mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 3 Aug 2026

569 papers

  1. StrataVLA: Hierarchical and Efficient 3D Geometric Grounding for Vision-Language-Action ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  2. Vectorization Of Narrow Matrix Multiplication for Ascend AI Inference AccelerationEfficient LLM inference and serving → Serving systems and request scheduling
  3. MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering ModelRetrieval-augmented generation → Privacy and security of RAG +1
  4. Towards the Harness of Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  5. ADIAS: Automated Design of Interactive Agentic SystemsLLM agents and tool use → Software engineering coding agents
  6. SubtleTalk: Generating Controllable Weakly-correlated Facial Dynamics for 3D Talking Heads via Residual Flow MatchingDiffusion models → Audio, speech and music
  7. A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and CombinationLLM safety and security → Vision-language and text-to-image safety
  8. SABRE: A Multi-Agent Approach for Selecting Out-of-Distribution Detectors Under a BudgetLLM agents and tool use → Multimodal and embodied agents
  9. ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action PoliciesVision-language-action models → Reinforcement learning and post-training
  10. Inverted Detection and Control in Steering VectorsMechanistic interpretability → Activation steering methods
  11. RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World ModelsWorld models → World models for autonomous driving +1
  12. SP3O: Reinforcement Learning from Segment Preferences without Reward ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  13. Rubrics as Privileged Information for Open-Ended GenerationKnowledge distillation → On-policy and self-distillation for LLMs
  14. ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
  15. OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  16. Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory SpeechLLM safety and security → Safety alignment, refusal and guardrails
  17. LACE: Large Language Model Aided Multi-Agent Framework for Agile RISC-V Instruction ExtensionLLM agents and tool use → Software engineering coding agents
  18. AnchorKV: Anchor-Residual KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  19. VeriTrace: Human-Like Temporal Exploration Completes Agentic Action SpaceLLM agents and tool use → Software engineering coding agents
  20. GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness AuditsLLM reasoning → Causal reasoning in LLMs
  21. BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQLLLM agents and tool use → Web, search, and research agents
  22. BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?LLM reasoning → Reinforcement learning for reasoning
  23. MutMem: Cryptographically Authorized Mutation in Persistent Agent MemoryLLM agents and tool use → Agent threats, guardrails and governance
  24. CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded ReasoningLLM reasoning → Multimodal reasoning +1
  25. In-Context Collapse in Vision-Language Models and How to Mitigate it?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. Emergence of Biased Consensus in Multi-Agent LLM DebatesLLM agents and tool use → Social simulation and multi-agent debate
  27. Improved Quantum Algorithms for Reinforcement Learning Under a Generative ModelDeep reinforcement learning methods → Quantum reinforcement learning
  28. Evading Chain-of-Thought Monitoring Through Model PoisoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  29. A Hyperfinite Framework for Score-Based Generative ModelingDiffusion models → Diffusion foundations and sampling
  30. Confident but Unreliable: A Behavioral Safety Audit of Vision-Language Models on Brain MRIMultimodal LLMs / vision-language models → Medical vision-language models
  31. Stateful Governance for Concurrent Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
  32. Everyone Conforms, No One Believes: Pluralistic Ignorance in LLM Agent PopulationsLLM agents and tool use → Social simulation and multi-agent debate
  33. Quo Vadis, World Modeling?World models → World models for language agents
  34. Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware OperatorsLLM agents and tool use → Software engineering coding agents
  35. Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal ApproachLLM agents and tool use → Agent threats, guardrails and governance
  36. Output-Aware Rotation for INT2 KV-Cache QuantizationEfficient LLM inference and serving → KV cache quantization
  37. PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
  38. S3: Improving Agent Safety through Multi-Stage DefenseLLM agents and tool use → Agent threats, guardrails and governance
  39. Safety in Batches? Understanding and Mitigating Safety Failures in Batch PromptingLLM safety and security → Safety alignment, refusal and guardrails
  40. TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic WorkflowsLLM agents and tool use → Software engineering coding agents
  41. WorldExam: Benchmarking World Models from Apparent Appearance to Inherent ReactivityWorld models → Video-generation world models and simulators
  42. AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language ModelingDiffusion models → Discrete and text diffusion
  43. GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent ReasoningLLM reasoning → Test-time compute and efficient thinking
  44. UEmbed: Unified Sparse and Dense Multimodal EmbeddingsRetrieval-augmented generation → Generation and context integration
  45. ACEM: A Cost Estimation Model for Agentic Software EngineeringLLM agents and tool use → Software engineering coding agents
  46. CoWAM: Coordination Contracts for Selective Policy Intervention with WAMsWorld models → Embodied and robot world models
  47. Noise in Diffusion Models Is a Learnable InputDiffusion models → Diffusion foundations and sampling
  48. AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane PoliciesLLM agents and tool use → Software engineering coding agents
  49. Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State InjectionRetrieval-augmented generation → Generation and context integration +1
  50. A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  51. Analytic Planning under Uncertainty with Moment ClosureDeep reinforcement learning methods → RL theory and sample complexity
  52. RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility StatesLLM agents and tool use → Agent memory systems +1
  53. Token Radius Attention for Efficient Video GenerationDiffusion models → Video generation
  54. CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum OrthogonalizationDiffusion models → Diffusion foundations and sampling
  55. SWE-Touch: Benchmarking Coding Agents When Users Touch the CodeLLM agents and tool use → Software engineering coding agents
  56. Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  57. Computational and Statistical Guarantees of the textitc-Rectified flowDiffusion models → Flow matching, time series and science
  58. Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMsMechanistic interpretability → Knowledge and representations inside LLMs
  59. EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video GenerationDiffusion models → Video generation
  60. Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage AssessmentLLM reasoning → Multimodal reasoning +2
  61. Real-Time Detection and Repair of LLM Agent FailuresLLM agents and tool use → Software engineering coding agents
  62. Infinite Trace Objectives with Finite Trace Techniques: Translating LTL to LTLf+Deep reinforcement learning methods → Interpretable and logic-guided RL
  63. MoRAL: Sensor-Grounded BEV Reasoning for Compact VLMs toward Edge-Oriented Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  64. Advancing Relevance Measurement with Vision-Language Models for Web-Scale SearchMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  65. ParEvalLayer: When Partial LLM-Agent Evaluations Support a DecisionLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science BenchmarksLLM reasoning → Mathematical reasoning
  67. Agentic Commerce World: An Auditable and Verifiable Environment for Vibe CommerceLLM agents and tool use → Social simulation and multi-agent debate
  68. xPress: Parallel Refinement for Diffusion Drafters in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  69. Foundations of Reinforcement Learning and Control:Connections and New PerspectivesDeep reinforcement learning methods → RL theory and sample complexity
  70. DF3: World Modeling via Decoder-Free Feature Forecasting in Autonomous NavigationWorld models → World models for navigation
  71. Agentic Incident Response through Digital Twin-Enhanced Multiscale PlanningLLM agents and tool use → Agent threats, guardrails and governance
  72. Antares: Foundation Models for Agentic Vulnerability LocalizationLLM agents and tool use → Agent threats, guardrails and governance
  73. A Unified Kullback--Leibler Divergence Analysis of Generative Diffusion Models via Entropy Production RateDiffusion models → Diffusion foundations and sampling
  74. USP-Mamba: Unmixing-Derived Spectral and Structural Prompting for Hyperspectral Image Super-ResolutionState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  75. Cooperative Coevolution for Resource-Constrained Agentic LLM Post-TrainingLLM reasoning → Reinforcement learning for reasoning +1
  76. Chess on Ice: Curling Tactical Decision-Making via Backward Induction and Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  77. Faster-WAM: Do World Action Models Need Deep Action Modules?World models → Embodied and robot world models
  78. ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next StepLLM agents and tool use → Tool learning and function calling
  79. SkillTrace: Traversing a Query-Skill Graph for Composable LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  80. Global Optimization and Inference-Time Region Grafting for Agentic WorkflowsLLM agents and tool use → Software engineering coding agents
  81. KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model ImprovementLLM agents and tool use → Web, search, and research agents
  82. Mamba with Hierarchical Memory: Solving Representation Bottleneck in Long Sequence ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  83. Loop-Mamba: A Loop Mamba with Degradation-Aware and Shared Memory for Old Photo RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
  84. Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic ExperimentationLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  86. ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  87. MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4LLM agents and tool use → Educational agents and math problem solving
  88. SKT: Skill-Use Training at Scale via Verified Synthetic Data GenerationLLM agents and tool use → Agent skill learning and evolution
  89. Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure TrajectoriesLLM agents and tool use → Software engineering coding agents
  90. Open-Set Visual Text Forensics via Sparse-Constraint Rectified FlowDiffusion models → Image generation, text-to-image and editing
  91. Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body TeleoperationVision-language-action models → Human-video and latent-action pretraining
  92. HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled ExpertsMultimodal LLMs / vision-language models → Medical vision-language models
  93. Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair SchedulingEfficient LLM inference and serving → Serving systems and request scheduling
  94. PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready OutputsLLM agents and tool use → Multimodal and embodied agents
  95. VC-Tooler: Learning Compositional and Adaptive Visual Tool UseLLM reasoning → Multimodal reasoning +1
  96. Local Margin Restoration for Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  97. Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
  98. MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  99. Microscopic dynamics of consensus formation in multi-agent LLM Naming GamesLLM agents and tool use → Social simulation and multi-agent debate
  100. CARNet: Channel-Adaptive Receiver Network for Robust NextG CommunicationsMixture-of-experts → Expert routing strategies
All 569
  1. From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM AgentsLLM agents and tool use → Agent memory systems
  2. Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional FingerprintsKnowledge distillation → Federated, robust and private distillation
  3. Fourier-Latent Diffusion for Constrained Generation of Triply Periodic Minimal SurfacesDiffusion models → Flow matching, time series and science
  4. PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMsWorld models → Latent predictive world models
  5. Beyond the Mean: Multi-Moment Policy Optimization for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  6. Self-Improving Large Language Models via Progressive Experience EvolutionSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  7. Two Sides of the Same Coin: Co-Evolving Search for Cross-Task Attacks on Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  8. Messages, Not Tokens: Grounded Coresets for Faithful VLM CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  9. HAFI-VLM: A Frequency Perspective for Diagnosing and Enhancing Visual Perception in Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  10. From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  11. MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM AgentsLLM agents and tool use → Agent memory systems
  12. IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent FluctuationsDeep reinforcement learning methods → RL training of language and agent models
  13. Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text CompressionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  14. Cross-Domain Hybrid OPD for Generalizable Search AgentsLLM agents and tool use → Web, search, and research agents +2
  15. How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  16. Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned PolicyKnowledge distillation → On-policy and self-distillation for LLMs +1
  17. CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  18. STEAM: A Spatio-TEmporal Alignment Mixture-of-Experts Model with Hierarchical Pre-training for EEG DecodingMixture-of-experts → Medical and biomedical MoE
  19. Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. MIEScore: Human-Aligned Evaluation for Multi-Source Image EditingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  21. SCOPE: Entanglement Frontier Escape for Source-Free Class UnlearningLLM safety and security → Machine unlearning
  22. RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  23. Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  24. DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  25. HPFA: Hypergraph-Based Paired Failure Attribution for LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  26. EduZone: A Framework for Evaluating LLM Safety for K-12 Students and TeachersLLM safety and security → Safety alignment, refusal and guardrails
  27. Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  28. Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAGLLM reasoning → Knowledge- and tool-augmented reasoning +2
  29. HALT: Verification-Aware Stopping for Retrieval-Augmented Search AgentsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  30. Evolving in the Agent Jungle via History-Informed Opponent AwarenessLLM agents and tool use → Agent skill learning and evolution
  31. TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  32. Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case StudyLLM agents and tool use → Agent memory systems
  33. SPARE: Structural Parameter-Free Affinity Regularization for Flow MatchingDiffusion models → Flow matching, time series and science
  34. DiffPrune: differentiable information throttling for token pruning in vision-language modelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  35. AdaThinkV: Adaptive Thinking for Token-Efficient Video ReasoningLLM reasoning → Multimodal reasoning
  36. ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  37. Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait AnimationDiffusion models → Audio, speech and music
  38. Music Restoration via Latent Operator Optimization and Diffusion Model PriorsDiffusion models → Audio, speech and music
  39. LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. Agentic Self-Healing for Data and AI Pipelines: An Affordable Vendor-Agnostic Architecture using Open-Source SoftwareLLM agents and tool use → Software engineering coding agents
  41. StyleForge: Indoor Furniture Styling by Counterfactual Reasoning in a Hypergraph FieldLLM reasoning → Spatial and embodied reasoning
  42. Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy DistillationLLM agents and tool use → Reinforcement learning for LLM agents +1
  43. A Self-Triggered Agentic Push Recommendation SystemLLM agents and tool use → Agentic recommender systems
  44. Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-ReflectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code GenerationRetrieval-augmented generation → RAG for code
  46. ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal ReachingWorld models → Latent predictive world models
  47. TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary MemoryLLM reasoning → Multimodal reasoning
  48. HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent HarnessesLLM agents and tool use → Software engineering coding agents
  49. Finite-Time Analysis of Discounted Exponential-Utility Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  50. PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  51. CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search AgentsLLM agents and tool use → Web, search, and research agents +1
  52. SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  53. GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth ObservationDiffusion models → Inverse problems and image restoration
  54. Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency ScalingEfficient LLM inference and serving → Serving systems and request scheduling
  55. World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous DeploymentWorld models → Embodied and robot world models
  56. ReasonCast: Towards Explainable Time Series Forecasting with ReasoningLLM reasoning → Time series reasoning
  57. CRISP: Critical Step Perception for Training Efficient Deep Search AgentsLLM agents and tool use → Web, search, and research agents
  58. EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change CaptioningDiffusion models → Inverse problems and image restoration
  59. Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  60. Decoupling semantics from vision: A framework for faithful visual-text compression evaluationEfficient LLM inference and serving → Visual token pruning in multimodal models
  61. HyperAgent4POI: Dynamic Semantic Message Passing on Multi-Agent Hypergraphs for Missing-Modality RecommendationLLM agents and tool use → Agentic recommender systems
  62. WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World ModelWorld models → Latent predictive world models
  63. PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  64. DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal AgentsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  65. Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA PoliciesVision-language-action models → 3D and spatial-aware VLA
  66. PartMat: Material-Aware 3D Part Decomposition with a Single Global LatentDiffusion models → 3D, point cloud and scene generation
  67. SearchMaster: Grounded and Regulated Self-Play for Search AgentsLLM agents and tool use → Web, search, and research agents +1
  68. DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  69. CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent CockpitsLLM agents and tool use → Agent threats, guardrails and governance
  70. ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly DetectionDiffusion models → Flow matching, time series and science
  71. Can You Trust the Confidence? ConfBench for Vision-Language Models on Document ExtractionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  72. PICopilot: An LLM-based Agentic Framework for Assisting Photonic Integrated Circuit Design via Script GenerationLLM agents and tool use → Software engineering coding agents
  73. REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +2
  74. FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise WorkflowsLLM agents and tool use → Agent threats, guardrails and governance
  75. DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving TestingEnd-to-end autonomous driving → Generative simulation for driving
  76. Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  77. Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMsLLM reasoning → Chain-of-thought reasoning for driving +3
  78. Can Urban Blight Be Accessed with Vision-language Models: A Case Study in DetroitMultimodal LLMs / vision-language models → Agricultural vision-language models
  79. RL-Lock: Reinforcement Learning for Generating Interlocking AssembliesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  80. MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  81. Disagree to Accelerate: Closing the Loop on Diffusion Feature ForecastsDiffusion models → Diffusion foundations and sampling
  82. CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM AgentsLLM agents and tool use → Agent memory systems
  83. X-KGRank: A Knowledge Graph RAG Framework for Explainable Recommendations via Pattern Mining and LLM Re-RankingRetrieval-augmented generation → RAG for recommendation
  84. MNC: Scope-Bound Semantic Declassification for Private LLM-Agent CommunicationLLM agents and tool use → Agent threats, guardrails and governance
  85. LaCache: Robust Semantic Caching for LLM ServingEfficient LLM inference and serving → KV cache optimization
  86. Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  87. Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They CatchLLM agents and tool use → Software engineering coding agents
  88. Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic HarnessLLM agents and tool use → Web, search, and research agents
  89. Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent ActionsLLM agents and tool use → Agent threats, guardrails and governance
  90. SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  91. PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized AgentsLLM agents and tool use → Agent memory systems
  92. Beckmann Transport Models: From Autonomous Flows to One-Step MapsDiffusion models → Flow matching, time series and science
  93. GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis TasksLLM agents and tool use → Web, search, and research agents
  94. When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation BoundaryLLM agents and tool use → Agent memory systems
  95. Progressive Agent Skill Generation via Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution +1
  96. TCPO: Turn-Level Credit Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  97. Allocation Before Ranking: Decoupled Token Compression for OmniLLMsEfficient LLM inference and serving → Audio and omni-modal token compression
  98. FAU at ImageCLEF 2026 Task on Multimodal Reasoning Robust Candidate Scoring and Concise Multilingual Visual AnsweringLLM reasoning → Multimodal reasoning
  99. SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive CorrectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  100. Bole: Efficient Tree Speculation for Hybrid-Attention Language ModelsEfficient LLM inference and serving → Speculative decoding
  101. GISAgentBench: A Practitioner-Sourced Benchmark for Evaluating LLM Agents on GIS TasksLLM agents and tool use → Multimodal and embodied agents
  102. CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  103. Dynamic Resolution Routing for Efficient Egocentric GroundingEfficient LLM inference and serving → Visual token pruning in multimodal models
  104. Salami Attack: Stealthy Collusive Memory Poisoning against OpenClawLLM agents and tool use → Agent threats, guardrails and governance
  105. Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  106. Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache CompressionEfficient LLM inference and serving → Efficient reasoning and agent inference
  107. RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge InjectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
  108. Human-LLM Alignment in Language Attitudes Toward Non-Native JapaneseLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  109. SMM Transformer: Leveraging Spiking Neural Networks for Multimodal TasksMixture-of-experts → Multimodal MoE models
  110. When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent ResponsesLLM agents and tool use → Agent memory systems
  111. Linear Multi-Timescale Retention as a Memory-Efficient Vision-Language BridgeMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  112. AffordTrajDP: Dynamic Affordance-Guided Visuomotor Policy Learning for Robotic ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  113. HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement LearningKnowledge distillation → On-policy and self-distillation for LLMs +1
  114. Latent Thought Credit: Multi-Answer Credit Assignment for Latent ReasoningLLM reasoning → Test-time compute and efficient thinking
  115. Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled ReasoningKnowledge distillation → On-policy and self-distillation for LLMs
  116. Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal referenceLLM reasoning → Test-time compute and efficient thinking
  117. Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  118. FedWorld: Scope-Aware Federation of Agent World ModelsWorld models → World models for language agents +1
  119. Securing Agentic AI: From Per-Action Checks to Trajectory AssuranceLLM agents and tool use → Agent threats, guardrails and governance
  120. Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated LearningLLM reasoning → Reinforcement learning for reasoning +1
  121. Large Language Models Exhibit Human-Like Bayesian Hypocrisy
  122. ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs
  123. Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization
  124. Domain-Adaptive ASR for Telephony AI Agents: Fine-tuning Canary Flash Models for Enterprise Contact Center Applications
  125. ODG-NoMaD: Overhead-Camera Direction-Guided NoMaD
  126. When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models
  127. Language Models for Portuguese: A Systematic Mapping Study
  128. Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection
  129. A Human Audit of OpenAIs AI-Generated Mathematical Proofs
  130. Continual Evolution Strategies in Control Tasks
  131. EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents
  132. Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier
  133. Temporal Generalization in fNIRS-Based Autism Classification: A Cross-Time-Window Transfer Benchmark
  134. The Field Knows: Cross-Dimensional Geometry from Navigation to Black Holes
  135. What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems
  136. Coarse-to-Fine Registration of Jawbone CT and Intraoral Scan Data Using GeDi and ICP with Pseudo-IOS Ground Truth
  137. Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models
  138. TransSLR: A Lightweight Transformer for Sign Language Recognition
  139. Deep Evidential Regression for Sparse Forest Height Estimation from Multimodal Satellite Imagery
  140. UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys
  141. CLARA: Clarification of Language Ambiguity through Result Analysis for Natural-Language Cancer Genomics Queries
  142. Reconstructing Persistent Worlds from Narratives for Narrative-Grounded Interactive Experiences
  143. CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers
  144. Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks
  145. A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics
  146. Material-Segmented Per-Pixel Emissivity Correction for Thermographic Anomaly Detection in Cultural Heritage Digital Twins
  147. Scaling an Autoregressive Transformer for Single-Cell Generation
  148. Chat Debugging: An Exploratory Study of Human-AI Collaboration to Debug Analog Circuits
  149. Schedule-Informed Temporal Fusion Forecasting of Hourly Airport Security-Checkpoint Throughput
  150. On the missing data layer and a potential solution
  151. Sedentary Behavior Classification for Wearable Sensors with a CNN-BiLSTM Model
  152. When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning
  153. Federated generative event models for tokenized electronic health records
  154. When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index
  155. ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
  156. Character Iconicity vs. Arbitrariness: An Arabic NLP Perspective
  157. Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning
  158. Calibrated Bayesian Inference for Stochastic Intervention Effects
  159. FLARE: Few-shot Learning-based Adaptive Reflective Engine
  160. Forecasting Revenue with its Customer-Base Drivers: When and Why Coordination Helps
  161. When Predictions Become Regressors: A Split-Sample Correction for Biases in Downstream Inference
  162. Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering
  163. Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models
  164. Modeling Scientific Experiment Scenes: Dataset and Model
  165. Population-Robust Feature Selection via Generalized Welfare Optimization
  166. Test Time Adaptation Methods for Point Cloud Registration in Laparoscopic Surgery
  167. Field-Aware Agent Skill Retrieval
  168. Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes
  169. Maglev: Sliding Recurrent Memory
  170. Contrast-invariant deep ptychography neural networks
  171. Adaptive Sampling for Automated Post-Disaster Rapid Damage Assessment via Level-Set Cost-Aware Bayesian Optimization
  172. NOMADD: Numerical Optimization of Models Adapting to Data Drift
  173. Particle-based Generalised Stochastic Optimisation
  174. Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews
  175. A Human-in-the-Loop Deep Learning Framework for Color Reconstruction of Lenticular Films
  176. Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
  177. Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling
  178. Topological Simplification in Predictive Coding Networks
  179. Learning a Vector-Symbolic Model for Socio-Cultural Tasks
  180. Fast Object Removal Attacks on Safety-Critical Video-based Perception Systems
  181. A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
  182. Detecting high-frequency brain disorder signals using dynamic mode decomposition from EEG
  183. SAGE: Semantic Explainability of Attention-Based Survival Models in Computational Pathology
  184. PixelUp: Zero-Shot Semantic Feature Upsampling for Fine-Grained Vision Tasks
  185. Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
  186. Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment
  187. Neural Networks with Local Converging Inputs for Efficient Options Pricing Models
  188. Tight Information Complexity of the Coin Problem in the Broadcast Model
  189. Towards a new paradigm of scientific discovery with socialized artificial intelligence
  190. Privacy-Preserving AI Verification via Minimal Information Disclosure
  191. DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing
  192. Oh Deer, How Should I Handle This? Seasonal Priors for Selective Wildlife Annotation and Classification
  193. Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents
  194. Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
  195. Escaping Oversquashing: Addressable and Support-Aware Global Memory for Message Passing Networks
  196. Can Training Logs Make Model Comparisons More Precise?
  197. Predictive Set Theory: A Generative Framework for Cognitive Architecture with Operationalized Core Mechanisms
  198. ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
  199. NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory
  200. Explainable AI for the EU Right to Explanation: A Systematic Review of the Law-XAI Translation Gap
  201. Measuring Explainer Stability via Attribution Separability
  202. Stylometric Defenses Against Author Impersonation in Software Repositories
  203. Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation
  204. PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification tasks
  205. GLOBE: Trajectory-Aligned Gradient Matching with Structured SparseOptimization for Coreset Selection
  206. Stuck on "A": Diagnosing and Repairing Interface Injury in Attention-to-KDA Linearization of a 0.6B Language Model
  207. Learning Molecular Representations from Cellular Phenotypes with Structure Preservation
  208. BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests
  209. A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models
  210. Bridging Artificial Intelligence and Power Systems Education Using a Hands-On Executable Framework
  211. VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification
  212. onepot-Bench 0: towards lab-aware in silico chemistry benchmarks
  213. CAPEval: A Decoupled Caption Evaluation across Understanding and Generation
  214. The Condition-Number Barrier in Sparse Least Squares
  215. Smooth Reparameterizations of Functions on Simplicial Product Spaces: Applications to Probabilistic Tensor Decomposition and Functional Data Registration
  216. ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment
  217. Benchmarking Sheaf Neural Networks for Inductive Tasks
  218. Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation
  219. Who Should Be Generated? Justifying Demographic Targets in Open-Ended Generation
  220. Estimating SSIM from MSE for DCT-Based Compressed Images via Modeling Local Error Statistics
  221. A Simple Approximation to the Distribution of the Ridge Regression Estimator
  222. Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation
  223. Optimal Unambiguous DNFs and Alon-Saks-Seymour
  224. Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
  225. MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs
  226. Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation
  227. LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
  228. Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies
  229. Beyond Modern Asymptotics for Log-Likelihood Ratios in Logistic Regression
  230. Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation
  231. DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
  232. Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions
  233. Fermat Active Laplace Learning for Semi-Supervised Hyperspectral Image Classification
  234. Private Generative Bootstrap via Blocking
  235. CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMs
  236. Action-grounded tissue affordance enables anticipatory auto-framing that lowers surgeon cognitive workload during laparoscopic surgery
  237. Calibrated Similarity and Graph Clustering for Open-Set Animal Re-Identification
  238. ISRS-DETR: Detection-Guided Click Propagation for Remote Sensing Interactive Segmentation
  239. Syntax Meets Semantics: Understanding Scientific Formulae
  240. Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees
  241. UAV-Based Environmental Monitoring of Rip-Current Indicators Using Wavelet-Derived Texture Features
  242. Intention Inference Under Execution Noise: Separating Aleatoric and Epistemic Uncertainty in Social Dilemmas
  243. InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
  244. Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
  245. Wasserstein mixing time of the unadjusted Langevin algorithm
  246. Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
  247. Why Large Language Models Fail at Tabular Prediction
  248. Human-Centered Reflections on Care Robots: A Comparative Study of Caregiver Perspectives
  249. MonitrLLM: A Community-Centered Evaluation Infrastructure for Large Language Models
  250. Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data
  251. Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry
  252. From fragmented data to actionable design: Physics-calibrated learning for plastic upcycling
  253. Network Information Enhances Unreliable News Domain Detection
  254. Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification
  255. Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
  256. GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience
  257. Gecko: Fast Private Inference via Secure Public Encoder Offloading
  258. Token-Native Storage: Read and Write in your Agent's Language
  259. A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems
  260. PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise
  261. GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation
  262. Fast and Accurate Quotation Attribution in Literary Texts
  263. Qwen-CUA: Native Computer Use for (almost) Everything
  264. Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning
  265. Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection
  266. Context-Aware Mixture of Domain Experts for Bodily Expression of Emotion in the Wild
  267. Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation
  268. Global-Scale Self-Supervised Spatiotemporal Learning for NDVI Time-Series Reconstruction
  269. FastGFDs: Efficient Validation of Graph Functional Dependencies with Desbordante
  270. TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks
  271. GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation
  272. An Evidence-Grounded Retrieval-Augmented Transformer Framework for Health Misinformation Verification
  273. CalibBEV: LiDAR-Camera Calibration via BEV Alignment
  274. The Push-Forward Transform for Continuous and Robust Comparison of Dynamic Shapes
  275. BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition
  276. TRACE: Ergodic Trajectory Optimization for Active Scene Reconstruction
  277. Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit
  278. A General-Purpose VLM Can Teach an Astronomy Foundation Model to Better Recognize Galaxy Morphology
  279. Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
  280. SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning
  281. Extended Field of View Analysis for VideoGAN-based Trajectory Generation
  282. Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration
  283. EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass
  284. A Multi-Objective AutoML-based Efficient Intrusion Detection System for EV Charging Networks
  285. Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
  286. TS-MAMP: A Remanufactured Agricultural Robot with Second-Life EV Components and NMS-Free On-Device Weed Detection
  287. Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss
  288. Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
  289. Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning
  290. An Accessible Solution for Deformable Image Registration Compared with Learning-Based Approaches
  291. Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability
  292. GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
  293. Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study
  294. Constrained Co-Design for Photonic Bayesian Neural Networks
  295. CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning
  296. VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting
  297. Fast Discovery of Inclusion Dependencies with Desbordante
  298. Self-supervised DXA representations encode multi-system disease risk, biological aging and heritability
  299. CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution
  300. RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures
  301. T2exture: Sparsely Perturbed Thermal-to-Texture Imaging
  302. DerainSplat: Feed-Forward Clean 3D Gaussian Splatting from Sparse Rainy Views
  303. Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval
  304. SPIRIT: Spatio-temporal Pairwise Relational Modeling of Instrument-Tissue Interactions for Surgical Action Triplet Recognition
  305. PAC Approximation and DIRECT Optimization for Parametric Markov Models
  306. SWINSleepNet: A Hierarchical Context-Aware Framework for Sleep Staging (v2)
  307. Start Classifying: Categorical Critics for LLM Reinforcement Learning
  308. GSRAIN: Physically Calibrated High-/Low-Frequency Rainfall Synthesis for 3D Gaussian Driving Scenes
  309. Randomized Algorithms for Learning Partitions with Near Optimal Query Complexity in Constant Rounds
  310. Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning
  311. From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution
  312. Lossless Tensor Compression as Program Synthesis
  313. AdaForensics: Learning A Characteristic-aware Adaptive Deepfake Detector
  314. RamanPFN: learning from Raman spectral structure with a tabular foundation model
  315. Douyin Multimodal Embedding Model Technical Report
  316. UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
  317. Quaternion Tensor Modeling for Joint Color-Polarization Demosaicking
  318. Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering
  319. HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams
  320. The Role of Disfluencies in Speech Translation
  321. Cardiovascular Digital Twins from Physics Based to Data Driven Approaches
  322. PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning
  323. CoRe-GNN: Multilevel Message passing on Coarsened graphs
  324. Do Static Embeddings Add Value to Hybrid Dutch Retrieval?
  325. Uncertainty-Aware Crossmodal Fusion for Classification of Animal Behavior
  326. From Information to Delegation: Mapping Human-AI Financial Decision Making
  327. DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization
  328. Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents
  329. Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition
  330. One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse
  331. An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting
  332. Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context
  333. A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study
  334. Isotonic Bradley-Terry Model for Paired Comparison Data
  335. Accelerating Evolutionary Strategy via Rao-Blackwellizing Realization of Uncertain Input
  336. Feed-Forward Steering in Transformer Residual Dynamics
  337. GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimation
  338. Geometry-Guided Layerwise FFN Width Allocation in Transformers
  339. Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification
  340. A Comparative Analysis of MLP and Kolmogorov-Arnold Networks (KAN) for Faster-than-Nyquist (FTN) Signaling Detection
  341. TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval
  342. Protocol generalisation for brain tissue microstructure estimation via hypernetwork-controlled geometric deep learning
  343. Secrets Everywhere: Auditing Memorization in Mobility Prediction Models
  344. TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention
  345. Adaptive Reconstruction of Bosonic Quantum States
  346. CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship
  347. Mapping melliferous tree species in Kenya via one-class classification with hyperspectral unsupervised domain adaptation
  348. D'ej`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates
  349. Convex Neural Energy Elements: Monolithic Finite-Element Assembly of Geometry-Parameterized Neural Operators with Stability and Error Guarantees
  350. Learning-Based Collaborative MEC for LLM Inference with Soft-Deadline Awareness via Transformer-Enhanced PPO
  351. Scikit-fingerprints: Python library for scikit-learn compatible molecular fingerprints and chemoinformatics
  352. Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling
  353. MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping
  354. ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment
  355. AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization
  356. Grounding and Explaining Visual Evidence for AI-Generated Image Detection in Human-Centric Scenes
  357. SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation
  358. Detecting Nonproperness of Likelihood Equations
  359. TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference
  360. Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis
  361. ChaosProbe: A Neurochaotic Lens on Frozen Transformer Input-Embedding Spaces
  362. OSSDD - a New Open Dataset for Sentinel-1 Ship Detection
  363. FAST-GS: Frequency Aware Space-time Gaussian Splatting for Photorealistic Dynamic Novel View Synthesis
  364. Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding
  365. Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory
  366. UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation
  367. CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation
  368. A Contractualist Argumentation Framework for Moral Decision-Making
  369. Semantic Networks as Clues: A Theoretical Foundation and Process Optimization for Semantic Network Construction
  370. Automatic Annotation of Ancient Greek Vowel Length
  371. TransNRank: Towards Accurate Neoantigen Ranking with Transformer
  372. CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM
  373. Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents
  374. Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagery
  375. PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph
  376. Understanding and Correcting Low-Frequency Bias in EEG Foundation Model
  377. Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement
  378. CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection
  379. Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models
  380. LAB-Tab: LLM-Augmented Bayesian Network Adaptation for Few-Shot Tabular Generation
  381. Transformer Geometry Observatory TGO-III: Semantic Geometry Observatory
  382. No One Wins in Nuclear War: A Social Simulation of Military Decision-making
  383. Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study
  384. Probabilistic Deep Learning for Drought Forecasting: Role of Internal Climate Variability
  385. Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge
  386. Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting
  387. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
  388. Physics-Informed Neural Networks for Complex Eigenfrequency Identification and Mode Structure Reconstruction of the Ground-State ITG Branch
  389. FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling
  390. tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital Twins
  391. Rewriting or Reweighting? A Geometric Account in Language Models
  392. Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping
  393. MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration
  394. Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
  395. Reassessing the Feasibility of PPG-Based Non-Invasive Blood Glucose Level Estimation
  396. Predictive Maintenance: Deep Learning-Based Remaining Useful Life Prediction for Combat Aircraft Engines
  397. Divergent large language model predictions from convergent representations in ambiguous word pairs
  398. RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation
  399. SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis
  400. Parameter-Dynamic Adaptive Fusion and Calibration Network for RGBT Tracking
  401. LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation
  402. CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning
  403. Illuminating Visual Identity in Universal Multimodal Embeddings
  404. Radar Detection in the CBRS Band: Techniques, Challenges, and Future Directions
  405. Investigating Social Bias in Narrative Image Generation
  406. Multi-Source Dynamic Graph Learning for Compound-Flood Forecasting in Managed Coastal Systems
  407. LiveLight: Real-time Streaming Video Relighting with Interactive Control
  408. Leveraging AI for fine-grained food safety risk forecasting in sparse data conditions
  409. EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming
  410. Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM
  411. Constructing Parallel Multidimensional Chromatic Lexicons for Corpus-Assisted Analysis of Russian and English Texts
  412. SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
  413. Heterogeneous Multi-Agent Reinforcement Learning for Radio Resource Management under Coupled Finite-Horizon Constraints
  414. Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning
  415. IDraw: Artist Verification from Digital Drawing Images
  416. DAPD: Dual-Anchored Policy Distillation
  417. LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses
  418. Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
  419. G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors
  420. CENTILE: A Telemetry Foundation Model Evaluated by the Decisions It Drives
  421. TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics
  422. When Extreme Darkness Meets Motion Blur: MeanFlow for Unified RAW Restoration
  423. STC-Net: Electroluminescence-Based Solar Cell Crack Segmentation for Power Loss Estimation
  424. UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
  425. Rethinking Generative AI Literacy: An Integrative, Developmental, and Dialectical Framework for K-12 Teacher Education
  426. Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?
  427. Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting
  428. ARM: Detector-Agnostic Changepoint Attribution with Finite-Sample Error Control
  429. ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions
  430. Generative AI and Foundation Models in Medical Image
  431. Generative Brownian Bridge Diffusion In Motion Space For Enhanced Myocardial Strain Analysis
  432. Understanding Sparse Attention Selectivity in Long-Context Foundation Models via Counterfactual Evaluation
  433. Learning What to Remember: Test-Time Training via Context Distillation
  434. Sharp Root Anti-Concentration via Projective Incidence and Ordered Root Laws
  435. Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation
  436. Few-Shot Concept Prompt Learning for Segmentation Foundation Models via Visual Grounding
  437. LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing
  438. FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection
  439. Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering
  440. StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting
  441. Non-KKT Accumulation in Entropic Mirror Descent
  442. Approximate Message Passing with Random Initialization for Phase Retrieval
  443. Evaluating Forecasting Techniques for Hardware Errors on a Large-scale HPC System
  444. StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
  445. AI-assisted Script Management for Requirements Elicitation Interviews
  446. GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution
  447. Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
  448. QWRF-Net: A Quantum-Wavelet Framework with Rectified Flow for Short-Term Precipitation Nowcasting
  449. Not the Dimension, the Norm: What Matters in Gradient-Free Weight Perturbation of Language Models
  450. Online Algorithms via Minimax and Posterior Matching
  451. Thermalizing Stochastic Programs
  452. Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer
  453. When Measurement Conventions Masquerade as Calibration Gains in Cardiac Digital Twins
  454. Latent-Regime Bias Auditing for Volatility Forecasting
  455. PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledge
  456. D^2-4DGS: Dual-Depth Guided Sparse-Camera 4D Gaussian Splatting
  457. The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning
  458. Statistical comparisons of time-series feature sets on classification tasks
  459. Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer
  460. LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical Systems
  461. Enhancing Visual Perception in Foggy Conditions via Multiclass Fog Density Modeling
  462. Characterizing Treatment-Context Medication Evidence Across Clinic Notes and Structured EHR Medication History
  463. DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering
  464. Meganeura: Portable GPU Training and Inference through Vulkan and Metal
  465. Discriminative Axis, Not Data Volume: What a Contrastive Corpus Teaches an Audio Embedding
  466. Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Controlled Negative Result
  467. Generalized Quadratic Gradient: A New Direction in Optimization via the Fusion of Positive-Definite Curvature Matrices and Gradients into A Unified Framework
  468. LLM Capability Limits: Static Emergence and Dynamic Boundary Control
  469. Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models