mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 16 Mar 2026

565 papers

  1. A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution TopologyLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  3. Beyond the Townhall: Spatial Anchoring and LLM Agents for Scalable Participatory Urban PlanningLLM agents and tool use → Multimodal and embodied agents
  4. HearthNet: Edge Multi-Agent Orchestration for Smart HomesLLM agents and tool use → Financial trading and forecasting agents
  5. Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  6. TelcoAgent-Bench: A Multilingual Benchmark for Telecom AI AgentsLLM agents and tool use → Agentic AI for wireless networks
  7. LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMsLLM reasoning → Spatial and embodied reasoning +1
  8. GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-ResolutionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  9. Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based ExplainabilityLLM reasoning → Reasoning benchmarks and evaluation +1
  10. Safety Case Patterns for VLA-based driving systems: Insights from SimLingoEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  11. FormulaCode: Evaluating Agentic Optimization on Large CodebasesLLM agents and tool use → Software engineering coding agents
  12. CoDesignAI: An AI-Enabled Multi-Agent, Multi-User System for Collaborative Urban Design at the Conceptual StageLLM agents and tool use → Multimodal and embodied agents
  13. Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  14. Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical ArchivingRetrieval-augmented generation → Generation and context integration
  15. An Agentic Evaluation Framework for AI-Generated Scientific Code in PETScLLM agents and tool use → Web, search, and research agents
  16. MAC: Multi-Agent Constitution LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  17. GASP: Guided Asymmetric Self-Play For Coding LLMsSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  18. ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior PriorsDiffusion models → Diffusion and flow policies for robotics
  19. Protein Design with Agent Rosetta: A Case Study for Specialized Scientific AgentsLLM reasoning → Clinical and biomedical applications +1
  20. Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For UsLLM reasoning → Reasoning benchmarks and evaluation +1
  21. Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  22. NAMD: Virtual Follow-up Computed Tomography Synthesis via Nodule-Aligned Multimodal Diffusion Models for Early Lung Cancer DiagnosisDiffusion models → Medical imaging and segmentation
  23. Generative Inverse Design with Abstention via Diagonal Flow MatchingDiffusion models → Flow matching, time series and science
  24. VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?LLM agents and tool use → Software engineering coding agents
  25. Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision TransformersMechanistic interpretability → Interpreting vision and multimodal models
  26. Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 ExperimentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine LearningLLM agents and tool use → Educational agents and math problem solving
  28. Human-AI Synergy in Agentic Code ReviewLLM agents and tool use → Software engineering coding agents
  29. Game-Theory-Assisted Reinforcement Learning for Border Defense: Early Termination based on Analytical SolutionsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  30. Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  31. Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report GenerationRetrieval-augmented generation → Medical and biomedical RAG
  32. Don't Trust Stubborn Neighbors: A Security Framework for Agentic NetworksLLM agents and tool use → Agent threats, guardrails and governance
  33. Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMsDiffusion models → Discrete and text diffusion
  34. Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective MemoryLLM reasoning → Reasoning for agents, planning and code +1
  35. OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific ReasoningLLM reasoning → Spatial and embodied reasoning +1
  36. Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  37. CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  38. Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World AdaptationWorld models → Embodied and robot world models
  39. You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise VectorDiffusion models → Diffusion and flow policies for robotics
  40. AgentWorm: Self-Propagating Attacks Across LLM Agent EcosystemsLLM agents and tool use → Agent threats, guardrails and governance
  41. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via VerificationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  42. Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal ModelsLLM reasoning → Multimodal reasoning
  43. How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public CompetitionLLM agents and tool use → Agent threats, guardrails and governance +1
  44. SEMAG: Self-Evolutionary Multi-Agent Code GenerationLLM agents and tool use → Software engineering coding agents
  45. BadLLM-TG: A Backdoor Defender powered by LLM Trigger GeneratorLLM safety and security → Backdoor and data poisoning attacks
  46. Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  47. Transition Flow MatchingDiffusion models → Flow matching, time series and science
  48. Towards Generalizable Robotic Manipulation in Dynamic EnvironmentsVision-language-action models → 3D and spatial-aware VLA
  49. Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  50. Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic VerificationLLM reasoning → Mathematical reasoning
  51. GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text RenderingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  52. Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and MotionDiffusion models → Video generation
  53. From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic ManipulationLLM reasoning → Spatial and embodied reasoning
  54. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training DataLLM agents and tool use → Web, search, and research agents
  55. Grounding World Simulation Models in a Real-World MetropolisWorld models → Video-generation world models and simulators
  56. Mamba-3: Improved Sequence Modeling using State Space PrinciplesLLM reasoning → Test-time compute and efficient thinking +1
  57. Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding AgentsLLM agents and tool use → Software engineering coding agents
  58. Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  59. Self-Distillation of Hidden Layers for Self-Supervised Representation LearningKnowledge distillation → General knowledge distillation methods
  60. Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor GenerationLLM reasoning → Mathematical reasoning
  61. InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social SystemsLLM reasoning → Causal reasoning in LLMs
  62. Bridging Local and Global Knowledge: Cascaded Mixture-of-Experts Learning for Near-Shortest Path RoutingMixture-of-experts → Expert routing strategies
  63. Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority GraphLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  64. ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  65. Understanding Reasoning in LLMs through Strategic Information Allocation under UncertaintyLLM reasoning → Test-time compute and efficient thinking
  66. RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge GuidanceDiffusion models → Inverse problems and image restoration
  67. Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature BinsKnowledge distillation → General knowledge distillation methods
  69. ViFeEdit: A Video-Free Tuner of Your Video Diffusion TransformerDiffusion models → Video generation
  70. Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI AgentsLLM agents and tool use → Software engineering coding agents
  71. Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room TaskMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  72. Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded ReasoningLLM reasoning → Reasoning for agents, planning and code
  73. Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series ForecastingLLM reasoning → Time series reasoning
  74. Deep Reinforcement Learning for Fano HypersurfacesDeep reinforcement learning methods → Deep RL algorithms and representations
  75. Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  76. Gym-V: A Unified Vision Environment System for Agentic Vision ResearchLLM agents and tool use → Multimodal and embodied agents
  77. CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model AgentsLLM agents and tool use → Agent memory systems
  78. MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team SettingsLLM agents and tool use → Reinforcement learning for LLM agents
  79. Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning VulnerabilitiesLLM reasoning → Reinforcement learning for reasoning +1
  80. TrinityGuard: A Unified Framework for Safeguarding Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  81. A Closer Look into LLMs for Table UnderstandingMixture-of-experts → MoE large language models
  82. SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?LLM agents and tool use → Software engineering coding agents
  83. SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and CalibrationLLM reasoning → Reasoning for agents, planning and code +1
  84. Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy OptimizationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  85. RieMind: Geometry-Grounded Spatial Agent for Scene UnderstandingLLM reasoning → Spatial and embodied reasoning +2
  86. More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam SearchLLM reasoning → Test-time compute and efficient thinking
  87. Brain-Inspired Graph Multi-Agent Systems for LLM ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  88. A PPO-Based Bitrate Allocation Conditional Diffusion Model for Remote Sensing Image CompressionDiffusion models → Inverse problems and image restoration
  89. CRASH: Cognitive Reasoning Agent for Safety Hazards in Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  90. NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social NavigationWorld models → World models for navigation
  91. Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion MethodDiffusion models → Flow matching, time series and science
  92. PMAx: An Agentic Framework for AI-Driven Process MiningLLM agents and tool use → Software engineering coding agents
  93. Intelligent Co-Design: An Interactive LLM Framework for Interior Spatial Design via Multi-Modal AgentsLLM agents and tool use → Multimodal and embodied agents
  94. DOS: Dependency-Oriented Sampler for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  95. CCTU: A Benchmark for Tool Use under Complex ConstraintsLLM agents and tool use → Tool learning and function calling
  96. Evaluating the Robustness of Reinforcement Learning based Adaptive Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  97. Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic MemoryLLM reasoning → Reasoning for agents, planning and code +1
  98. Faster Inference of Flow-Based Generative Models via Improved Data-Noise CouplingDiffusion models → Flow matching, time series and science
  99. Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  100. AGCD: Agent-Guided Cross-Modal Decoding for Weather ForecastingLLM agents and tool use → Financial trading and forecasting agents
All 565
  1. Directional Embedding Smoothing for Robust Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  2. HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile SensingVision-language-action models → Tactile, force-aware and humanoid VLA
  3. SAGE: Multi-Agent Self-Evolution for LLM ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  4. HalDec-Bench: Benchmarking Hallucination Detector in Image CaptioningMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  5. Mechanistic Foundations of Goal-Directed ControlMechanistic interpretability → Circuits and mechanistic analysis
  6. Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly DetectionLLM reasoning → Spatial and embodied reasoning +1
  7. ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  8. Efficient Document Parsing via Parallel Token PredictionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  9. Simple is Better: Multiplication May Be All You Need for LLM Request SchedulingEfficient LLM inference and serving → Serving systems and request scheduling
  10. What Matters for Scalable and Robust Learning in End-to-End Driving Planners?End-to-end autonomous driving → End-to-end system architecture
  11. Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM SystemsLLM agents and tool use → Software engineering coding agents
  12. Iterative Learning Control-Informed Reinforcement Learning for Batch Process ControlDeep reinforcement learning methods → RL for energy, networks and operations
  13. KiRAS: Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning in Quadruped RobotsOffline RL and imitation learning from data → Robot manipulation imitation learning +1
  14. Question-guided Visual Compression with Memory Feedback for Long-Term Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  15. DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher TransferMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  16. HindSight: Evaluating LLM-Generated Research Ideas via Future ImpactRetrieval-augmented generation → RAG pipeline design and evaluation
  17. Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow PoliciesOffline RL and imitation learning from data → Safe offline RL
  18. Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  19. WiT: Waypoint Diffusion Transformers for Alleviating Trajectory Conflict in Pixel-Space Image GenerationDiffusion models → Diffusion foundations and sampling
  20. Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion PriorsDiffusion models → Diffusion for compression and wireless
  21. From Storage to Steering: Memory Control Flow Attacks on LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  22. MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual KnowledgeLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  23. HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. Writer-R1: Enhancing Generative Writing in LLMs via Memory-augmented Replay Policy OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  25. Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking
  26. AnoleVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile ManipulationVision-language-action models → Generalist VLA models and benchmarks
  27. GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  28. Models Designed to Forget: Machine Unlearning via Key DeletionLLM safety and security → Machine unlearning
  29. VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool ChainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  30. Describing Agentic AI Systems with C4: Lessons from Industry ProjectsLLM agents and tool use → Software engineering coding agents
  31. Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow MatchingDiffusion models → Flow matching, time series and science
  32. CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  33. Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram ParsingDeep reinforcement learning methods → RL for energy, networks and operations
  34. Clue Matters: Leveraging Latent Visual Clues to Empower Video ReasoningLLM reasoning → Multimodal reasoning +1
  35. Edit2Interp: Adapting Image Foundation Models from Spatial Editing to Video Frame Interpolation with Few-Shot LearningLLM reasoning → Multimodal reasoning
  36. OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate CorporaLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  37. MMSpec: Benchmarking Speculative Decoding for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  38. Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  39. ReMAP-DP: Reprojected Multi-view Aligned PointMaps for Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  40. Why Agents Compromise Safety Under PressureLLM agents and tool use → Agent threats, guardrails and governance
  41. Learning from Mistakes: Post-Training for Driving VLA with Takeover DataEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  42. Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party FrameworkLLM safety and security → Watermarking generated content and models
  43. GeoNVS: Geometry Grounded Video Diffusion for Novel View SynthesisDiffusion models → 3D, point cloud and scene generation
  44. CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
  46. GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLMMultimodal LLMs / vision-language models → Image editing and quality assessment
  47. Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion RepresentationWorld models → World models for autonomous driving +1
  48. RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense ForecastingWorld models → Latent predictive world models
  49. FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
  50. LLM as Graph Kernel: Rethinking Message Passing on Text-Rich GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
  51. Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image DiffusionDiffusion models → Diffusion and flow policies for robotics
  52. EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image EditingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  53. PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
  54. Photonic Quantum-Enhanced Knowledge DistillationKnowledge distillation → Graph neural network distillation
  55. Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  56. SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and ColloquialnessLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  57. ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  58. LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  59. Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  60. Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce TasksLLM agents and tool use → Social simulation and multi-agent debate +1
  61. AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  62. From Artefact to Insight: Efficient Low-Rank Adaptation of BrushNet for Scanning Probe Microscopy Image RestorationDiffusion models → Inverse problems and image restoration
  63. The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 TreatmentsRetrieval-augmented generation → Medical and biomedical RAG
  64. Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  65. Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature ProjectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  66. RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  67. M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts +1
  68. Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement LearningLLM reasoning → Spatial and embodied reasoning
  69. HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory SystemLLM agents and tool use → Multimodal and embodied agents
  70. Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software DevelopmentLLM agents and tool use → Software engineering coding agents
  71. CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater MonitoringLLM reasoning → Spatial and embodied reasoning
  72. P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k RetrievalRetrieval-augmented generation → Privacy and security of RAG
  73. OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective IntelligenceLLM agents and tool use → Medical and scientific domain agents
  74. BrainBench: Exposing the Commonsense Reasoning Gap in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  75. CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  76. PHAC: Promptable Human Amodal CompletionDiffusion models → 3D, point cloud and scene generation
  77. TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric PerspectiveState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  78. A Skill-augmented Agentic Framework and Benchmark for Multi-Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  79. DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  80. Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series ForecastingRetrieval-augmented generation → Time series and agricultural RAG
  81. Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using AgentsLLM safety and security → Prompt injection and agent security
  82. Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic PlanningDiffusion models → Diffusion and flow policies for robotics
  83. Beyond Local Code Optimization: Multi-Agent Reasoning for Software System OptimizationLLM reasoning → Reasoning for agents, planning and code +1
  84. AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  85. Scalable Text-Embedding-informed Cognitive Diagnosis of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  86. Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detection
  87. AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains
  88. Training for Compositional Sensitivity Reduces Dense Retrieval Generalization
  89. Benchmarking Real-Time Question Answering via Executable Code Workflows
  90. Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization
  91. Bridging the Experimental Last Mile: Digitizing Laboratory Know-How for Safe AI-Assisted Support
  92. Elder-Sim: A Psychometrically Validated Platform for Personality-Stable Elderly Digital Twins
  93. Hijacking online reviews: sparse manipulation and behavioral buffering in popularity-biased rating systems
  94. AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
  95. SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Discussions Using Large Language Models
  96. Governing frontier general-purpose AI in the public sector: adaptive risk management and policy capacity under uncertainty through 2030
  97. Unsupervised Neural Network for Automated Classification of Surgical Urgency Levels in Medical Transcriptions
  98. Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models
  99. Code Sharing In Prediction Model Research: A Scoping Review
  100. Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
  101. Extracting Breast Cancer Phenotypes from Clinical Notes: Comparing LLMs with Classical Ontology Methods
  102. A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction
  103. Physicochemical-Neural Fusion for Semi-Closed-Circuit Respiratory Autonomy in Extreme Environments
  104. Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach
  105. Degrees, Levels, and Profiles of Contextuality
  106. SpatialPoint: Spatial-aware Point Prediction for Embodied Localization
  107. A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems
  108. Exploring Novelty Differences between Industry and Academia: A Knowledge Entity-centric Perspective
  109. Towards Solving Polynomial-Objective Integer Programming with Hypergraph Neural Networks
  110. RARE disease detection from Capsule Endoscopic Videos based on Vision Transformers
  111. Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
  112. Minimum-Action Learning: Energy-Constrained Symbolic Model Selection for Physical Law Identification from Noisy Data
  113. Kriging via variably scaled kernels
  114. Entropy-Aware Task Offloading in Mobile Edge Computing
  115. A Framework for Modeling Liquefaction-Induced Road Disruptions After Earthquakes: Implications for Emergency Response and Access in the Cascadia Region of North America
  116. Automatic Termination Strategy of Inelastic Neutron-scattering Measurement Using Bayesian Optimization for Bin-width Selection
  117. Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing
  118. Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models
  119. KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition
  120. UNICORN: Ultrasound Nakagami Imaging via Score Matching and Adaptation for Assessing Hepatic Steatosis
  121. IRAM-Omega-Q: A Computational Framework for Uncertainty Regulation in Adaptive Agents
  122. FlatLands: Generative Floormap Completion From a Single Egocentric View
  123. The Importance of Being Smoothly Calibrated
  124. Breakdown properties of optimal transport maps: general transportation costs
  125. RadAnnotate: Large Language Models for Efficient and Reliable Radiology Report Annotation
  126. NLP Occupational Emergence Analysis: How Occupations Form and Evolve in Real Time -- A Zero-Assumption Method Demonstrated on AI in the US Technology Workforce, 2022-2026
  127. Visual Set Program Synthesizer
  128. The Midas Touch in Gaze vs. Hand Pointing: Modality-Specific Failure Modes and Implications for XR Interfaces
  129. W2T: LoRA Weights Already Know What They Can Do
  130. Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
  131. Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity
  132. Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
  133. Standardizing Medical Images at Scale for AI
  134. From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
  135. UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
  136. Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
  137. 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
  138. Robust Language Identification for Romansh Varieties
  139. A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images
  140. MoLoRA: Composable Specialization via Per-Token Adapter Routing
  141. Optimizing Hospital Capacity During Pandemics: A Dual-Component Framework for Strategic Patient Relocation
  142. Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
  143. MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
  144. A Family of LLMs Liberated from Static Vocabularies
  145. POLAR:A Per-User Association Test in Embedding Space
  146. BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction
  147. Towards Fair and Robust Volumetric CT Classification via KL-Regularised Group Distributionally Robust Optimisation
  148. Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification
  149. CTG-DB: An Ontology-Based Transformation of ClinicalTrials.gov to Enable Cross-Trial Drug Safety Analyses
  150. Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
  151. Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems
  152. Evaluating Causal Discovery Algorithms for Path-Specific Fairness and Utility in Healthcare
  153. Learning to Recall with Transformers Beyond Orthogonal Embeddings
  154. Machine Translation in the Wild: User Reaction to Xiaohongshu's Built-In Translation Feature
  155. Data-efficient Bayesian-guided design selection from large candidate sets: Application to hyperelastic stochastic metamaterials
  156. Prompt Engineering for Scale Development in Generative Psychometrics
  157. Agent-based imitation dynamics can yield efficiently compressed population-level vocabularies
  158. Federated Learning for Privacy-Preserving Medical AI
  159. The Internet of Physical AI Agents: Interoperability, Longevity, and the Cost of Getting It Wrong
  160. COGNAC at SemEval-2026 Task 5: LLM Ensembles for Human-Level Word Sense Plausibility Rating in Challenging Narratives
  161. Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN
  162. AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback
  163. EvoIQA - Explaining Image Distortions with Evolved White-Box Logic
  164. PhasorFlow: A Python Library for Unit Circle Based Computing
  165. Resilience Meets Autonomy: Governing Embodied AI in Critical Infrastructure
  166. Electrodermal Activity as a Unimodal Signal for Aerobic Exercise Detection in Wearable Sensors
  167. Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations
  168. Interpretative Interfaces: Designing for AI-Mediated Reading Practices and the Knowledge Commons
  169. Self-supervised Disentanglement of Disease Effects from Aging in 3D Medical Shapes
  170. Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
  171. FlashSampling: Fast and Memory-Efficient Exact Sampling
  172. Algorithmic Trading Strategy Development and Optimisation
  173. FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
  174. Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
  175. When Stability Fails: Hidden Failure Modes Of LLMS in Data-Constrained Scientific Decision-Making
  176. Spectral Hierarchy of the Cosmic Web
  177. Persona-Conditioned Risk Behavior in Large Language Models: A Simulated Gambling Study with GPT-4.1
  178. Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
  179. Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition
  180. Longitudinal Risk Prediction in Mammography with Privileged History Distillation
  181. ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation
  182. Feed-forward Gaussian Registration for Head Avatar Creation and Editing
  183. Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
  184. Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
  185. CUBE: A Standard for Unifying Agent Benchmarks
  186. Learnability with Partial Labels and Adaptive Nearest Neighbors
  187. Parallelised Differentiable Straightest Geodesics for 3D Meshes
  188. Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis
  189. Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs
  190. CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning
  191. S2Act: Simple Spiking Actor
  192. Context-Length Robustness in Question Answering Models: A Comparative Empirical Study
  193. A Framework and Prototype for a Navigable Map of Datasets in Engineering Design and Systems Engineering
  194. GLANCE: Gaze-Led Attention Network for Compressed Edge-inference
  195. Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences
  196. LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation
  197. Knowledge Graph Extraction from Biomedical Literature for Alkaptonuria Rare Disease
  198. Survey of Various Fuzzy and Uncertain Decision-Making Methods
  199. Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning
  200. This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
  201. Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
  202. Mixture-of-Depths Attention
  203. Mechanistic Origin of Moral Indifference in Language Models
  204. HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
  205. Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
  206. Do Metrics for Counterfactual Explanations Align with User Perception?
  207. Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
  208. SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
  209. AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
  210. Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
  211. Effective Distillation to Hybrid xLSTM Architectures
  212. Computational Concept of the Psyche
  213. Physics-Informed Neural Systems for the Simulation of EUV Electromagnetic Wave Diffraction from a Lithography Mask
  214. Benchmarking Machine Learning Approaches for Polarization Mapping in Ferroelectrics Using 4D-STEM
  215. Low-Complexity and Consistent Graphon Estimation from Multiple Networks
  216. Unbiased and Biased Variance-Reduced Forward-Reflected-Backward Splitting Methods for Stochastic Composite Inclusions
  217. Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments
  218. Co-Design of Memory-Storage Systems for Workload Awareness with Interpretable Models
  219. Estimating Staged Event Tree Models via Hierarchical Clustering on the Simplex
  220. Predictive Uncertainty in Short-Term PV Forecasting under Missing Data: A Multiple Imputation Approach
  221. The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
  222. Panoramic Affordance Prediction
  223. Learning Latent Proxies for Controllable Single-Image Relighting
  224. Kimodo: Scaling Controllable Human Motion Generation
  225. DOT: Dynamic Knob Selection and Online Sampling for Automated Database Tuning
  226. Vib2ECG: A Paired Chest-Lead SCG-ECG Dataset and Benchmark for ECG Reconstruction
  227. Building Trust in PINNs: Error Estimation through Finite Difference Methods
  228. Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models
  229. SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction
  230. Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models
  231. FreeTalk: Emotional Topology-Free 3D Talking Heads
  232. Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
  233. Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference
  234. Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains
  235. Real-Time Oriented Object Detection Transformer in Remote Sensing Images
  236. Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold
  237. Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation
  238. Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation
  239. Anchor then Polish for Low-light Enhancement
  240. Automated Counting of Stacked Objects in Industrial Inspection
  241. RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation
  242. Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
  243. Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches
  244. MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
  245. Real-Time Human Frontal View Synthesis from a Single Image
  246. Physics-informed fine-tuning of foundation models for partial differential equations
  247. Invisible failures in human-AI interactions
  248. AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
  249. RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
  250. The Metric Slingshot: Navigational Reuse as Width-Optimal Structural Decoupling in Continual Learning
  251. A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning
  252. SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
  253. Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models
  254. Detection of Autonomous Shuttles in Urban Traffic Images Using Adaptive Residual Context
  255. Pointing-Based Object Recognition
  256. AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanations
  257. When Does Sparsity Mitigate the Curse of Depth in LLMs
  258. Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport
  259. Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
  260. Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation
  261. GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
  262. SKILLS: Structured Knowledge Injection for LLM-Driven Telecommunications Operations
  263. Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
  264. IRIS: Intersection-aware Ray-based Implicit Editable Scenes
  265. Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
  266. Deep learning and the rate of approximation by flows
  267. FuXiWeather2: Learning accurate atmospheric state estimation for operational global weather forecasting
  268. NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation
  269. Oscillating Dispersion for Maximal Light-throughput Spectral Imaging
  270. Active Seriation: Efficient Ordering Recovery with Statistical Guarantees
  271. Data Augmentation via Causal-Residual Bootstrapping
  272. A scaled TW-PINN: A physics-informed neural network for traveling wave solutions of reaction-diffusion equations with general coefficients
  273. MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction
  274. Tagarela - A Portuguese speech dataset from podcasts
  275. CASHomon Sets: Efficient Rashomon Sets Across Multiple Model Classes and their Hyperparameters
  276. PYTHEN: A Flexible Framework for Legal Reasoning in Python
  277. A Kolmogorov-Arnold Surrogate Model for Chemical Equilibria: Application to Solid Solutions
  278. xplainfi: Feature Importance and Statistical Inference for Machine Learning in R
  279. Generative Video Compression with One-Dimensional Latent Representation
  280. GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
  281. Enhancing classification accuracy through chaos
  282. Evolutionary Transfer Learning for Dragonchess
  283. Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies
  284. Scalable Simulation-Based Model Inference with Test-Time Complexity Control
  285. Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems: Technical Report
  286. Dataset Diversity Metrics and Impact on Classification Models
  287. From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding
  288. Self-Supervised ImageNet Representations for In Vivo Confocal Microscopy: Tortuosity Grading without Segmentation Maps
  289. Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
  290. IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
  291. Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
  292. In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
  293. Practicing with Language Models Cultivates Human Empathic Communication
  294. A proof-of-concept for automated AI-driven stellarator coil optimization with in-the-loop finite-element calculations
  295. Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones
  296. Decomposing Probabilistic Scores: Reliability, Information Loss and Uncertainty
  297. HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
  298. Bidirectional Chinese and English Passive Sentences Dataset for Machine Translation
  299. SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
  300. InterPol: De-anonymizing LM Arena via Interpolated Preference Learning
  301. Towards Foundation Models for Consensus Rank Aggregation
  302. Tracking the Discriminative Axis: Dual Prototypes for Test-Time OOD Detection Under Covariate Shift
  303. Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football
  304. Bridging Theory and Data: Correcting Nuclear Mass Models with Interpretable Machine Learning
  305. Geometric framework for biological evolution
  306. Massive Redundancy in Gradient Transport Enables Sparse Online Learning
  307. PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturing
  308. The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
  309. Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
  310. The Hrunting of AI: Where and How to Improve English Dialectal Fairness
  311. CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds
  312. Sequential Transport for Causal Mediation Analysis
  313. Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning
  314. To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
  315. Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies
  316. Storage and selection of multiple chaotic attractors in minimal reservoir computers
  317. Vision-Language Model Based Multi-Expert Fusion for CT Image Classification
  318. TextOVSR: Text-Guided Real-World Opera Video Super-Resolution
  319. SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation
  320. Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
  321. Clinical Priors Guided Lung Disease Detection in 3D CT Scans
  322. Context-Aware Sensor Modeling for Asynchronous Multi-Sensor Tracking in Stone Soup
  323. Low-light Image Enhancement with Retinex Decomposition in Latent Space
  324. Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike
  325. A Novel Camera-to-Robot Calibration Method for Vision-Based Floor Measurements
  326. Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks
  327. A Tutorial on ALOS2 SAR Utilization: Dataset Preparation, Self-Supervised Pretraining, and Semantic Segmentation
  328. VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents
  329. Sampling-guided exploration of active feature selection policies
  330. PAKAN: Pixel Adaptive Kolmogorov-Arnold Network Modules for Pansharpening
  331. PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units
  332. Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC
  333. Bridging National and International Legal Data: Two Projects Based on the Japanese Legal Standard XML Schema for Comparative Law Studies
  334. Trustworthy Koopman Operator Learning: Invariance Diagnostics and Error Bounds
  335. Affordable Precision Agriculture: A Deployment-Oriented Review of Low-Cost, Low-Power Edge AI and TinyML for Resource-Constrained Farming Systems
  336. ReactMotion: Generating Reactive Listener Motions from Speaker Utterance
  337. Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
  338. Interpretable Classification of Time Series Using Euler Characteristic Surfaces
  339. Generative Semantic HARQ: Latent-Space Text Retransmission and Combining
  340. The Good, the Better, and the Best: Improving the Discriminability of Face Embeddings through Attribute-aware Learning
  341. Muon Converges under Heavy-Tailed Noise: Nonconvex H"older-Smooth Empirical Risk Minimization
  342. Analyzing Error Sources in Global Feature Effect Estimation
  343. Spatio-temporal probabilistic forecast using MMAF-guided learning
  344. Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
  345. SRL-MAD: Structured Residual Latents for One-Class Morphing Attack Detection
  346. CrossADR: enhancing adverse drug reactions prediction for combination pharmacotherapy with cross-layer feature integration and cross-level associative learning
  347. Prompt Readiness Levels (PRL): a maturity scale and scoring framework for production grade prompt assets
  348. A convolutional autoencoder and neural ODE surrogate modeling framework applied to transient counterflow flames
  349. Interpretable Predictability-Based AI Text Detection: A Replication Study
  350. Attention Residuals
  351. Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
  352. One CT Unified Model Training Framework to Rule All Scanning Protocols
  353. MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal
  354. Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization
  355. Consequentialist Objectives and Catastrophe
  356. TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models
  357. Empowering Chemical Structures with Biological Insights for Scalable Phenotypic Virtual Screening
  358. Pretraining and Benchmarking Modern Encoders for Latvian
  359. MONET: Modeling and Optimization of neural NEtwork Training from Edge to Data Centers
  360. How Log-Barrier Helps Exploration in Policy Optimization
  361. Thermal Image Refinement with Depth Estimation using Recurrent Networks for Monocular ORB-SLAM3
  362. Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos
  363. Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation
  364. Voronoi-based Second-order Descriptor with Whitened Metric in LiDAR Place Recognition
  365. Lightweight User-Personalization Method for Closed Split Computing
  366. SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning
  367. Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset
  368. FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data
  369. Spiking Layer-Adaptive Magnitude-based Pruning
  370. Ultra-Early Prediction of Tipping Points: Integrating Dynamical Measures with Reservoir Computing
  371. Intelligent Control of Differential Drive Robots Subject to Unmodeled Dynamics with EKF-based State Estimation
  372. Video-CoE: Reinforcing Video Event Prediction via Chain of Events
  373. Masked BRep Autoencoder via Hierarchical Graph Transformer
  374. Workflow-Aware Structured Layer Decomposition for Illustration Production
  375. Directional Routing in Transformers
  376. F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
  377. Bayesian Symbolic Regression for Missing Physics
  378. Spectrogram features for audio and speech analysis
  379. ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction
  380. Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs
  381. TopoVST: Toward Topology-fidelitous Vessel Skeleton Tracking
  382. Machine learning for sustainable geoenergy: uncertainty, physics and decision-ready inference
  383. ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation
  384. The impact of machine learning forecasting on strategic decision-making for Bike Sharing Systems
  385. BiTro: Bidirectional Transfer Learning Enhances Bulk and Spatial Transcriptomics Prediction in Cancer Pathological Images
  386. Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
  387. LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy
  388. Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models
  389. PASTE: Physics-Aware Scattering Topology Embedding Framework for SAR Object Detection
  390. SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras
  391. Customizing ChatGPT for Second Language Speaking Practice: Genuine Support or Just a Marketing Gimmick?
  392. RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation
  393. Seismic full-waveform inversion based on a physics-driven generative adversarial network
  394. A Hybrid AI and Rule-Based Decision Support System for Disease Diagnosis and Management Using Labs
  395. Developing an English-Efik Corpus and Machine Translation System for Digitization Inclusion
  396. IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
  397. A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems
  398. A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems
  399. Video Detector: A Dual-Phase Vision-Based System for Real-Time Traffic Intersection Control and Intelligent Transportation Analysis
  400. Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats
  401. From Horizontal to Rotated: Cross-View Object Geo-Localization with Orientation Awareness
  402. PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent
  403. Personalized Federated Learning with Residual Fisher Information for Medical Image Segmentation
  404. Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks
  405. Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
  406. ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
  407. Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling
  408. DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagery
  409. Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
  410. Halfway to 3D: Ensembling 2.5D and 3D Models for Robust COVID-19 CT Diagnosis
  411. Neural Networks as Local-to-Global Computations
  412. Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
  413. SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space
  414. Planning as Goal Recognition: Deriving Heuristics from Intention Models -- Extended Version
  415. RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving
  416. SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression
  417. Fold-CP: A Context Parallelism Framework for Biomolecular Modeling
  418. VorTEX: Various overlap ratio for Target speech EXtraction
  419. OpenReservoirComputing: GPU-Accelerated Reservoir Computing in JAX
  420. Universe Routing: Why Self-Evolving Agents Need Epistemic Control
  421. Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces
  422. Multi-Task Genetic Algorithm with Multi-Granularity Encoding for Protein-Nucleotide Binding Site Prediction
  423. Global Truncated Loss Minimization for Robust and Threshold-Resilient Geometric Estimation
  424. Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling
  425. GARCH-FIS: A Hybrid Forecasting Model with Dynamic Volatility-Driven Parameter Adaptation
  426. LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction
  427. Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making
  428. Orthogonal Subspace Clustering: Enhancing High-Dimensional Data Analysis through Adaptive Dimensionality Reduction and Efficient Clustering
  429. Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA
  430. High-Fidelity 3D Facial Avatar Synthesis with Controllable Fine-Grained Expressions
  431. Vietnamese Automatic Speech Recognition: A Revisit
  432. HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
  433. Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image
  434. AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
  435. POLCA: Stochastic Generative Optimization with LLM
  436. Understanding the geometry of deep learning with decision boundary volume
  437. Investigating the Impact of Speech Enhancement on Audio Deepfake Detection in Noisy Environments
  438. SSR: A Training-Free Approach for Streaming 3D Reconstruction
  439. Topology-Preserving Polygon Augmentation for Segmentation in Structured Visual Domains
  440. LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision
  441. Online Learning for Supervisory Switching Control
  442. Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark
  443. Learning Constituent Headedness
  444. Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization
  445. Efficient Event Camera Volume System
  446. Gauge-Equivariant Intrinsic Neural Operators for Geometry-Consistent Learning of Elliptic PDE Maps
  447. LLM-as-a-judge validity is strongly task-dependent across physics assessment formats
  448. GNNVerifier: Graph-based Verifier for LLM Task Planning
  449. Automated Diabetic Screening via Anterior Segment Ocular Imaging: A Deep Learning and Explainable AI Approach
  450. Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator
  451. GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation
  452. Beyond Creed: A Non-Identity Safety Condition A Strong Empirical Alternative to Identity Framing in Low-Data LoRA Fine-Tuning
  453. Multimodal Deep Learning for Early Prediction of Patient Deterioration in the ICU: Integrating Time-Series EHR Data with Clinical Notes
  454. Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention
  455. Towards Next-Generation LLM Training: From the Data-Centric Perspective
  456. AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers
  457. Fractal Autoregressive Depth Estimation with Continuous Token Diffusion
  458. AURORA-KITTI: Any-Weather Depth Completion and Denoising
  459. Design Space of Self--Consistent Electrostatic Machine Learning Interatomic Potentials
  460. Scaling Autoregressive Models for Lattice Thermodynamics
  461. Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation
  462. Applications of Intuitionistic Temporal Logic to Temporal Answer Set Programming
  463. MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model
  464. E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction
  465. Generalized Hierarchical Bayesian Segmentation with Irregular Designs, Multi-Sequence Hierarchies, and Grouped/Latent-Group Designs