mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 18 Aug 2026

381 papers

  1. Groundbench: Multi-Resolution Polygon Grounding Exposes the Geometry Gap in Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  2. LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour LawRetrieval-augmented generation → Legal and financial RAG
  3. Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot ManipulationDiffusion models → Diffusion and flow policies for robotics
  4. Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent FlowsDiffusion models → 3D, point cloud and scene generation
  5. PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM ContextsLLM agents and tool use → Software engineering coding agents +1
  6. Test-time Reinforcement Learning for Anomalous Video UnderstandingDeep reinforcement learning methods → RL training of language and agent models
  7. CoEvo: Oracle-Grounded Self-Evolution of a Single Model for Multi-Step Causal ReasoningLLM reasoning → Causal reasoning in LLMs
  8. Beyond the Text: Verifying That Agent-Written Papers Are Backed by Their ArtifactsLLM agents and tool use → Web, search, and research agents
  9. Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate AnalysisRetrieval-augmented generation → RAG robustness and adaptive retrieval
  10. Geo-VLA: Geometry-Aware Vision-Language-Action Planning via Internalization of Map SemanticsVision-language-action models → VLA for autonomous driving +1
  11. WorldMind: Decoupled Game World Model for State-Aware NPC BehaviorWorld models → Video-generation world models and simulators
  12. DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal ReasoningLLM reasoning → Spatial and embodied reasoning
  13. The Evaluation Context Protocol (ECP): A Portable Contract for AI Agent EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving TransformationsLLM agents and tool use → Software engineering coding agents
  15. Depth Anything V4: Dynamic 4D Scene Reconstruction via Riemannian Flow Matching on 4D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  16. TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMsKnowledge distillation → Multimodal distillation
  17. One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  18. Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP AgentsLLM agents and tool use → Agent threats, guardrails and governance
  19. From Inference to Adaptation: A Unified Optimal Transport View of Vision Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  20. SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  21. XRF-to-Optical Field-of-View Localization with Vision Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  22. ComponentBench: Diagnosing Component-Level Failures in Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  23. Rethinking Privileged Information in On-Policy Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  24. Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement StudyMixture-of-experts → Efficient MoE training and inference systems
  25. VERAGMIL: Virtual Environment for Scooping Granular Foods with Imitation Learning ModelsOffline RL and imitation learning from data → Robot manipulation imitation learning
  26. ClosureBench: A Constructive Benchmark for Compositional Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  27. Sobolev Regularized Score Difference Estimation in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  28. GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment InteractionWorld models → Humanoid and legged locomotion world models
  29. Allocating Recurrent Compute in Looped Language ModelsLLM reasoning → Test-time compute and efficient thinking
  30. Revisiting the "Push-T" Robot Manipulation Task with Agentic RoboticsLLM agents and tool use → Multimodal and embodied agents
  31. Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi RolloutsKnowledge distillation → Multimodal distillation
  32. Hydra-0: Action Flow for Generalist World Modeling and ControlWorld models → Embodied and robot world models
  33. On the Fragility of Self-Improving Agents: Variance, Task Order, and UnderspecificationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  34. Delegation Asymmetry in Agentic Recommender Systems: Measuring Two-Sided Receptivity in Online DatingLLM agents and tool use → Social simulation and multi-agent debate
  35. StagedWorkspace: A Versioned Workspace for Knowledge-Work AgentsLLM agents and tool use → Software engineering coding agents
  36. Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian OptimizationDiffusion models → Diffusion foundations and sampling
  37. Plug-and-Play Traffic Element Awareness for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  38. Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey AutomationLLM agents and tool use → Web, search, and research agents
  39. The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic ReasoningLLM reasoning → Mathematical reasoning
  40. Memory Tree Guided Key Frame Querying for Efficient 3D Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  41. Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  42. Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE FieldsDiffusion models → Flow matching, time series and science
  43. AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution GenerationDiffusion models → Diffusion foundations and sampling
  44. aDSL: Agentic 3D Creation via Joint Agent-Program DesignLLM agents and tool use → Multimodal and embodied agents
  45. LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature CachingDiffusion models → Diffusion foundations and sampling
  46. Towards Zero-Shot Task Transfer with Neurosymbolic World ModelsWorld models → Latent dynamics models and model-based RL +1
  47. An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World ModelsWorld models → World models for language agents
  48. Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context ManifoldsLLM reasoning → Reasoning benchmarks and evaluation
  49. Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude RegularizationLLM safety and security → Machine unlearning
  50. Efficient RLVR Scheduling via Graph-Structured Online Difficulty EstimationLLM reasoning → Reinforcement learning for reasoning
  51. EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point DetectionLLM agents and tool use → Financial trading and forecasting agents +1
  52. PerFact: Perception-Derived Fact Prompting for 3D Brain MRI Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  53. CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and ExpansionLLM agents and tool use → Agent memory systems
  54. BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal ModelsLLM reasoning → Multimodal reasoning +1
  55. AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data AnalysisLLM agents and tool use → Web, search, and research agents
  56. GenRec: Knowing Where to Reconstruct and Where to GenerateDiffusion models → 3D, point cloud and scene generation
  57. Bounded-State Restoration: Decoupling Local Restore Capacity from External LLM StateEfficient LLM inference and serving → KV cache optimization
  58. An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM UnlearningLLM reasoning → Reinforcement learning for reasoning +1
  59. StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  60. Debate Training Reduces Reward Hacking in RLAIFLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  61. D2ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent MemoryLLM agents and tool use → Agent memory systems
  62. TINA+: Probing Residual Visual Knowledge in Unlearned Diffusion Models via Diffusion-Consistent Text-Free InversionDiffusion models → Robustness, privacy and adversarial aspects +1
  63. Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot SeeMixture-of-experts → MoE large language models
  64. Offline Multi-Agent Reinforcement Learning with a Physics-Informed World Model for Cooperative Mixed Traffic ControlWorld models → World models for autonomous driving +1
  65. Vision-Language Models for Analog Gauge Reading: An Empirical Study of Specialization, Transfer and ReliabilityMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  66. MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data PoisoningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  67. Beyond Suspicious Steps: Ontological Trust in Long-Horizon AgentsLLM agents and tool use → Agent threats, guardrails and governance
  68. Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching ModelsDiffusion models → Video generation
  69. Mixture-of-Expert Blocks Contain Strong Hallucination Detection SignalsMixture-of-experts → MoE large language models
  70. GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent CommunitiesLLM agents and tool use → Social simulation and multi-agent debate
  71. MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android AppsLLM agents and tool use → Agent threats, guardrails and governance +1
  72. rl-triton: High-Performance Triton GPU Kernels for Reinforcement Learning Credit AssignmentDeep reinforcement learning methods → RL training of language and agent models
  73. Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE RoutingLLM reasoning → Test-time compute and efficient thinking +1
  74. Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D VisionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  75. RetiWave-Mamba: A Dual-Stream Network for Retinal Disease Detection based on Multi-scale Context and Frequency-Adaptive Mamba ProjectionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  76. PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case ContextsLLM reasoning → Clinical and biomedical applications
  77. LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  78. HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness SafetyLLM agents and tool use → Agent threats, guardrails and governance
  79. tinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained MillirobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  80. Write, Execute, Refine: From Skill Follower to Skill Optimizer via Reinforcement Learning from Execution FeedbackDeep reinforcement learning methods → RL training of language and agent models
  81. Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified StudyLLM safety and security → Safety alignment, refusal and guardrails
  82. Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic EmbeddingsLLM safety and security → Safety alignment, refusal and guardrails
  83. No Gaussian Required: Contrastive Inverse Dynamics for JEPA World ModelsWorld models → Latent predictive world models
  84. CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation MethodRetrieval-augmented generation → Legal and financial RAG
  85. Agent Lightning v1.0: Towards Harnessed Agentic RLLLM agents and tool use → Software engineering coding agents
  86. Evaluating RL Explainability Methods by How Much They Help Fix Bugs in AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  87. Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related TaskKnowledge distillation → Knowledge distillation for LLMs
  88. SE-MoLoRA: Shared-Expert LoRA Adapters for Domain-Specific Photographic AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  89. Embodied-Navigator: Point, Think, Memorize, and Align for Efficient NavigationLLM reasoning → Spatial and embodied reasoning +1
  90. SGHA: Evidence-Grounded Research Problem Discovery with Local Language ModelsLLM agents and tool use → Web, search, and research agents
  91. Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal PoliciesVision-language-action models → Failure recovery and robustness
  92. When AI Designs AI: Innovation or Imitation?LLM agents and tool use → General LLM agent frameworks and benchmarks
  93. SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule EvolutionSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  94. EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action ControlVision-language-action models → Tactile, force-aware and humanoid VLA
  95. Structure-Internalized Rule Language Model for Faithful Knowledge Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  96. Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure OperationsLLM agents and tool use → Software engineering coding agents
  97. UniReflex: Plug-and-Play Force Control for Pretrained Generative Policies via Fast-Slow ReflexOffline RL and imitation learning from data → Robot manipulation imitation learning
  98. Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  99. Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome GroupsLLM reasoning → Reinforcement learning for reasoning +1
  100. TEAMS: Text-prompted spatiotEmporal dual-heAd Mamba SnakeState-space sequence models (S4, Mamba) → Mamba for medical image analysis
All 381
  1. REChart: Reasoning-Efficient Chart Editing with Large Reasoning ModelsLLM reasoning → Multimodal reasoning
  2. GUPO: Gradient Uncertainty-aware Policy Optimization for Post-Training Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  3. MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  4. LEGO-RL: Harness-Native Reinforcement Learning for Coding AgentsLLM agents and tool use → Software engineering coding agents +1
  5. Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  6. Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call BudgetsLLM safety and security → Jailbreaking
  7. Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  8. MoFE: A Novel Mixture-of-Experts Framework with Fourier Neural Operators for Cryptocurrency ForecastingMixture-of-experts → MoE for time series and graphs
  9. TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference AccelerationEfficient LLM inference and serving → KV cache optimization
  10. MS-MFAD : Multimodal large language models for Face Anti-spoofing DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  11. ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human FeedbackOffline RL and imitation learning from data → Robot manipulation imitation learning
  12. Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  13. Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU RequirementsLLM agents and tool use → Reinforcement learning for LLM agents
  14. Learning What Not to Learn: Adversarial Disentangled Prompt Tuning for Robust Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  15. SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  16. PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  17. Abra: Scaling Diffusion Image TrainingDiffusion models → Diffusion foundations and sampling
  18. DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought NavigationLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool CallingLLM agents and tool use → Agent threats, guardrails and governance
  20. A Hybrid End-to-End and Modular Control Architecture Toward Safe Vehicle Lateral Control: Combining Soft Actor-Critic with Model Predictive ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  21. Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RLLLM reasoning → Reinforcement learning for reasoning +2
  22. Training-Free Agentic Computer Vision for Structural Component Detection in 2D Structural Framing PlansLLM agents and tool use → Multimodal and embodied agents
  23. Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential BuildingsDeep reinforcement learning methods → RL for energy, networks and operations
  24. COMIC: Reference-Aware Safety Gating for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  25. PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized FinanceLLM agents and tool use → Financial trading and forecasting agents
  26. "AI Is Turning Too Human": How Teenagers Experience and Negotiate AI in Everyday Life
  27. What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation
  28. When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding
  29. Safe Multi-Robot Coordination via VLM-LLM Reasoning and Reachability Analysis
  30. Evaluating ADC-only deep learning pipelines for breast cancer detection and segmentation using standalone diffusion-weighted MRI
  31. A Decade of Climate Polarization on Brazilian YouTube using Language Models
  32. Early Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy Using Temporal Deep Learning on DWI
  33. Neoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic resonance imaging with clinical variables
  34. Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum
  35. Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation
  36. A Learning Algorithm for Threshold Boolean Networks with Prescribed Fixed Points
  37. Can Large Language Models Identify Meaningful Touchpoints in Conversion Attribution?
  38. Constructing Predictive Surgical Path for AI-based Capsulorhexis Skill Transfer
  39. Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility
  40. Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation
  41. Mapping General-Purpose AI Governance in Twenty AI Middle-Power Jurisdictions
  42. What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals
  43. Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus
  44. Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
  45. Inference and Uncertainty Quantification for Streaming r-PCA
  46. Optic Disc Segmentation in Fundus Images: From Classical Image Processing and Deformable Models to Modern AI
  47. Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning
  48. Coupled-cluster molecular properties across the main group that extrapolate beyond training size
  49. Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
  50. Measuring the Partial-Credit Gap: A Strict Benchmark on Vietnam's 2025 Convex Marking Scheme
  51. When Does Dynamic Ensembling Pay Off? Diagnosing Regionwise Gains in Regression under Distribution Shift
  52. Governance Records as Supervision: Verifier-Selected Self-Training for Structured Workflow Repair
  53. Reproducible Multimodal Affordance Prediction
  54. A Configurable Privacy-Preserving MRI Processing Workflow Using Deep Learning-Based Brain Extraction and Adaptive Anatomical Preservation
  55. Artifact-centered Claim-aware Observability for Autonomous Scientific Agents
  56. FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning
  57. High-Flux Count-Free Single-Photon 3D Cameras
  58. Acquisition Geometry-Assisted Whole-Group Localization of X-ray Fluorescence Maps in Optical Microscopy Images
  59. SESSE: Sketch, Expand, Sort, Summarize, Evaluate -- LLM-as-Judge Evaluation via Structured Decomposition
  60. The Lifecycle of LLM-as-a-Judge for Large-Scale Recommendation Explanations
  61. FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation
  62. Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
  63. GuideFetch: A Task Coordination Framework for Concurrent Navigation and Object Retrieval in Assistive Robot Dogs
  64. Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
  65. QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splatting
  66. Self-supervised In-context Operator Learning for Stochastic Mean-Field Control
  67. What Makes Software Issue Resolution Tasks Difficult for Agents?
  68. A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design
  69. Model Card for OpenAI Privacy Filter
  70. SeisEvo: Evolution of Seismic Data Reconstruction Algorithms by Agents
  71. Global Crises and National Policies: A Large Scale Analysis of Political Content in German Language Online Media
  72. Modeling Human Behavior with Type Vectors Using AI
  73. SIGMA: Symmetry-aware, Intelligent, Geometric, Multi-faced Adaptive Traffic Control for Reliable Intelligent Transportation Systems
  74. Redakto - The Incognito Tab for LLMs
  75. Visual-Prompt Guided Wildlife Instance-Level Recognition
  76. Bidirectional representational alignment between biological and artificial neural networks
  77. Zero-Shot Transfer of Force Map Estimation Across GelSight Mini Sensors
  78. GenEx: A Graph-Based Representational Paradigm for SARS-CoV-2 Variant Detection via Codon Co-occurrence Networks
  79. Classifying Directional Trajectories Near Criticality in the Three-State Majority-Vote Model with Deep Belief Networks and Bidirectional GRUs
  80. Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth
  81. LumiTokens: 3D Relighting via Token-Space Lighting Transformation
  82. On the Triangle Inequality for the Jaccard Distance in Arbitrary Lattices
  83. Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift
  84. ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy
  85. Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors
  86. A systematic review of machine learning techniques to address diagnosis and treatment of autism: challenges and opportunities
  87. What Can Artificial Intelligence Learn from Medicine? Generative Analogies and Reliable Machine Learning Systems
  88. H2EDL: Hyper Evidential Deep Learning for Hierarchical Classification
  89. Human-Centric Intelligence in the Era of Foundation Models: A Survey
  90. Efficient INT8 Inference of Small NLP Models on Server CPUs with PyTorch Native Stack
  91. Fair Multi-View Determinantal Coresets via Adaptive NEPv
  92. Trust as a Field: A Macroscopic Representation for Vehicular Networks
  93. Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
  94. From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation
  95. Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation
  96. EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
  97. TokEval: A Tokenizer Evaluation Suite
  98. The concentration game: Bayesian updating, regret, and information
  99. HLSR: Hybrid Live Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
  100. Primitive Representation Learning for Unsupervised Dynamic Contrast Enhanced MRI Reconstruction
  101. Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation
  102. Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors
  103. Where A Small Language Model Helps in Invoice Categorisation, Understood Through Embedding Geometry
  104. Initialization-Free Bundle Adjustment Revisited: A Controlled Experimental Study
  105. Chain-of-Experience for Continual LLM Improvement
  106. TabNSM: Neural Sparse Mixer for Tabular Regression
  107. How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness
  108. Revisiting WEASEL 2.0: Reproduction, Sensitivity, and an Adaptive Ensemble-Size Rule
  109. Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach
  110. Automated ACL Footprint Identification Using 3D Deep Learning
  111. Traceable Trust for action-ready artificial intelligence in bioscience
  112. Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees
  113. GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation
  114. Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media
  115. Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity
  116. Recirculation
  117. When Writing Style Drifts: Benchmarking Authorship Verification under Distribution Shifts in Genre, Time and the AI-Era
  118. Evaluating and improving crop-yield forecasting methods during extreme drought
  119. SFMformer: A Spatial-Frequency Modulation Transformer for Lightweight Image Super-Resolution
  120. Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
  121. Understanding the Surprising Generalization Properties of Tabular Foundation Models
  122. SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE
  123. Procedural Content Metageneration via Program Search and Continual Abstraction Discovery
  124. Grading Needs a Rubric, Not Intelligence
  125. Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment
  126. Collective Counterfactual Planning: Coordination, Consent, and Verification under Representational Constraints
  127. SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis
  128. Adaptive Policy Portfolios for Robust Markov Decision Processes
  129. A Theoretical Framework for Parallel Lifelong MAPF Using Group Decentralized Planning
  130. AppendiGrade: An XAI-Enhanced Deep Learning Framework for Grading Appendicitis in Ultrasound with Gaussian Blur and Grad-CAM
  131. Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks
  132. Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition
  133. Hybrid ML for Lightweight Pre-Route Delay Estimation in Open-Source IC Design
  134. An RKHS Framework for Fixed Effects in Permanental Process Models
  135. AutoResearch: Insight In, Hallucination Out
  136. Dynamic Compression in Recurrent Networks
  137. A Residual Learning Approach for Unsteady Aerodynamic Load Prediction
  138. VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval
  139. CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking
  140. Improving Complex Moir'e Removal with Generative Supervision
  141. DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance
  142. BayesPrompt: human readable prompts that make sense
  143. ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction
  144. Efficient Resource Optimization for Split Federated Learning
  145. MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models
  146. Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints
  147. Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits
  148. Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs
  149. The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
  150. From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector
  151. MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure
  152. Spatially explicit feature importance for building height estimation using research-access high-resolution SAR and optical sensors
  153. Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses
  154. Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It
  155. Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation
  156. Fourth-Moment Geometry of Rademacher Sums
  157. Training with synthetic data for drone detection in thermal imagery
  158. Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models
  159. TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification
  160. ETHEREAL: A 25.6-μs/inf. Low-latency Event-driven Graph-neural-network Processor for High-resolution Vision at the Edge
  161. Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility
  162. Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correction
  163. Learnware for CSI Feedback: Scene-specific Small Models Can Do Big
  164. MAGPIE-Net: Predicting short-duration heavy-rainfall events in station neighborhoods from multitemporal FY-4A AGRI observations
  165. The Curious Case of Exploding DecPOMDPs: Containing the Fire through Policy Counting
  166. Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits
  167. Evaluating the Diversity of AI-Generated Content with Diversity Profiles
  168. Evaluation of AI-based Visual Crack Detection in Steel Bridges Using Probability of Detection
  169. VERaiPHY -- Validation & Evaluation for Robust AI in PHYsics
  170. What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
  171. Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models
  172. Cross-View Correspondence Is a Measurement Intervention: Two-Sided Validation for Agent Evaluation and Credit Assignment
  173. Accuracy and Robustness of Model Cascades Under Data Perturbations
  174. DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation
  175. Monitoring Pasture Restoration from Satellite Image Time Series: Caveats and Opportunities
  176. Dijkstra as an Oracle for Online Stochastic Shortest Path Navigation with Provable Guarantees
  177. Environment-Invariant Subspace Learning for Generalizable Deepfake Detection
  178. GADR: Gathering Architecture Decision Records from Meeting Transcriptions
  179. Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch
  180. Differentiable Voronoi Ray Tracing Beyond Rasterization Speeds
  181. Conformal Prediction for Molecular Properties under Label Shift
  182. Benchmarking Automated Security Patch Backporting: How Far Are We?
  183. Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors
  184. Is Haar Enough? Exploring Symlets and Coiflets for Wavelet Convolution Layers
  185. Denoised Variance-Based Pruning with Optimal Brain Bias Compensation
  186. Elimination Geometry
  187. LLM-Derived Preference Judgments Are Not Self-Consistent
  188. MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation
  189. Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
  190. DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval
  191. Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)
  192. OOD Detection for EEG-based Machine Learning in High-Risk Environments
  193. From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support
  194. MoNe: Modular Neural Memory for Efficient Long Context Inference
  195. Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
  196. SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging
  197. Modified Bryson-Frazier Smoothing and Hyperparameter Learning for Temporal Gaussian Process Regression
  198. Communication Reduction via Semantic-Based Encoding in DMPC Using LSTMs
  199. TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
  200. Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making
  201. Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and Tight Coordinatewise Rates
  202. DMT-Dens: Density-preserving manifold visualization for biological data
  203. Domain-Adapted Molecular Language Models for Efficient Search of Make-on-Demand Libraries
  204. CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing
  205. Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models
  206. Leveraging existing sparse point annotations for benthic imagery dense segmentation
  207. MSEditor: Toward Consistent Multi-Shot Video Editing
  208. Code as Representation: A Compilable Parsing Paradigm for Academic Documents
  209. GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting
  210. ArborMem: Navigating Interaction States with Memory Forests
  211. Regularization of Statistical Inverse Problems on Non-Reflexive Banach Spaces
  212. When to Review: Spaced Repetition for Continual Pre-Training of Language Models
  213. Explainable AI-Powered Framework for Video-Based Skill Assessment in Cataract Surgery
  214. BrainNorm: A Foundation Model that knows Normal via Semantic Atlas Pretraining
  215. Looking Beyond the Scale: Do Surgical Skill Models Learn Transferable Representations Across Assessment Rubrics?
  216. Effects of Answer Format Variation on Gender Bias in Large Language Models
  217. Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context
  218. When More Foundation Models Means Less: Diagnosing and Addressing Multi-View Fusion Failure
  219. NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognition
  220. S3AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection
  221. Online Generalized Sparse Regression: How Does Overparametrization Help?
  222. From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis
  223. Causal Local States: Scalable Simultaneous Causal Network Inference and Forecasting for Dynamical Systems
  224. Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines
  225. NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting
  226. Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
  227. General Semantic Knowledge Infusion for Spatio-Temporal Traffic Forecasting
  228. Depth Enables Local Entropy: Quadratic Depth Dependence in Deep Variation-Norm ReLU Regression
  229. SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
  230. GSToken: Geometry-Structured Gaussian Tokens for Compact 3D Medical Image Representation
  231. TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection
  232. SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering
  233. Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale
  234. An Investigation of Translationese in the Generations of Multilingual Large Language Models
  235. To Remove or Not to Remove Clouds: A Comparative Analysis and Fusion of Raw SAR and Synthetic NDWI for Overcast Water Segmentation
  236. Noisy group neurons with synchronous resetting for high-performance spiking neural networks
  237. GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly
  238. Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design
  239. PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX
  240. On the Pseudo-Mixing of Kac's Walk
  241. Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease
  242. CORAM: Coherent Orthogonal Rotation for Model Merging
  243. Continuity-Driven Representation Learning for Industrial Defect Detection
  244. ArguLens: An Open-Source System for Automated Essay Scoring and Label-Aware Feedback Generation
  245. Cognitive Graph Intelligence for Adaptive and Robust DDoS Attack Detection in Next Generation Networks
  246. Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing
  247. Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems
  248. Tight Bounds for Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function
  249. LLM-Only PDDL Domain Repair with Open-Weight Models
  250. Learning latent progression states from spatial heterogeneity in uterine histopathology
  251. SPACE: Sample-cloud Predictive Adaptive Conformal Ellipsoids for Multivariate Time-Series Forecasting
  252. LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap
  253. What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?
  254. Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
  255. If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigation
  256. Scanline-Aware Animatable Gaussian Avatars from Rolling-Shutter Videos
  257. NeuroAbs: A Neuro-Symbolic RTL Abstraction Framework for Property Checking Acceleration
  258. LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models
  259. 3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation
  260. Beyond MSE: Rethinking the Evaluation Metric and Benchmarking for Irregular Time Series Forecasting
  261. B-Spline Embedded Structure Learning for 3D Tooth Segmentation
  262. Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention
  263. Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functions
  264. UniQuery4R: Unified 4D Scene Reconstruction from a Single Query
  265. Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge
  266. ASI-Bench: At the Dawn of Artificial Superintelligence
  267. Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
  268. Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics
  269. Nonadaptive Learning in Robust Nonlinear Output Regulation
  270. Minimax Optimal Estimator and Improved Error Rate for the MLE in Logistic Regression with Gaussian Design
  271. Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction
  272. Heterogeneity-Aware Deep Learning for Tumour Classification from Multiparametric MRI
  273. Adaptive surrogate modeling for high-dimensional spatio-temporal output
  274. Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data
  275. Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification
  276. Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication
  277. Maximum Tsallis Entropy Distributions for Robust and Efficient Sparse Learning from Correlated Data
  278. Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection
  279. Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking
  280. Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal
  281. The Plot Thins: Uniformity and Linearity in Literary Summaries