Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
  333. Pathwise Learning of Stochastic Dynamical Systems with Partial Observations
  334. Blind Ultrasound Image Enhancement via Self-Supervised Physics-Guided Degradation Modeling
  335. LEMUR: Learned Multi-Vector Retrieval
  336. Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models
  337. READY: Reward Discovery for Meta-Black-Box Optimization
  338. Bridging Forecast Accuracy and Inventory KPIs: A Simulation-Based Software Framework
  339. Trustworthy Intelligent Education: A Systematic Perspective on Progress, Challenges, and Future Directions
  340. Scalable Linearized Laplace Approximation via Surrogate Neural Kernel
  341. Goal-Driven Adaptive Sampling Strategies for Machine Learning Models Predicting Fields
  342. Looking Beyond Accuracy: A Holistic Benchmark of ECG Foundation Models
  343. DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
  344. A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth
  345. Moral Outrage Shapes Commitments Beyond Attention: Multimodal Moral Emotions on YouTube in Korea and the US
  346. A Unified XAI-LLM Approach for EndotrachealSuctioning Activity Recognition
  347. Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptation
  348. KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection
  349. Effective LoRA Adapter Routing using Task Representations
  350. NetMamba+: A Framework of Pre-trained Models for Efficient and Accurate Network Traffic Classification
  351. ECSEL: Explainable Classification via Signomial Equation Learning
  352. Assessing the Business Process Modeling Competences of Large Language Models
  353. Synthetic-to-Real Domain Bridging for Single-View 3D Reconstruction of Ships for Maritime Monitoring
  354. Quantum LEGO Learning: A Modular Design Principle for Hybrid Artificial Intelligence
  355. Error Amplification Limits ANN-to-SNN Conversion in Continuous Control
  356. Differentiable Knapsack and Top-k Operators via Dynamic Programming
  357. Abstract Concept Modelling in Conceptual Spaces: A Study on Chess Strategies
  358. Evaluating ChatGPT on Medical Information Extraction Tasks: Performance, Explainability and Beyond
  359. CoFrGeNet: Continued Fraction Architectures for Language Generation
  360. Mean-field Variational Bayes for Sparse Probit Regression
  361. Zero-Shot Statistical Downscaling via Diffusion Posterior Sampling
  362. Influence Guided Sampling for Domain Adaptation of Text Retrievers
  363. EWSJF: An Adaptive Scheduler with Hybrid Partitioning for Mixed-Workload LLM Inference
  364. Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation
  365. FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer
  366. Temporal Sepsis Modeling: a Relational and Explainable-by-Design Framework
  367. Temporal Guidance for Large Language Models
  368. Why β1 = β2 Is Dynamically Special in Adam
  369. From Global to Granular: Revealing IQA Model Performance via Correlation Surface
  370. Mixed-Precision Training and Compilation for RRAM-based Computing-in-Memory Accelerators
  371. CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answering
  372. Mechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks
  373. DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
  374. Procedural Pretraining: Warming Up Language Models with Abstract Data
  375. Enhancing Language Models for Robust Greenwashing Detection
  376. LoRA and Privacy: When Random Projections Help (and When They Don't)
  377. On sample complexity for covariance estimation via the unadjusted Langevin algorithm
  378. DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
  379. Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations
  380. FBS: Modeling Native Parallel Reading inside a Transformer
  381. SmartMeterFM: Unifying Smart Meter Data Generative Tasks Using Flow Matching Models
  382. Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics
  383. Independent Component Discovery in Temporal Count Data
  384. ChartE3: A Comprehensive Benchmark for End-to-End Chart Editing
  385. A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws
  386. XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
  387. Can Local Learning Match Self-Supervised Backpropagation?
  388. LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics
  389. Scale-Dependent Semantic Dynamics Revealed by Allan Deviation
  390. Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification
  391. Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion
  392. From Instruction to Event: Sound-Triggered Mobile Manipulation
  393. AdaptBPE: From General Purpose to Specialized Tokenizers
  394. SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework
  395. Few-Shot Domain Adaptation with Temporal References and Static Priors for Glacier Calving Front Delineation
  396. TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering
  397. ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research
  398. Gauge-invariant representation holonomy
  399. When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption
  400. Identifiable Equivariant Networks are Layerwise Equivariant
  401. Generative Design of Ship Propellers using Conditional Flow Matching
  402. Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
  403. HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning
  404. Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps
  405. LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
  406. Similarity of Processing Steps in Vision Model Representations
  407. Semantic Content Determines Algorithmic Performance
  408. Beyond Parameter Finetuning: Test-Time Representation Refinement for Node Classification
  409. Representation-Regularized Convolutional Audio Transformer for Audio Understanding
  410. Search-Based Risk Feature Discovery in Document Structure Spaces under a Constrained Budget
  411. Age Matters: Analyzing Age-Related Discussions in App Reviews
  412. Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
  413. HydroSense: A Dual-Microcontroller IoT Framework for Real-Time Multi-Parameter Water Quality Monitoring with Edge Processing and Cloud Analytics
  414. Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
  415. Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning
  416. A Study of Crosslinguistic Influence in Language Models
  417. CORDS: Continuous Representations of Discrete Structures
  418. Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
  419. Evaluating Prediction Uncertainty Estimates from BatchEnsemble
  420. KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
  421. Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis
  422. Shaping capabilities with token-level data filtering
  423. Bridging Functional and Representational Similarity via Usable Information
  424. FlexCausal: Flexible Causal Disentanglement via Structural Flow Priors and Manifold-Aware Interventions
  425. Multi-objective Integer Linear Programming approach for Automatic Software Cognitive Complexity Reduction
  426. SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification
  427. HistoPrism: Unlocking Functional Pathway Analysis from Pan-Cancer Histology via Gene Expression Prediction
  428. Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes
  429. inversedMixup: Data Augmentation via Inverting Mixed Embeddings
  430. Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks
  431. Fast and Geometrically Grounded Lorentz Neural Networks
  432. Sustainable Materials Discovery in the Era of Artificial Intelligence
  433. KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
  434. LMK > CLS: Landmark Pooling for Dense Embeddings
  435. Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning
  436. More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)
  437. A Unified SPD Token Transformer Framework for EEG Classification: Systematic Comparison of Geometric Embeddings
  438. Cascaded Transfer: Learning Many Tasks under Budget Constraints
  439. MURAD: A Large-Scale Multi-Domain Unified Reverse Arabic Dictionary Dataset
  440. LLaMEA-SAGE: Guiding Automated Algorithm Design with Structural Feedback from Explainable AI
  441. MAR: Efficient Large Language Models via Module-aware Architecture Refinement
  442. Task-Awareness Improves LLM Generations and Uncertainty
  443. SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing
  444. Manifold constrained steepest descent for smooth and closed-set optimization
  445. DimStance: Multilingual Datasets for Dimensional Stance Analysis
  446. Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking
  447. Differential Dynamic Causal Nets: Model Construction, Identification and Group Comparisons
  448. Task-free Adaptive Meta Black-box Optimization
  449. Best Arm Identification with LLM Judges and Limited Human
  450. PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization
  451. A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation
  452. Topeax -- An Improved Clustering Topic Model with Density Peak Detection and Lexical-Semantic Term Importance
  453. Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs
  454. Partial Feedback Online Learning
  455. Mining Forgery Traces from Reconstruction Error: A Weakly Supervised Framework for Multimodal Deepfake Temporal Localization
  456. Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better
  457. 4D-CAAL: 4D Radar-Camera Calibration and Auto-Labeling for Autonomous Driving
  458. LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
  459. Variance & Greediness: A comparative study of metric-learning losses
  460. ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design
  461. Synthetic Pattern Generation and Detection of Financial Activities using Graph Autoencoders
  462. The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making
  463. Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas
  464. MultiModal Fine-tuning with Synthetic Captions
  465. Lossy Common Information in a Learnable Gray-Wyner Network
  466. From Implicit Ambiguity to Explicit Solidity: Diagnosing Interior Geometric Degradation in Neural Radiance Fields for Dense 3D Scene Understanding
  467. System 1&2 Synergy via Dynamic Model Interpolation
  468. Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration
  469. MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations
  470. Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
  471. Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification
  472. User-Centric Evidence Ranking for Attribution and Fact Verification
  473. Understanding Frechet Speech Distance for Synthetic Speech Quality Evaluation
  474. Sim-MSTNet: sim2real based Multi-task SpatioTemporal Network Traffic Forecasting
  475. DA-SPS: A Dual-stage Network based on Singular Spectrum Analysis, Patching-strategy and Spearman-correlation for Multivariate Time-series Prediction
  476. TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models
  477. Hebbian Learning with Global Direction
  478. Perceptrons and localization of attention's mean-field landscape
  479. ViTMAlis: Towards Latency-Critical Mobile Video Analytics with Vision Transformers
  480. The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
  481. Graph-Free Root Cause Analysis
  482. Beyond Objective-Based Improvement: Stationarity-Aware Expected Improvement for Bayesian Optimization
  483. Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning
  484. Dynamic Framework for Collaborative Learning: Leveraging Advanced LLM with Adaptive Feedback Mechanisms
  485. Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
  486. Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks
  487. Correcting Spectra Outside the Backbone: A Model-Agnostic Rectifier for Hyperspectral Image Super-Resolution
  488. Qwen3-ASR Technical Report
  489. Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
  490. Convex Loss Functions for Support Vector Machines (SVMs) and Neural Networks
  491. Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
  492. Adversarial Vulnerability Transcends Computational Paradigms: Feature Engineering Provides No Defense Against Neural Adversarial Transfer
  493. Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
  494. Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation
  495. HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence
  496. Transferable Graph Condensation from the Causal Perspective
  497. Mam-App: A Novel Parameter-Efficient Mamba Model for Apple Leaf Disease Classification
  498. Grounding and Enhancing Informativeness and Utility in Dataset Distillation
  499. Missing-Data-Induced Phase Transitions in Spectral Partial Least Squares
  500. Reliability-Calibrated Edge-IoT Early Fault Warning for Rotating Machinery with a Physics-Guided Tiny-Mamba Transformer
  501. Gaussian Belief Propagation Network for Depth Completion
  502. TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
  503. Zenith: Scaling up Ranking Models for Billion-scale Livestreaming Recommendation
  504. Token Entropy Regularization for Multi-modal Antenna Affiliation Identification
  505. NEXUS: Bit-Exact ANN-to-SNN Equivalence via Neuromorphic Gate Circuits with Surrogate-Free Training
  506. Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference
  507. Model-Free Neural Filtering: A Comparison with Classical Filters in Nonlinear Systems
  508. Music Plagiarism Detection: Problem Formulation and a Segment-based Solution
  509. MoCo: A One-Stop Shop for Model Collaboration Research
  510. Hypersolid: Emergent Vision Representations via Short-Range Repulsion
  511. Position: Certifiable State Integrity Should Be Built from Local Validity, Not Global Scale
  512. Conditional Generative Framework with Peak-Aware Attention for Robust Chemical Detection under Interferences
  513. Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
  514. TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design
  515. PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
  516. Characterizing the Effect of Noise in Language Generation in the Limit
  517. SHARP: Social Harm Analysis via Risk Profiles for Measuring Inequities in Large Language Models
  518. Data-Driven Generation of Neutron Star Equations of State Using Variational Autoencoders
  519. Delegation Without Living Governance
  520. Causal Discovery for Explainable AI: A Dual-Encoding Approach
  521. Soft Quantization: Model Compression Via Weight Coupling
  522. Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data
  523. A Flexible Empirical Bayes Approach to Generalized Linear Models, with Applications to Sparse Logistic Regression
  524. Temporal Context and Architecture: A Benchmark for Naturalistic EEG Decoding
  525. Intelli-Planner: Towards Customized Urban Planning via Large Language Model Empowered Reinforcement Learning
  526. A Sheaf-Theoretic and Topological Perspective on Complex Network Modeling and Attention Mechanisms in Graph Neural Models
  527. Multilingual Dysarthric Speech Assessment Using Universal Phone Recognition and Language-Specific Phonemic Contrast Modeling
  528. Rethinking Self-Training Based Cross-Subject Domain Adaptation for SSVEP Classification
  529. Generative Recall, Dense Reranking: Learning Multi-View Semantic IDs for Efficient Text-to-Video Retrieval
  530. Function Words as Statistical Cues for Language Learning
  531. Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks
  532. Rethinking Refinement: Correcting Generative Bias without Noise Injection
  533. Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process
  534. Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
  535. Breaking the Reasoning Horizon in Entity Alignment Foundation Models
  536. Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios
  537. AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
  538. The Powers of Precision: Structure-Informed Detection in Complex Systems -- From Customer Churn to Seizure Onset
  539. Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space
  540. Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits
  541. A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of Components
  542. Spatial-Regularization-Aware Dual-Branch Collaborative Inference for Training-Free OVSS in Remote Sensing Imagery
  543. A new strategy for finite-sample valid prediction of future insurance claims in the regression setting
  544. Learning to Advect: A Neural Semi-Lagrangian Architecture for Weather Forecasting
  545. Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations
  546. Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement
  547. Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials
  548. Maxwait: A Generalized Mechanism for Distributed Time-Sensitive Systems
  549. Optimization and Mobile Deployment for Anthropocene Neural Style Transfer
  550. EnsembleLink: Accurate Record Linkage Without Training Data
  551. TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
  552. Large Language Models Naively Recover Ethnicity from Individual Records
  553. Thompson sampling: Precise arm-pull dynamics and adaptive inference
  554. What You Feel Is Not What They See: On Predicting Self-Reported Emotion from Third-Party Observer Labels
  555. Beyond a Single Reference: Training and Evaluation with Paraphrases in Sign Language Translation