mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 15 Sep 2026

467 papers

  1. What Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy BanksLLM safety and security → Safety alignment, refusal and guardrails
  2. EditWM: Event-Decomposed World Modeling with Incremental Correction for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +1
  3. CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  4. BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological ResearchLLM reasoning → Clinical and biomedical applications
  5. Beyond the Previous Layer: Residual Predictive Structure in Sparse MoE RoutingMixture-of-experts → Expert routing strategies
  6. Collaborative Memory for Multi-Agent VLM SystemsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  7. Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text ControlWorld models → Video-generation world models and simulators
  8. When AI Agents Meet MEV: Cross-Chain Arbitrage in the Agentic EconomyLLM agents and tool use → Financial trading and forecasting agents
  9. OBC-Prune: Outcome-Based Calibration for Large Reasoning Model PruningLLM reasoning → Test-time compute and efficient thinking
  10. ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise SoftwareLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational PathologyMultimodal LLMs / vision-language models → Medical vision-language models
  12. The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier?Efficient LLM inference and serving → Serving systems and request scheduling
  13. SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and ScaleLLM reasoning → Reinforcement learning for reasoning +1
  14. Learning Heterogeneous PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  15. PrimeScientist: Strategic Allocation of Research Effort in Autonomous ResearchLLM agents and tool use → Web, search, and research agents
  16. Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics AgentsLLM agents and tool use → Multimodal and embodied agents
  17. Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learningDeep reinforcement learning methods → RL theory and sample complexity
  18. METALICA: METAdynamics and repLICA exchange for enhanced diffusion samplingDiffusion models → Flow matching, time series and science
  19. Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned BenchmarksLLM agents and tool use → Agent threats, guardrails and governance +1
  20. GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial ConditioningDiffusion models → Video generation
  21. A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math ReasoningLLM reasoning → Mathematical reasoning
  22. AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence InjectionMultimodal LLMs / vision-language models → Medical vision-language models
  23. Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  24. FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA DeploymentLLM agents and tool use → Software engineering coding agents
  25. HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  26. CALOS: Control-Affine Lyapunov On-manifold Safety Layer for Safe Deep Reinforcement Learning for QuadrotorsDeep reinforcement learning methods → RL for robot navigation and UAV control
  27. Imitation Learning for Autonomous Driving in CARLAEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  28. REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL CliffDeep reinforcement learning methods → Deep RL algorithms and representations
  29. RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +2
  30. Vision-Language Grounded Task-Context-Aware Imitation Learning for Robotic DisassemblyOffline RL and imitation learning from data → Robot manipulation imitation learning
  31. One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  32. Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to AgentsLLM reasoning → Test-time compute and efficient thinking +1
  33. A Large-Scale Empirical Study of Quality Assurance Practices and Gaps in AI AgentsLLM agents and tool use → Software engineering coding agents
  34. Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  35. GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph AgentsLLM agents and tool use → Agent threats, guardrails and governance
  36. Accelerating Diffusion Sampling via Speculative Draft TreesDiffusion models → Discrete and text diffusion +1
  37. CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric VideoMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  38. The Missing "I Don't Know": Why Three Reasoning-Reliability Findings Converge on Calibrated AbstentionLLM reasoning → Test-time compute and efficient thinking
  39. Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI AgentsLLM agents and tool use → GUI and mobile agents
  40. Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV CachesEfficient LLM inference and serving → KV cache optimization
  41. Trust propagation and structural containment in Multi-agent LLM pipelinesLLM agents and tool use → Agent threats, guardrails and governance
  42. Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  43. EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading AgentsLLM agents and tool use → Financial trading and forecasting agents +1
  44. Agentic Societies Need a Social HarnessLLM agents and tool use → Social simulation and multi-agent debate
  45. Modality-Autoregressive World-Action ModelsWorld models → Embodied and robot world models
  46. What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task ComplexityLLM agents and tool use → Tool learning and function calling +1
  47. Verifiable Social Reasoning for LLM AssistantsLLM reasoning → Reasoning for agents, planning and code
  48. Dissecting Motion-Prior Regularization for Data-Scarce Robotic InsertionDiffusion models → Diffusion and flow policies for robotics
  49. JustFit: Just-in-Time State Management for Local LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  50. Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward FeedbackKnowledge distillation → Knowledge distillation for LLMs
  51. BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  52. SlotDiT: Object-Centric Representations for Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  53. Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure InsteadLLM agents and tool use → Software engineering coding agents
  54. XPACE: Joint World and Action Modeling from Heterogeneous ExperienceWorld models → Embodied and robot world models
  55. Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-ModelingLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language OutputsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  57. Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-OrganisationWorld models → Latent dynamics models and model-based RL +1
  58. Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  59. Towards Detecting AI-Assisted Responses in Online SurveysLLM agents and tool use → Web, search, and research agents
  60. Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. Same Flow, Different Paths: Variance Reduction in Flow MatchingDiffusion models → Flow matching, time series and science
  62. Personalized Federated Learning through Global Knowledge Distillation and Local Head AdaptationKnowledge distillation → Federated, robust and private distillation
  63. Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  64. Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?LLM reasoning → Audio-language model reasoning +1
  65. ECHO: Early-layer Collaborative Hierarchical Orchestration with Bonus Logits in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  66. FROD: Feature Matching Residual Denoising Oracle Bone DecipherDiffusion models → Image generation, text-to-image and editing
  67. Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical MappingLLM agents and tool use → Software engineering coding agents
  68. FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied IntelligenceWorld models → Embodied and robot world models +2
  69. [MM/AI] Mental Models in Human-AI Interaction: Methods and Challenges in the Generative and Agentic AI Era (Workshop)LLM agents and tool use → General LLM agent frameworks and benchmarks
  70. MyoFlow: Anchor-Tied Rectified Flow for HD-sEMG Gesture Recognition Across Sessions and SubjectsDiffusion models → Diffusion and flow policies for robotics
  71. End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI ServicesLLM agents and tool use → Software engineering coding agents
  72. LoopSpec: Pipelined Self-Speculative Decoding for Looped TransformersEfficient LLM inference and serving → Speculative decoding
  73. Plug 'n' Pray: Agentic LLM-based Detection of Potential Log File Exposures in Third-Party Content Management System PluginsLLM agents and tool use → Agent threats, guardrails and governance
  74. ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision TransformersMechanistic interpretability → Interpreting vision and multimodal models
  75. Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous RacingEnd-to-end autonomous driving → Reinforcement learning for driving
  76. FirmCORe: A Benchmark for Structured Reasoning about Inter-Firm Collaboration OpportunitiesLLM reasoning → Reasoning for agents, planning and code
  77. Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy ImprovementVision-language-action models → Reinforcement learning and post-training
  78. Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data AnalyticsLLM agents and tool use → Web, search, and research agents
  79. sensVLA: Spatially-Grounded Vision-Language-Action Model for Autonomous Wheel LoaderVision-language-action models → VLA for autonomous driving
  80. SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise ReasoningLLM reasoning → Mathematical reasoning +1
  81. ORDER: Task-Conditioned Routing for Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  82. FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM InferenceEfficient LLM inference and serving → Early exit and edge inference
  83. Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim VerificationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  84. PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in ProgressLLM agents and tool use → Web, search, and research agents
  85. ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM FailuresLLM agents and tool use → Software engineering coding agents
  86. Target-Language Generation in Multilingual Models: Activation Steering and Optimal ControlMechanistic interpretability → Activation steering methods
  87. Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  88. RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository ViewsLLM agents and tool use → Software engineering coding agents
  89. MedPCFM-TED: One-Step Point Cloud Flow Matching for Implant Generation via Teacher-Guided Endpoint DistillationDiffusion models → 3D, point cloud and scene generation
  90. Verbalizing Subliminal Learning Effects Using Text OptimizationKnowledge distillation → On-policy and self-distillation for LLMs
  91. NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  92. Cascade: Hierarchical Recoverability Control for Large Language Model UnlearningLLM safety and security → Machine unlearning
  93. QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum ScalingLLM reasoning → Reinforcement learning for reasoning
  94. TEMPO: Learning Temporal Context for Dynamic Robot ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  95. TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  96. RegRet: Enhancing Region-Level Retrieval in Large Multimodal ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  97. StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token SelectionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  98. InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  99. Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  100. Unifying Semantic Priors and High-Frequency Traces: Enhancing V-JEPA with Mixture-of-Experts for Robust Synthetic Image ForensicsMixture-of-experts → Multimodal MoE models
All 467
  1. RECTIFY: An Interactive Workbench for Post-Evaluation RAG Diagnosis, Repair, and VerificationRetrieval-augmented generation → RAG pipeline design and evaluation
  2. Turn-level Multiscale Density Ratio Estimation for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. TAME: Token Attribution and Masking for Emergent misalignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  4. When Agents See Differently: Exposing UI Desynchronization Threats in Mobile AgentsLLM agents and tool use → GUI and mobile agents
  5. CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory PlanningWorld models → World models for autonomous driving
  6. VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  7. World Models for Embodied Intelligence: From Plausible to Controllable to ActionableWorld models → World models for navigation
  8. IL-ACT: Imitation Learning with Adaptive Cartesian Tracking Control for a 30-ton ExcavatorOffline RL and imitation learning from data → Imitation learning methods
  9. Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural PerspectivesLLM agents and tool use → Agent threats, guardrails and governance +1
  10. Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling StrategyDiffusion models → Medical imaging and segmentation
  11. Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  12. MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM WatermarksLLM safety and security → Watermarking generated content and models
  13. little m: An AI Agent for Industrial Process OptimizationLLM agents and tool use → Medical and scientific domain agents
  14. AI for Games in the Foundation Model EraWorld models → World models for language agents
  15. Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  16. Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQAMultimodal LLMs / vision-language models → Image editing and quality assessment
  17. DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference OptimizationLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  18. Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space DualityState-space sequence models (S4, Mamba) → Vision Mamba backbones
  19. Mechanism-Level Evaluation for Vision-Language Models: Controlled Activation-Replacement Diagnosis of Gender BiasMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  20. ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  21. What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding ProbesLLM reasoning → Hallucination detection and mitigation
  22. WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded CoordinationWorld models → Humanoid and legged locomotion world models
  23. SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic ManipulationVision-language-action models → 3D and spatial-aware VLA
  24. ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-TrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  25. EchoPath: Execution-Level Replayable Memory for GUI AgentsLLM agents and tool use → GUI and mobile agents
  26. AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at ScaleLLM agents and tool use → Agentic recommender systems
  27. Divergence Timing and Cumulative Disagreement under KV-Cache EvictionEfficient LLM inference and serving → KV cache optimization
  28. EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  29. SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination MitigationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  30. Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  32. AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal ForecastingDiffusion models → Flow matching, time series and science
  33. Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  34. Query-Aware Source-Risk Triage for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  35. PunGraph: Retrieval-Enhanced Phonetic-Semantic Graph Reasoning for Pun UnderstandingLLM reasoning → Knowledge- and tool-augmented reasoning
  36. What Does Layer-Importance Reveal About Transformers and State-Space Models?State-space sequence models (S4, Mamba) → Core SSM architectures for language
  37. Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference DataLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. FlowATC: Aircraft Trajectory Prediction via Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  39. QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible moleculesDiffusion models → Flow matching, time series and science
  40. AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific ResearchRetrieval-augmented generation → RAG robustness and adaptive retrieval
  41. Dense to MoE Adaptation for Compact Vision Language Action PoliciesVision-language-action models → Generalist VLA models and benchmarks
  42. PipeSwift: Revisiting Pipeline Parallelism for Large-Scale Completion-Oriented Agentic LLM ServingEfficient LLM inference and serving → Efficient reasoning and agent inference
  43. Skill-based Agentic Evaluation for Real-time Data Science TasksLLM agents and tool use → Web, search, and research agents
  44. VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image SegmentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. Protocol-Preserving Context Trimming for Agentic Workflows: Benefits, Failure Regimes, and Budget GuardrailsLLM agents and tool use → Tool learning and function calling +1
  46. OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy DistillationLLM reasoning → Multimodal reasoning +1
  47. Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +2
  48. Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel SamplingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  49. When Can World Models Recover Physical Laws?
  50. Efficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales
  51. Unsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data
  52. One-Step Is Optimal: Unconditional Rectified Flows are Noise2Noise Denoisers, and Multi-Step Integration Provably Hurts---A Benchmark and Task-Based Detectability Study on Low-Dose CT
  53. NanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization
  54. Query-aligned video frame selection for long video understanding
  55. Age-Adaptive Handwriting Reconstruction from an IMU-Based Digital Pen through Shared Representations and Domain-Specific Heads
  56. Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges
  57. LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text
  58. Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment
  59. ForensicZoom: Adaptive Visual Inspection with Multimodal LLMs for Industrial-Grade Face Forgery Detection
  60. Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents
  61. Cross-Material Support Transfer for Core-Loss Prediction Under Waveform Covariate Shift
  62. Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification
  63. Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling
  64. From Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness
  65. One Evaluation, Any Operating Point: Hypernetwork-Amortized MeanFlow for 3D MRI Reconstruction
  66. AI in Science: Early Insights
  67. Stable and Faithful Explanations for Knowledge Tracing
  68. TTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration
  69. Yarn tracking of large-scale 3D textile reinforcements using topological material features
  70. GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents
  71. TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision
  72. Automated Physics-Informed Neural-Networks-Based Calibration of Highly Segmented Silicon Telescopes
  73. Message capacity and claim wording set the transition points of collective truth-finding in language-model networks
  74. What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks
  75. Optimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation
  76. Locating Hidden Failures Makes Long-Horizon Agents More Reliable
  77. Symmetry without a manifold: intrinsic dimension on orbits
  78. Rapid Loss of the Sierra Nevada's Largest Trees Driven by Fire
  79. Audio for Sports Highlight Detection: A Comparative Empirical Study
  80. EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction
  81. Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan
  82. Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds
  83. Generalized DCCQ: From Binary Quotients to Multinomial Simplex Geometry and Critical-Strip Coordinates
  84. QEMScore: How Much Does the Measurement Add to Learned Quantum Error Mitigation?
  85. TabPFN-3.5: Technical Report
  86. Bracketing Uncertainty in Clustering Under the Manifold Hypothesis
  87. Long-Context Demonstration Selection Using State Space Models
  88. Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning
  89. The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification
  90. Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming
  91. Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?
  92. Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space
  93. Do Frontier Models Seek Safety Evidence Before Acting?
  94. Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels
  95. Investigating Adversarial Robustness of Heterogeneous Cooperative Perception
  96. SNOMED CT Concept Recommendation from Masked Clinical Context
  97. AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content
  98. Sharp margin-based generalization bounds for realizable SVM
  99. RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos
  100. Hybrid coupling with numerics-informed neural networks and the overlapping Schwarz alternating method
  101. Learning Nuclear Structure with AI: Radii and Collectivity
  102. Procedural Pretraining for Molecular Property Prediction
  103. NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections
  104. Learning Multi-Humanoid Pickup and Transport via Decentralized Object-Centric Control
  105. CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts
  106. The Free Inference Dimension: Complexity Measure for Zero-Collision Navigation under Hypothesis Mixtures
  107. Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction
  108. Wind on Trees: Testing Physical Grounding in Dynamic 4D Gaussian Splatting
  109. Synthetic Electric Vehicle Charging Session Generation Using a Conditional Variational Autoencoder
  110. Approximating Measures on Function Spaces: Transport and Truncation
  111. Random tilts to find stationary points in stochastic convex optimization
  112. QiT: Quantum-Inspired Transformer for Visual Recognition Task
  113. SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity
  114. AI and Human Approaches to Mathematical Problem Solving
  115. Information Set Emulation: Causal Certificates for AI Derived EHR Features
  116. SAGE: Governed Artifact Generation from Enterprise Guidelines
  117. When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments
  118. How Calibration Content Shapes Attention-Based Reranking
  119. Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Prediction
  120. Is Luke the Author of a Gospel and the Acts of the Apostles?
  121. Derivative-Free Structured Updates for Muon
  122. Evolution of US Oral Political Language
  123. Beyond Performance Metrics: Uncertainty Mapping of Label Ambiguity in Fazekas Score Prediction
  124. How to make effective use of domain experts for image classification?
  125. SAM-on-the-Curve: Sharpness-Aware Mode Connectivity for Robust Weight-Space Interpolation
  126. Is Trump's Vocabulary Poor? Vocabulary Richness Across Texts of Different Lenghts
  127. Geometry-Driven Shadow Harmonisation for Composited Faces: A Multiplicative, Albedo-Preserving Relighting Pipeline
  128. Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC
  129. Machine learning kinetics from molecular dynamics data
  130. A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products
  131. FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining
  132. Self-Supervised Learning for Robust Resonance Mass Regression in Cascade Decays
  133. Decoding Extrahepatic Targeting of Lipid Nanoparticles with Interpretable Machine Learning
  134. NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation
  135. GVD: Governed Versioning and Deduplication for Document Repositories
  136. DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery
  137. Efficient Robust Learning at the Information-Theoretic Limit
  138. Regularized Least Squares Training of Quadratic Neural Networks with Applications to System Identification
  139. Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction
  140. Scaling Articulated Rationales for MLLM-based Recommendation
  141. Lecture notes on Physics Informed Neural Networks, Neural Operators, and their applications
  142. What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization
  143. Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
  144. One Color Preprocessing Improves DSATUR
  145. Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records
  146. Fenchel-Young Duality Gaps: Certified Early Stopping for Regularized Inverse Problems
  147. LEAP: Learning Emergent Active Perception for Quadruped Navigation
  148. ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
  149. PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
  150. When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
  151. LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
  152. ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
  153. FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
  154. LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
  155. Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult
  156. Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
  157. Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
  158. Decomposition Buys Integrity, Not Yield
  159. Tables Decoded: DELTA for Structure, TARQA for Understanding
  160. ORCA: Occlusion-Aware Refinement and Completion for Novel View Synthesis
  161. Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
  162. Evaluating Verified Autonomy in Quantum Engineering
  163. Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM
  164. CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
  165. Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
  166. Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
  167. SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion
  168. Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation
  169. FlashVector: Agent for Hierarchical Model Serving Stack Optimization
  170. PanoGS-SLAM: Panoramic 3D Gaussian Splatting SLAM
  171. Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
  172. OPEN-1B: A Fully Auditable Training Run
  173. Large Language Models Develop Belief State Geometry In-Context
  174. Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts
  175. Hybrid Variational Quantum Circuits for Multivariate Regression and High-Dimensional Data Reconstruction
  176. Where Should a Document Live: Context, Representations, or Parameters?
  177. Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
  178. From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
  179. Zero-shot narrative detection in social messaging
  180. Optical-Flow Wingbeat Counting in MuJoCo: A Comparison of Convolutional, Spiking, and Attention-Based Temporal Models
  181. Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting
  182. Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks
  183. Conformal Policy Learning with Distribution-Free Safety Guarantees
  184. Extracting ontology-compliant knowledge from scientific text describing irradiated materials using large language models
  185. After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem
  186. Towards Illusions Awareness in Cyber-Physical System's Design
  187. Exploring 2D backbone effects for indoor semantic occupancy prediction
  188. Persistent Recurrent Memory Between Transformer Layers - Improves Language Model Generalization
  189. Covariate Selection for Doubly Robust Double/debiased Machine Learning Estimators for Causal Inference
  190. AraMIP: Extending MIPVU Towards Metaphor Identification in Arabic
  191. DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming
  192. Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
  193. Psychological Effects of Cultural Upheavals from Millions of Song Lyrics Over 100 Years
  194. Memorisation bias in medical AI
  195. InfoTaxa: Information-Calibrated Label-Free Clustering for Fine-Grained Visual Taxonomy
  196. Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection
  197. Cross-Domain Inference for Human Localization: Applying Wi-Fi RSSI Data to CSI-Trained Models
  198. EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset
  199. Multimodal Cultural Heritage Architectural Style Classification for Residential Buildings in the UAE Based on CLIP Embeddings and SVM
  200. MOCC-R1: Reinforcing Reasoning-Response Consistency for Multimodal Counselor Response Generation
  201. IRENE: A Convolutional GRU Ensemble Model for Radar Precipitation Nowcasting over Italy
  202. A unified framework for global and local interpretability using adaptive derivative-ordered random explanation
  203. MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis
  204. HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM
  205. Neural Field Ensembles for Aerodynamic Surface Prediction: Winning Solution to the ONERA CRM Wall Distribution 2025 Challenge
  206. Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation
  207. From Foundation Embeddings to Cropland Maps: Label Efficiency, Temporal Transferability and Independent Human Validation
  208. Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection
  209. Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition
  210. AI for Science with GPT-6 Astra: Thermal Design and Electrothermal Analysis of 2D CFET
  211. An Empirical Study of Counterfactual Self-Explanations in LLMs
  212. Not Another Text Benchmark: Putting the "Visual" Back in Visual Question Answering for Large Video Models
  213. Finding Common Mistakes In Modelling With Mathematical Formalisms Using LLMs
  214. Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs
  215. High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics
  216. Semi-Supervised Learning-Based Genetic Biomarkers Dataset for Multiple-Stage Hepatocellular Carcinoma Prediction
  217. GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos
  218. Hub-Spectral Activation of Latent Multimodal Knowledge
  219. Scaling-Score Conformal Prediction for Multi-Target Regression
  220. Optimization over covariance matrices with a parameterized metric
  221. Interactive Memory Learning for Long-Term Conversations
  222. EviScope: Paired Counterfactual Evidence Diagnostics for Faithful and Efficient Grounded Language Models
  223. Sample-Conditioned Representation Selection for Audio Few-Shot Learning
  224. Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation
  225. Bio-Inspired Palette Evolution in Indirectly Encoded Substrates: Timescale Compatibility Shapes Activation Function Discovery
  226. Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work
  227. Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior
  228. Repurposing Unified Topological Signatures for Graph Representation Learning
  229. Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios
  230. Near-Optimal Nonconvex Matrix Completion
  231. Diagnosing the Fact-Grounding Gap in Multi-Hop Question Answering
  232. Learning Options for Compositional Motor Control with Adapter Banks
  233. Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
  234. Bi-FlowGS: Bridging Generative View Completion and Gaussian Geometry through Bidirectional Flow Co-Refinement
  235. Distributed JEPA: A Self-Supervised Framework for Energy Forecasting
  236. CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework
  237. Beyond Measurement Metrics: A Human-Centered Framework for Semantic Validation of Network Traffic Classification
  238. ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
  239. Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising
  240. The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment
  241. Autoformalizing Argumentative Material Inferences
  242. Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs
  243. Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation
  244. Splitting the Difference: Interpretable Causal Forests for Treatment Effect Heterogeneity and Bias
  245. HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning
  246. Affect-Prototype Guided Fusion for Open-Vocabulary Incomplete Multi-modal Emotion Recognition
  247. Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence
  248. AntennaFlow: A Generative Flow Model for Offset Correction in Phaseless Antenna Testing
  249. AeroLat: Channel-Aware Latent Space Semantic Communication for Decentralized UAV Swarms
  250. High-Fidelity Video Quality Assessment with VQA-Specific Saliency
  251. When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models
  252. Causal Discovery via Transformed Low-Rank Quantile Surfaces
  253. Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling
  254. Evaluating Mesh Reconstruction Methods for Crop Phenotyping
  255. HyCoSeq: Contextual Hyperbolic Representation Learning for Genomic Sequences
  256. Multi-Agent Learning with Cooperation-Driven Optimization Dynamics
  257. Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
  258. PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
  259. Disrupted Companionship: A Risk Assessment Framework and Cross-Platform Quantitative Analysis of Psychosocial Responses to AI Companion Disruptions
  260. Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech
  261. RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
  262. OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
  263. Temporally Consistent Graph Extraction and Matching for Longitudinal Angiographic Images
  264. Bridging Learned Visual Perception and Symbolic Belief-Space Planning
  265. VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal
  266. Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility
  267. Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation
  268. NeuroTS-Net: Multi-Class Semantic Segmentation of Pediatric Brain Tumors in Multi-Modal MRI
  269. GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking
  270. SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning
  271. tcnerv:dual-domain temporal context modeling for implicit neural video compression
  272. Reduplicative constructions in Mandarin: Socio-emotional profiling through distributional semantics
  273. Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes
  274. The Evolution of Coordination in a Collective Intelligence System: 25 Years of English Wikipedia and the Emergence of Generative AI
  275. A Data-free Universal Prior over Syntactic Structures
  276. Can Deep Learning Achieve Cross-Physics Mapping?
  277. CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarms
  278. FAHCD-Net: Frequency-Adaptive Heatmap-Conditional Diffusion Networks for Robust Facial Landmark Detection
  279. What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking
  280. Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories
  281. Adapting to Decision-Relevant Non-Stationarity in Decentralized Heterogeneous Bandits
  282. LCAP: Population-Informed Latent Chip Adaptation from Few Output Probes for Photonic Neural Networks
  283. Execution Flexibility in Automated Planning: A Comparative Evaluation of Deordering and Reordering Strategies
  284. ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
  285. Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
  286. Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation
  287. Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization
  288. SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals
  289. On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm
  290. Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement
  291. TEDi: Temporal Memory-Enhanced and Denoising Transformer for Surgical Instrument Segmentation
  292. Time-warping estimation via stationarity-based learning of the de-warped signal
  293. Available but Unclaimed: An Empirical Study of Human-AI Synergy
  294. Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising
  295. PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection
  296. Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making
  297. Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
  298. IMVS: Interactive Medical Volume Segmentation with Test-Time Adaptation - A New Method for Annotating Radiology Datasets
  299. FSANet: Frequency-Spatial Aware Network for Image Segmentation
  300. Robust 3D Reconstruction from Multi-View Optical Satellite Imagery via Reliability-Aware Height-Evidence Fusion in Gaussian Splatting
  301. Coverage-Aware Virtual IMU Augmentation for Low-Resource Human Activity Recognition
  302. De-GAN - Dynamic Parameter Tuned GAN for 3D Medical Image Segmentation: A Step Towards Generalisation
  303. Beyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition
  304. Constant Swap Regret in General-Sum Games via Two-Scale Higher-Order Optimism
  305. TIAO: Token Importance-Aware Policy Optimization for Text Summarization
  306. The Latent That Never Was: A Forensic Re-run of the CVAE Ablation in Action Chunking Transformers
  307. A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids
  308. Carry-Through Checksum: A Lightweight Fault-Detection for CNN Inference at the Edge
  309. Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models
  310. Unified Heterogeneous Graph Neural Network solver for Power Flow, Optimal Power Flow and State Estimation
  311. Visual Cue Guided Video Planning for Generalizable Robot Navigation
  312. LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture
  313. PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
  314. Continuous-Time Machine Learning: A Unified Mathematical Perspective
  315. MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking
  316. Differentiable Mesh State Estimation via Factor Graph Inference for Deformable Object Reconstruction
  317. MEgoVista: Multi-view Ego-aware Motion Estimation for Metric 4D Hands and Head in the Wild
  318. Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions
  319. Lesion-centered 3D mapping of colonoscopy procedures: validation of a hierarchical ensemble pipeline on public benchmark videos
  320. ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds
  321. SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Tracking
  322. Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA
  323. GrowMTP: Can RL Grow Its Own Draft Head?
  324. Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
  325. Quantifying Organizational Environmental Action from Web Data and Large Language Models
  326. JewelTry: Mask-Free Scale Aware Jewelry Virtual Try-On
  327. Characterizing Heterogeneous Rates in Finite Mixture Estimation via Partial Optimal Transport
  328. Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction
  329. RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
  330. Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders
  331. A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure
  332. G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
  333. A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data
  334. FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation
  335. A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance
  336. FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
  337. Challenges of Auditing: Variability in Outputs of Large Language Models for Health
  338. ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation
  339. CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection
  340. Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging
  341. GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
  342. Counterfactual Reasoning for Robust Visual Question Answering
  343. Vision And Text Transformer For Predicting Answerability On Visual Question Answering
  344. The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs
  345. Supervising the Chain Ladder
  346. Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound
  347. QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge
  348. A Cyber Range Evaluation of Autonomous Network Incident Response Agents
  349. On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models
  350. Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening
  351. Causal Path Analysis from Perturbational and Population-Scale Single-Cell Data with Multiscale Confounding and Measurement Error
  352. Beyond the Name: Demographic Leakage in De-Identified R'esum'es and Evaluation Artifacts in LLM Bias Audits
  353. High-Performance Tensor Formulation of the Viterbi Algorithm for Hidden Semi-Markov Models
  354. Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines
  355. AI Policies: Help or Hindrance? A Software Developer's Perspective
  356. From Manual Construction to AI-Driven Scenario Emergence: Rethinking Catastrophe Risk Modeling
  357. Decoder Design Matters for ECG Delineation
  358. Certified Inference and Training for Deep Equilibrium Networks: A Continuation Framework with Polynomial Complexity Guarantees
  359. MDN-Control: Mask-Depth-Noise Guided Region Control for Multi-Subject Video Editing
  360. Online Gradient Computation for Warping Gaussian Process Transformations
  361. HairCS: Reconstructing Strand-Based Hair from Hair Cards
  362. A multimodal large language model for evidence-based autism spectrum disorder screening
  363. Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection
  364. Language Orthogonalization for Zero-Shot Cross-Lingual Audio Deepfake Detection
  365. Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs
  366. Decentralized Gossip Learning and Federated Averaging for Histopathology Image Classification
  367. Adaptive Bayesian Partner Selection for Federated Clinical Centers