mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 27 Aug 2026

462 papers

  1. PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent EvaluationLLM agents and tool use → Software engineering coding agents
  2. BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease DiagnosisMultimodal LLMs / vision-language models → Agricultural vision-language models
  3. Beyond Task Completion: Training Capable and Safe Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  4. Contrastive World ModelsWorld models → Latent predictive world models
  5. LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat GamesLLM agents and tool use → Reinforcement learning for LLM agents
  6. UI-Venus-2 Technical ReportLLM agents and tool use → GUI and mobile agents
  7. ReVA: A Region-Aware Visual Assistant for Visually Grounded Question AnsweringLLM reasoning → Multimodal reasoning +1
  8. TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  9. Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAGLLM reasoning → Multimodal reasoning +1
  10. State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  11. Instruction Distillation: Text Instructions as Visual ExamplesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid InteractionDiffusion models → Audio, speech and music
  13. Fast Weight Attention for Continual LearningState-space sequence models (S4, Mamba) → Core SSM architectures for language
  14. Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  15. Efficient Auto-Interpretability of AI Models in BiologyMechanistic interpretability → Interpreting biomedical and science models
  16. What Can Low Resource Languages Learn From Each Other?Multimodal LLMs / vision-language models → Document understanding and multimodal RAG
  17. The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMsLLM agents and tool use → Tool learning and function calling
  18. Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  19. Diffusion Distillation for Efficient Weather EnsemblesDiffusion models → Flow matching, time series and science
  20. SegBench-GC: Testing Segmentation Invariance in Multi-Step Offline Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  21. Agents for Everyone: A Workshop Framework for Building Agentic AI Capabilities in a Distributed Curation CommunityLLM agents and tool use → Web, search, and research agents
  22. First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  23. Semantic Watermarking with Order-Robust Detection over Sub-sentence UnitsLLM safety and security → Watermarking generated content and models
  24. Knowing Before Answering: Decoding Language Models for Reliable RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  25. If Agents Were Angels, No Governance Would Be Necessary: Out-of-Band Policy Enforcement at a Trusted Tool BoundaryLLM safety and security → Prompt injection and agent security
  26. PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  27. LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
  28. Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
  29. Code as Worlds: Agentic Discovery of Executable World Representations for Physical ReasoningLLM reasoning → Spatial and embodied reasoning +2
  30. Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety ModeratorLLM safety and security → Vision-language and text-to-image safety
  31. Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  32. SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication CoachingLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. A Deeper Analysis of Block-Sparse FeaturizersMechanistic interpretability → Sparse autoencoder training and evaluation
  34. Trajectory-Level Speculative Decoding for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  35. DAMP: Decay-Aware Mixed-Precision Recurrent-State QuantizationEfficient LLM inference and serving → KV cache quantization
  36. Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment GapLLM safety and security → Backdoor and data poisoning attacks
  37. How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted AttributionMechanistic interpretability → Circuits and mechanistic analysis
  38. WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement LearningWorld models → World model security and GUI agents +2
  39. Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  40. Thinking Costs Tokens: When More Structure is Worth the PriceLLM reasoning → Test-time compute and efficient thinking
  41. A Survey on Rubric-Guided Reinforcement Learning for Language ModelsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  42. Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability StudyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  43. INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical ReasoningLLM reasoning → Mathematical reasoning
  44. ROPE: Routed Origin Policy Enforcement against Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  45. UrbanGround: From Local Perception to Spatial Agency in a Real-Scale CityMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  46. CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure ModesLLM reasoning → Test-time compute and efficient thinking
  47. TTPO: Test-Time Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  48. Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?LLM agents and tool use → Agent threats, guardrails and governance
  49. RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill EvolutionLLM agents and tool use → Agent threats, guardrails and governance +1
  50. Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution AuditLLM agents and tool use → Agent threats, guardrails and governance
  51. Boosting LLM Exploration via Weak-Model Guidance in RLVRLLM reasoning → Reinforcement learning for reasoning
  52. Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual InformationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  53. CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical SimulatorsWorld models → Embodied and robot world models
  54. Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust PredictionMechanistic interpretability → Interpreting biomedical and science models
  55. FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA InferenceVision-language-action models → Efficient VLA inference and adaptation
  56. Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World ModelsWorld models → Latent predictive world models
  57. Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPOLLM reasoning → Reinforcement learning for reasoning
  58. INTENT-AS-A-TOOL Makes it Easy to Track Agentic MisalignmentLLM agents and tool use → Agent threats, guardrails and governance
  59. PAWBench: How Far Are We from Probabilistically Aligned World Modeling?World models → Video-generation world models and simulators
  60. One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of RolesLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent BenchmarksLLM agents and tool use → Software engineering coding agents
  62. R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World ModelsWorld models → Video-generation world models and simulators
  63. Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware VerificationLLM agents and tool use → Software engineering coding agents
  64. Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI SystemsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  65. Naive Prompt Optimization: Rethinking the Need for Complex Prompt SearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  67. What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. Making Latent Evolution Explicit: Operator-Structured Transitions for World Action ModelsWorld models → Embodied and robot world models
  69. Circuit Condensation: Post-Training that Concentrates a Behavior's Causal CircuitMechanistic interpretability → Circuits and mechanistic analysis
  70. SPA: Securing Persistent LLM Agents Across Queries with Plan-First Information-Flow ControlLLM agents and tool use → Agent threats, guardrails and governance
  71. STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot CollaborationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  72. BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health SensingLLM agents and tool use → Medical and scientific domain agents
  73. PACE: A Unified Condense-and-Extract Paradigm for Fast VLM InferenceLLM reasoning → Multimodal reasoning +1
  74. Knowledge Distillation Driven Semantic NOMA with GAN Refinement for 6G Robotic Vehicle NetworksKnowledge distillation → General knowledge distillation methods
  75. TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause AttributionLLM agents and tool use → Software engineering coding agents
  76. When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded DialogueLLM reasoning → Audio-language model reasoning
  77. X-WAD: eXplainable Web Anomaly DetectionLLM safety and security → Backdoor and data poisoning attacks
  78. STAR : Sentence Translation Alignment Rate for Document-to-Document Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  79. Diffusion Policies for Short-Horizon Planning in Robot Crowd NavigationDiffusion models → Diffusion and flow policies for robotics
  80. ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error CorrectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  81. AgentDV: Closed-Loop Agentic AI for Hardware Design VerificationLLM agents and tool use → Software engineering coding agents
  82. When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  83. GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RLLLM reasoning → Knowledge- and tool-augmented reasoning +1
  84. Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  85. Small Frequency Corrections Can Change What Survives KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  86. TransMeme: A Multi-Agent Framework for Cross-Cultural Meme TranscreationLLM agents and tool use → General LLM agent frameworks and benchmarks
  87. pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology LearningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  88. The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  89. A Contract-Centered Architecture for Scalable and Manageable Agentic RuntimesLLM agents and tool use → Software engineering coding agents
  90. GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot ManipulationVision-language-action models → Reinforcement learning and post-training
  91. SpatialCrafter: Single Image World Modeling with Generative 3D ProxiesWorld models → Video-generation world models and simulators
  92. Emotional Preferences as Goal-Priority RegulationDeep reinforcement learning methods → RL training of language and agent models
  93. Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language ModelsKnowledge distillation → Multimodal distillation
  94. Performance Foundations of Parallel & Distributed Reasoning Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
  95. Reasoning about In-Context Samples for Machine-TranslationLLM reasoning → Reasoning benchmarks and evaluation
  96. Riemann-1.0: An Embodied World Action Model for Physical AIWorld models → Embodied and robot world models
  97. Disentangling Optimization Scale from Preference Scale in DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  98. FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User TicketsLLM agents and tool use → Software engineering coding agents
  99. The Guard That Cried Wolf: How Scary Words Make Agent Guardrails Refuse Legitimate ActionsLLM agents and tool use → Agent threats, guardrails and governance +1
  100. MVC-Bench: Benchmarking Calibration of Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
All 462
  1. Aphanta: Diagnosing Task-Aligned Image-Edited Intermediates for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  2. DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock ResearchLLM agents and tool use → Financial trading and forecasting agents
  3. GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent MemoryLLM agents and tool use → Agent memory systems
  4. TempJail: Temporal Jailbreak Attacks against Image-to-Video Generation ModelsLLM safety and security → Vision-language and text-to-image safety
  5. Gromov-Monge Flow Matching for Equivariant Graph GenerationDiffusion models → Flow matching, time series and science
  6. Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More RecoverableSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  7. RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and EditingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  8. From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical CapabilitiesLLM reasoning → Reasoning for agents, planning and code +1
  9. Climate Physics Dynamic MatchingDiffusion models → Flow matching, time series and science
  10. When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender SystemsLLM agents and tool use → Agentic recommender systems
  11. Self-OPD: On-Policy Distillation for Flow Matching Models without TeacherDiffusion models → Diffusion and flow policies for robotics +1
  12. C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  13. BekchiAI: Measuring, Observing, and Controlling LLM Agents in One ClickLLM agents and tool use → Agent threats, guardrails and governance
  14. Order Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language ReasoningLLM reasoning → Multimodal reasoning
  15. FIDA: Feature Instability-Driven Attack on Self-Supervised Facial RepresentationLLM safety and security → Backdoor and data poisoning attacks
  16. Reinforcement Learning-Based Control of CAV Platoon Joining Maneuvers in Mixed TrafficDeep reinforcement learning methods → RL for autonomous driving and traffic
  17. From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and SegmentationLLM reasoning → Clinical and biomedical applications +1
  18. Towards Safe Reinforcement Learning with Reduced Conservativeness: A Case Study on Drone Flight ControlDeep reinforcement learning methods → Safe and constrained RL
  19. LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream EcosystemsLLM agents and tool use → Social simulation and multi-agent debate
  20. MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQAMultimodal LLMs / vision-language models → Medical vision-language models
  21. Evaluating Confidence-Gated Retrieval with Matched Trajectory ReplayLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic SolversLLM reasoning → Reasoning benchmarks and evaluation
  23. RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  24. TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  25. LLaVAFlow: Preserving Latent Alignment Flow for Parameter-Efficient Multimodal Fine-TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  26. Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image InpaintingDiffusion models → Inverse problems and image restoration
  27. Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic ReasoningLLM reasoning → Multimodal reasoning +1
  28. Multi-Image Visual Token Pruning in Large Visual Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  29. Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video DiffusionDiffusion models → Video generation
  30. Decoupling Planning and Control for Instructable AgentsWorld models → Embodied and robot world models +2
  31. Self-Reflective Multi-modal Reasoning for Short-Video Fake News DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  32. AI Control Scientist: LLM-driven Agentic System for Automated Control DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Instruction Quality Matters: Refining Instructions for Effective Preference LearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. Cross-Architecture Knowledge Distillation from a Vision Foundation Model to a Lightweight Visual State Space Model for Tea Leaf Disease ClassificationKnowledge distillation → Detection and dense prediction distillation
  35. MeshPriorDiT: Hierarchical Modeling for Action-Conditioned Cloth DynamicsDiffusion models → 3D, point cloud and scene generation
  36. Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific ResearchLLM agents and tool use → Web, search, and research agents
  37. Self-Augmented Diffusion Guidance for Physics-Informed GenerationDiffusion models → Flow matching, time series and science
  38. AgentFold: Closed-Loop Agentic Search for Protein Folding Model DesignLLM agents and tool use → Medical and scientific domain agents
  39. G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image ClassificationLLM reasoning → Multimodal reasoning +1
  40. Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget SeedsLLM safety and security → Machine unlearning
  41. Residual Deep Reinforcement Learning-Based Computed Torque Control for a Cable-Driven Lower-Limb Rehabilitation Robot under Disturbances and Parametric UncertaintiesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  42. Generative Semantic Scene CompletionDiffusion models → 3D, point cloud and scene generation
  43. Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  44. Rethinking Message Passing as Retrieval for Text-Attributed Graph LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  45. UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-LocalizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  46. Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  47. LiveVVT: High-Fidelity Video Virtual Try-On in Real TimeDiffusion models → 3D, point cloud and scene generation
  48. AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual SuitabilityMultimodal LLMs / vision-language models → Image editing and quality assessment
  49. Towards Expert Financial QA via Self-Improving RAGRetrieval-augmented generation → Legal and financial RAG
  50. Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMsLLM reasoning → Reinforcement learning for reasoning +1
  51. Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral InferenceLLM reasoning → Reasoning benchmarks and evaluation
  52. PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot ManipulationVision-language-action models → World model-based VLA
  53. Simple Actors and Deep Critics for Scalable Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +2
  54. Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEsMixture-of-experts → Expert routing strategies
  55. FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic ManipulationVision-language-action models → Failure recovery and robustness
  56. Information-Guided Frontier Decoding: Contextual Utility-Driven Commitment in dMLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  57. AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-CallingLLM agents and tool use → Tool learning and function calling
  58. FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  59. hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic AdvisingRetrieval-augmented generation → Agentic RAG, agents and memory
  60. Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic PaperLLM reasoning → Knowledge- and tool-augmented reasoning +2
  61. SimCast-S2S: A Computationally Efficient Diffusion Model for Subseasonal Precipitation ForecastingDiffusion models → Flow matching, time series and science
  62. Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language ModelsLLM reasoning → Clinical and biomedical applications
  63. VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete DiffusionDiffusion models → Flow matching, time series and science
  64. Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  65. Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  66. Preference Flow Matching with Spectral Factorization for Micro-video RecommendationDiffusion models → Diffusion recommenders
  67. TrapVLA: Trapping Vision-Language-Action Models in Configured Failure ModesVision-language-action models → Failure recovery and robustness +1
  68. Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure SignalsDeep reinforcement learning methods → Safe and constrained RL
  69. SPT: Skills as Pre-Training Data for Agentic Language ModelsLLM agents and tool use → Agent skill learning and evolution
  70. DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving RepositoriesLLM agents and tool use → Software engineering coding agents
  71. SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +2
  72. DuMateBench: Evaluating Autonomous Agents in Complex Real-World WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  73. Chart2SVG: Editable SVG Generation from Raster Chart ImagesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  74. A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model FamiliesLLM safety and security → Jailbreaking
  75. Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  76. Zero-Shot Video Restoration and Enhancement with Text-to-Image Latent Diffusion Models and Multi-Modal ReferencesDiffusion models → Inverse problems and image restoration
  77. Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity
  78. PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging
  79. A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data
  80. When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection
  81. The Recall Ceiling of LLM Recommendation Reranking
  82. CleanScore: Black-Box Benchmark Audits with Negative Controls and Sensitivity Bounds
  83. Gaussian Process Decorrelation for Spatiotemporal Deep Learning-Based Snow Water Equivalent Prediction
  84. Interpretable Stress Detection from ECG Signals Using Motif-Based Anomaly Analysis
  85. OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games
  86. SCoR: A Hierarchical Framework for Forecasting Relations Between Scientific Concepts
  87. Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator
  88. Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features
  89. Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery
  90. Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
  91. The Curse of Multilinguality in Lexical Normalization
  92. Enhancing MRI Brain Tumor Edge Detection: A Hybrid Preprocessing Approach Utilizing CLAHE
  93. STEP: A Modular Silent Trial Engine for Operational Evaluation of Digital Pathology AI in Routine Workflow
  94. Variable-Granularity Tokenization for High-Resolution Object Detection
  95. Is Deformable Image Registration Ready for Brain Metastasis Reirradiation Dose Accumulation? A Longitudinal MRI Benchmark of Registration Accuracy
  96. ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery
  97. Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting
  98. Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching
  99. SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation
  100. Growing a Stand, Not a Tree: Joint Canopy Generation Reproduces Crown Shyness
  101. Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal Conflict
  102. SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs
  103. Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots
  104. Beyond Procrustes distances: a multilinear Gromov-Wasserstein distance capturing chirality
  105. Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models
  106. Informational Antilocality and the Locality Bias in LLMs
  107. Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess
  108. The role of parameter Jacobians in the stability of network outputs
  109. ABCD: Alpha-Composited Block Coordinate Descent: Constant-VRAM Training for Large Radiance Fields
  110. Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls
  111. Leveraging a Foundation Model for the EEG-Based Diagnosis of Alzheimer's Disease
  112. PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation
  113. Beyond Non-IID: Learner--Client Distribution Mismatch in Federated Learning
  114. DART-FL: Burst-Aware Multitask Federated Learning under Dynamic Inference Demand at the Edge
  115. On the Computational and Statistical Efficiency of the Empirical Maximum Entropy on the Mean Method
  116. RiskBlend: A Multi-Signal Framework for Test Input Prioritization in Machine Learning Regression Testing
  117. Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance
  118. CARDINAL Predicts Cardiovascular Risk From Non-contrast Cardiac CT
  119. SafeStep: An Interactive Demonstration of Semantic Communication for Pedestrian Safety Monitoring
  120. A Framework for Object-Centric Predictive Monitoring of Collaborative Processes
  121. Report Supervision
  122. Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay
  123. When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages
  124. More Data Cannot Break a Symmetry: Identifiability by Design
  125. Generative AI Expands the Intellectual Reach of Course Based Undergraduate Research Experiences (CUREs)
  126. Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification
  127. Depth-Aware Pothole Detection Using YOLO and RT-DETR at the Edge
  128. LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data
  129. Quantum SEDONet: Spectrally-Embedded Quantum Deep Operator Networks for Partial Differential Equations
  130. Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates
  131. ShiftSplit-AD: Separating Domain Shift from Defects in Foundation-Feature Visual Anomaly Detection
  132. Robust model-based clustering via mixtures of multivariate pseudo-Voigt distributions
  133. Physics-informed learning for the inverse problem in resonant ultrasound spectroscopy
  134. Quanta Perception as Probabilistic Events
  135. Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
  136. Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution
  137. VidParse: Online Parsing of Egocentric Procedures Like a Pro
  138. Towards a mathematical theory of superposition
  139. Ab initio Modeling of MoS2/Oxide Device Interfaces with Machine Learned Electronic Structures
  140. Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
  141. FVeinSyn: Synthetic Finger Vein Image Generator
  142. Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics
  143. When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
  144. Destroy Me: Automatic Artifact Generation for Histopathology Images
  145. Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems
  146. Optimal Transport for Network Comparison: A Unified Review with New Spectral Bounds and Machine Learning Applications
  147. WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
  148. SWE-Prime: Fewer Trajectories, Better Performance
  149. From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
  150. Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
  151. Stochastic Estimation of Transduced Language Models
  152. Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
  153. Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
  154. Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
  155. Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
  156. Reconstructing Humans and Objects in Interaction using Large Reconstruction Models
  157. How Language Models Organize and Structure Moral Knowledge
  158. LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
  159. RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
  160. Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditions
  161. CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
  162. Token-Level Advertising
  163. D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
  164. Universality and sharp thresholds for ellipsoid fitting
  165. Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within 5090
  166. Stageboost: Recommending Signals Based on Counterfactual Estimation
  167. KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representations
  168. Sophistication in GenAI Use: Field Evidence from a Large Firm
  169. Your Voice Cloning System is Secretly a Voice Anonymizer
  170. RCMN: Understanding Misleadingness in Influential Public Discourse
  171. Pair-Level Essay-Scale Republication and Reuse from Fragmented Historical Text Reuse: A Workflow Study on Eighteenth-Century Books and Newspapers
  172. Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
  173. Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting
  174. A Finite-Sample Analysis of Quantile Temporal-Difference Learning
  175. Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit
  176. QuantumBoostNet: Hybrid Classical-Quantum Cardiac View Identification
  177. Comparative Evaluation of 3D Reconstruction Methods for Immersive Visualization of Laboratory Objects
  178. LLMs Can Design Near-Optimal OR Algorithms
  179. Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach
  180. Detection of Christmas tree plantations from high-resolution aerial imagery. A case study in the French Morvan
  181. MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
  182. TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
  183. Sidecar: Training-Free Semantic Reuse for Character-Consistent Free-form Visual Storytelling
  184. Decoupled I/O-Dominant Pipelines for Large-Scale Whole-Slide Image Embedding Extraction
  185. BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models
  186. Enforcing Dirichlet Boundary Conditions in Operator Learning
  187. Compositional Online Learning for Semantic Data Processing Systems
  188. Importance Scoring of Transformer Attention Heads in Learning Tabular Data
  189. UniFLM: United Segmentation and Measurement on Fetal Limb Ultrasonic Image
  190. An Offline Smartphone Check for Drug Interactions and Past Reactions in Handwritten Prescriptions: A Technical Feasibility Study in Rural Bangladeshi Outpatient Care
  191. HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition
  192. On the approximation of posterior laws in compound loss models by conditional Wasserstein GANs
  193. DINOcular: Self-Supervised Visuospatial Representations
  194. CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection
  195. Accurate prediction is not profitable advice: profit-based evaluation of machine learning nitrogen recommendations in winter wheat
  196. Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classification
  197. Vision-centric generative AI models: A software-hardware perspective
  198. Unsupervised Adaptation of 3D CT Foundation Models for 3D CBCT Segmentation
  199. When Interference Graphs Evolve: Doubly Robust Estimation of Dynamic Peer Effects
  200. LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration
  201. SSMB: Self-Supervised Local Feature Detection under Motion Blur
  202. Parameter-Efficient pretrained-CT-to-MRI Transfer for Rectal Cancer Segmentation: Performance-Calibration Trade-offs
  203. Temporal Sensitivity Analysis of Tessera Embeddings
  204. Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition
  205. Magpie: Real-Time World Renderer for Interactive Games
  206. Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
  207. Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models
  208. Data-efficient crack quantification in lithium-ion cathodes using foundation model transfer
  209. Inductive Correlation Clustering with Graph Neural Networks
  210. Ultra Low-Power, Lightweight, Probabilistic RSS-Based Path Reconstruction: A System for Landscape-Scale Bee Tracking
  211. ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification
  212. BPMN4CAI: A BPMN Extension for Modeling Dynamic Conversational AI
  213. Thomson: Continual Learning of Frontier Models for SovereignAI
  214. Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection
  215. Over-The-Air Extreme Learning Machines with Nonlinear Stacked Intelligent Metasurfaces
  216. Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models
  217. TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction
  218. EditaLive! Unified Character Video Editing for Live Streaming
  219. Cone Rayleigh Levels: Finite Perturbations and Certified Control
  220. How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space
  221. Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?
  222. Linear Independence of Polynomial Compositions and Identifiability of Deep Neural Networks
  223. DocTalkBN: A Novel Dataset of Expert Telemedicine Conversations in Bengali
  224. SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring
  225. LAAF: A Layered Accountability Architecture Framework for LLM Applications
  226. Automated 2D and 3D Segmentation of AMD and DME Lesions in OCT
  227. Active sensing to characterize the heterogeneity of plant stress
  228. Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors
  229. Learning Transverse Momentum Distributions from Raw Scattering Events via Conditional Diffusion
  230. Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation
  231. Unifying Detection and Adaptation in Task-Free Continual Learning
  232. Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
  233. An Accurate and Single-Communication Federated Inference Algorithm
  234. Anatomy-Guided Foundation Model Adaptation with Within-Case Prototype Supervision for Standard Plane Detection in Fetal Ultrasound Blind Sweeps
  235. Research Design Tracking and Assessment for the Social Sciences
  236. Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
  237. Omni-Interactive Universal Embedder
  238. Multi-Person Human Motion Forecasting in Complex Scenes
  239. Cascaded Batch Prompting
  240. Representing and Parsing Korean Constituency Structure at Different Levels of Granularity
  241. Differentiable Jitter Correction using Deep Learning-based Image Quality Metric for Phase-Contrast Micro-CT
  242. ITL: Interpretable Document Alignment with Structured Reference Frameworks
  243. FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetch
  244. Representation Measurements Under Function-Preserving Reparameterizations
  245. Magnon-induced phononic Chern insulator
  246. A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems
  247. Virtual iEEG from Scalp EEG: Charting the Landscape of Source Imaging, Intracranial Inference and Reconstruction
  248. Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units
  249. ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions
  250. Decentralized Multitask Learning over Learned Task Graphs
  251. JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols
  252. Terrain signatures in Welsh settlement names
  253. Why not to use the Gaussian kernel
  254. Squeezing More from Limited Data with Recursive Transformers
  255. TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements
  256. ClusterAttention: A training-free speedup of bidirectional attention
  257. Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
  258. Adversarial Training Without Input Gradients via Low-Rank Householder Expansions
  259. Packora: Systematic Design for Generative Molecular Crystal Structure Prediction
  260. Geo-LoRA: Geometry-Aware Subspace Evolution for Low-Rank Adaptation in Continual Learning
  261. Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS
  262. A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
  263. KISS-GS: 3D Gaussian Splatting Compression Kept Simple
  264. 4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation
  265. Data-driven Koopman mode approximation: A neural power iteration algorithm
  266. KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training
  267. A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
  268. Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding
  269. TabuLM: Morphology-Aware Tabular Pre-training for Low-Resource Languages
  270. AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations
  271. Tether the Subject, Release the Scene: Query-Aware Memory Routing for Long-Horizon Autoregressive Video Generation
  272. Dose-PlanNet: Physics Based Radiotherapy Dose Prediction with Deep Learning
  273. Counterfactual Bias Testing for Application Tracking System
  274. AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion
  275. Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
  276. Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry
  277. Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency
  278. PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?
  279. Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion
  280. Contact Geometry and Covariance Deficits in Volume-Sampled Least Squares
  281. CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction
  282. A Geometry-Driven, Framework-Agnostic Optimization for Object Pose Estimation
  283. Rethinking Image Processing for the Age of AI: A Problem-First Framework for Scientific Progress
  284. SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting
  285. Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocation
  286. Bridging short- and medium-range weather forecasting with machine learning
  287. Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
  288. Incremental Recommendation via Causal Models
  289. On the Indistinguishability of Human v/s AI Generated Text
  290. Beyond Client Averaging: A Client-Independent Second-Order Stationary-Bias Component in Stochastic SCAFFOLD
  291. Neural Renormalization Group Flow for Percolation
  292. Categorizer Automata for Discounted-Sum Payoffs
  293. Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers
  294. DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?
  295. Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions
  296. Glass Surface Detection Grounded in 3D Visual Geometry
  297. Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case
  298. Letters hide the truth from our eyes: English homophones have meaningfully different phonetic realizations
  299. FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs
  300. Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction
  301. Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
  302. Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs
  303. GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment
  304. Parameter Efficient Continual Learning for Sparse Event-Based Transformers
  305. Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing
  306. Accelerating Scientific Research with Gemini in the Real-World
  307. PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments
  308. Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation
  309. Five Primitives for Governing Autonomous AI Agents at Runtime
  310. Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
  311. Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling
  312. Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification
  313. BLANC: Discovering Patent White Space via Changes in Normalized Pointwise Mutual Information Between Multi-View Clusters
  314. SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
  315. FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models
  316. RECAP-Forcing: Retaining Content Appearances for Long Video Generation
  317. Beyond the Proving Ground: Independent Public-Road Testing of Assisted Lane Change Systems using LiDAR
  318. Hull First, Wake Second: Wake-Reliance Suppression for Robust Maritime Vessel Detection
  319. PailitaoGR: Latent Think-with-Images for Generative Image Retrieval
  320. CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
  321. When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy
  322. Robust Neural Stimulation Response Modeling Through Meta-Learning and Pretraining
  323. Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection
  324. Tissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution
  325. Real-time Unsupervised Object Discovery from Asynchronous Event Streams
  326. Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation
  327. Who Remains, What Changes: Identity Anchored Composed Gait Retrieval
  328. Risks and Controls for Multi-Agent Systems: an analytical framework for deployment of AI agents across organisational boundaries
  329. Text-to-seed generation: Training-free open-vocabulary seeded semantic segmentation via re-purposing diffusion as text-guided seed generator
  330. A Unified Descriptive-Complexity Framework for Model Selection under Correlated Designs
  331. Technical Comparative Benchmarking Study: Advanced AI Hybrid Methods for Renewable Energy Farm Optimization and Forecasting
  332. On efficiency gains via augmenting a tiny sample with a massive auxiliary sample
  333. The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning
  334. Benchmarking Clinical Decision Pathway Adherence in Large Language Models
  335. DPA-I2P: Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration in Autonomous Driving
  336. J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data
  337. Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations
  338. Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference
  339. Dynamical phase selection controls compute scaling in looped transformers
  340. Hadamard Flattening and Gaussian Pooling Sketch for Least Squares with Coordinate-wise Guarantee
  341. Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations
  342. Camera Calibration Using Inaccurate and Asynchronous Discrete GPS Trajectory from Drones
  343. Predicting Quantifiability from Primary Screens to Prioritize Dose-Response Profiling
  344. Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
  345. FAN-LoRA: A Fourier-Adaptive Nonlinear Low-Rank Adaptor for Medical Foundation Model Domain Adaptation
  346. PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
  347. Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue
  348. High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube
  349. HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence
  350. Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning
  351. Sharp Minimax Regret for Infinite-Memory Logistic Prediction
  352. Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update
  353. NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning
  354. Explicit Bounds on the Entropy of Piecewise H"older Graphon Models
  355. Systematic Literature Review of Machine Learning Models and Applications for Text Recognition
  356. RTNav: Towards Real-Time Zero-Shot Object Navigation
  357. Video-FLAIR: Not Whether to Reason, But How
  358. A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints
  359. Bayesian methods and Markov chain Monte Carlo algorithms for curve reconstruction and point cloud data analysis
  360. Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation
  361. GVS5H: Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance
  362. DTD-VAE: Disentangled Temporal Dependencies VAE for Credit Risk Prediction