mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 1 Jul 2026

511 papers

  1. BudgetBench: A Budget-Tiered Protocol and Pilot Harness for Memory Strategy Evaluation in Local Large Language Model AgentsLLM agents and tool use → Agent memory systems
  2. A Governance Methodology Layer for AI-Assisted Software Development: Defect Taxonomy, Controlled Ablation, and a Test of Process-Over-CapabilityLLM agents and tool use → Software engineering coding agents
  3. R2Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  4. Probe Generalization as Subspace Selection for OOD Deception DetectionMechanistic interpretability → Probing deception, bias and beliefs
  5. SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive InteractionLLM reasoning → Multimodal reasoning
  6. LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review PlatformLLM agents and tool use → Web, search, and research agents
  7. Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified MemoryLLM agents and tool use → Software engineering coding agents +1
  8. Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AILLM agents and tool use → General LLM agent frameworks and benchmarks +1
  9. You Are What You Prompt: Prompt Quality, Domain Shift, and Uncertainty in Agrifood Vision-Language ModelsMultimodal LLMs / vision-language models → Agricultural vision-language models
  10. Think in Latent, Explain in Language: Self-Explainable Latent ReasoningLLM reasoning → Test-time compute and efficient thinking
  11. Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI AgentsLLM agents and tool use → GUI and mobile agents
  12. Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score VarianceMechanistic interpretability → SAE features and their applications
  13. On the Limits of Support-Preserving Alignment and Bounded FilteringLLM safety and security → Safety alignment, refusal and guardrails
  14. Precomputing the Future-Offset Average in TriAttentionLLM reasoning → Test-time compute and efficient thinking +1
  15. In-Context Reinforcement Learning under Non-Stationarity: A SurveyDeep reinforcement learning methods → Deep RL algorithms and representations
  16. CHARLIE: An On-Premise Multi-Agent Retrieval-Augmented Generation System for Evidential Reasoning in Forensic ScienceRetrieval-augmented generation → Agentic RAG, agents and memory
  17. TAG: A Lightweight Framework for Test-Driven Agentic Artifact GenerationLLM agents and tool use → Software engineering coding agents
  18. Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformersEfficient LLM inference and serving → Token pruning and merging for ViTs
  19. Latent Visual Cache for Video ReasoningMultimodal LLMs / vision-language models → Video understanding with MLLMs
  20. ChainSWE: Benchmarking Coding Agents on Multi-Bug Software MaintenanceLLM agents and tool use → Software engineering coding agents
  21. DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object ManipulationVision-language-action models → 3D and spatial-aware VLA
  22. AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM AgentsLLM agents and tool use → Tool learning and function calling
  23. Evaluating Agentic Harness Systems for Autonomous Computational PathologyLLM agents and tool use → Medical and scientific domain agents
  24. Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural TransferLLM agents and tool use → Agent skill learning and evolution
  25. Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  26. H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy DistillationKnowledge distillation → Multimodal distillation
  27. Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic ReasoningLLM reasoning → Multimodal reasoning +2
  28. Evaluating Intellectual Property Guardrails of Generative Image Models: A Technical ReportLLM safety and security → Watermarking generated content and models
  29. ESC: Emotional Self-Correction for Reliable Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  30. Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active PerceptionWorld models → Latent predictive world models
  31. OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3World models → World models for language agents
  32. Wind-Aware Reinforcement Learning Control of a Small Quadrotor Using Learned Onboard Wind Estimation in Simulated Atmospheric TurbulenceDeep reinforcement learning methods → RL for robot navigation and UAV control
  33. Mean Field Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  34. Multi-Head Recurrent Memory AgentsLLM agents and tool use → Agent memory systems
  35. The risk of KV cache compressionEfficient LLM inference and serving → KV cache optimization
  36. Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic SystemsLLM reasoning → Reasoning for agents, planning and code +1
  37. Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought LearningLLM reasoning → Prompting and chain-of-thought reasoning
  38. Janus: a Playground for User-Involved Agentic Permission ManagementLLM agents and tool use → Agent threats, guardrails and governance
  39. The Agentic Garden of Forking PathsLLM agents and tool use → Social simulation and multi-agent debate
  40. Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering TaskMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  41. From Monolingual to Multilingual: Evaluating Mamba for ASR in South African LanguagesState-space sequence models (S4, Mamba) → Speech and audio SSMs
  42. Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RLLLM reasoning → Reinforcement learning for reasoning +1
  43. Procedural Memory Distillation: Online Reflection for Self-Improving Language ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  44. Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQALLM agents and tool use → Multimodal and embodied agents
  45. Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian WorkflowsLLM agents and tool use → Reinforcement learning for LLM agents
  46. From Anatomy to Smells: An Empirical Study of SKILL.md in Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  47. On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical DomainMixture-of-experts → Medical and biomedical MoE +1
  48. FaithMed: Training LLMs For Faithful Evidence-Based Medical ReasoningLLM reasoning → Clinical and biomedical applications
  49. Discrete Diffusion Language Models for Interactive Radiology Report DraftingDiffusion models → Medical imaging and segmentation
  50. CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode CollapseLLM reasoning → Reasoning benchmarks and evaluation
  51. IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  52. Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical CodebasesLLM agents and tool use → Software engineering coding agents
  53. Risk Architecture for AI-Native Engineering Teams: An Organizational Framework for Agentic System GovernanceLLM agents and tool use → Agent threats, guardrails and governance
  54. Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLILLM agents and tool use → Software engineering coding agents
  55. The Rollout Infrastructure Tax in Coding-Agent Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  56. Multi-Objective Exploration and Preference Optimization via Mutual InformationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  57. RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned EvaluationLLM reasoning → Reasoning for agents, planning and code
  58. CommonRoad-Game: A Human-in-the-Loop Simulation Framework for Autonomous DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
  59. Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow MatchingVision-language-action models → Safety and adversarial attacks +1
  60. MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map GenerationDiffusion models → Diffusion and flow policies for robotics
  61. Auto-FL-Research: Agentic Search for Federated Learning AlgorithmsLLM agents and tool use → Agentic AI for wireless networks
  62. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  63. HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent CachingRetrieval-augmented generation → Generation and context integration +1
  64. WaveLander: A Generalizable Hierarchical Control Framework for UAV Landing on Wave-Disturbed Platforms via Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  65. Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM SafetyLLM safety and security → Safety alignment, refusal and guardrails
  66. Language-Critique Imitation Learning from Suboptimal DemonstrationsOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  67. Theoria: Rewrite-Acceptability Verification over Informal Reasoning StatesLLM reasoning → Mathematical reasoning
  68. RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility RescueLLM agents and tool use → Software engineering coding agents
  69. FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action ModelVision-language-action models → Generalist VLA models and benchmarks
  70. Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?LLM agents and tool use → Software engineering coding agents
  71. Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual ReasoningLLM reasoning → Multimodal reasoning +1
  72. Right in the Right Way: LM Training with Verifiable Rewards and Human DemonstrationsLLM reasoning → Reinforcement learning for reasoning
  73. QuasiMoTTo: Quasi-Monte Carlo Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  74. Diffusion-GR2: Diffusion Generative Reasoning Re-rankerLLM reasoning → LLM reasoning for recommendation +2
  75. Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated ControlLLM agents and tool use → Agent threats, guardrails and governance
  76. EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image GenerationDiffusion models → Image generation, text-to-image and editing
  77. Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven SearchLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  78. Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply ChainsLLM agents and tool use → Agent skill learning and evolution
  79. SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore ProfilesDiffusion models → Flow matching, time series and science
  80. SAGE: Structured Agentic Graph Editing for Software DiagramsLLM agents and tool use → Multimodal and embodied agents
  81. Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software EngineeringLLM agents and tool use → Software engineering coding agents
  82. LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  83. Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool UseLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. Staleness-Learning Rate Scaling Laws for Asynchronous RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  85. Where Am I? Semantic Map Grounding via Vision-Language Models for Multi-Modal LocalizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  86. Message Passing Enables Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
  87. MemSyco-Bench: Benchmarking Sycophancy in Agent MemoryLLM agents and tool use → Agent memory systems
  88. GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV CacheEfficient LLM inference and serving → KV cache quantization
  89. Agentic generation of verifiable rules for deterministic, self-expanding reaction classificationLLM agents and tool use → Medical and scientific domain agents
  90. RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy EvaluationWorld models → Embodied and robot world models +1
  91. GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process SupervisionLLM reasoning → Spatial and embodied reasoning +1
  92. GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  93. Conversable Complexity: Agentic LLM Collectives as Interpretable SubstratesLLM agents and tool use → General LLM agent frameworks and benchmarks
  94. Behavior-Adaptive Conversational Agents: Toward a Fluid Personality FrameworkLLM agents and tool use → Social simulation and multi-agent debate
  95. The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training MethodologyMechanistic interpretability → Knowledge and representations inside LLMs
  96. SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction TestsLLM agents and tool use → Software engineering coding agents
  97. SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned EnvironmentsLLM agents and tool use → Multimodal and embodied agents
  98. AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  99. Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question AnsweringRetrieval-augmented generation → Agentic RAG, agents and memory +1
  100. A Geometric Perspective on Composable Emotion Steering in Text-to-Speech ModelsMechanistic interpretability → Activation steering methods
All 511
  1. From Runtime Records to Legal Findings: An Evidentiary-Adequacy Criterion for Agentic AI OversightLLM agents and tool use → Agent threats, guardrails and governance
  2. Leveraging LLM-Based Agentic Systems to Generate Quantum Applications for Test OptimizationLLM agents and tool use → Medical and scientific domain agents
  3. Post-Training Pruning for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  4. Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual RecombinationLLM reasoning → Clinical and biomedical applications +1
  5. From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form NarrativesLLM agents and tool use → Multimodal and embodied agents
  6. Valdi: Value Diffusion World ModelsWorld models → Latent predictive world models +1
  7. From Registry to Repository: How AI Agent Skills Are Written, Adapted, and MaintainedLLM agents and tool use → Software engineering coding agents
  8. Calibrating the Instrument: Controllability of an LLM-Driven Synthetic PopulationLLM agents and tool use → Social simulation and multi-agent debate
  9. Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and DocumentsRetrieval-augmented generation → Hallucination detection in RAG
  10. DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model PriorsWorld models → Video-generation world models and simulators
  11. OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial MappingLLM reasoning → Spatial and embodied reasoning +1
  12. CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  13. From World Models to World Action Models: A Concise Tutorial for RoboticsWorld models → World models for language agents
  14. Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical WorkflowsLLM agents and tool use → Web, search, and research agents
  15. Knowledge-Enhanced Agentic Vulnerability RepairLLM agents and tool use → Agent threats, guardrails and governance
  16. Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising OptimizationDiffusion models → Image generation, text-to-image and editing
  17. Towards High-Resolution Visual Perception via Hierarchical Entity ExplorationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-trainingDeep reinforcement learning methods → Deep RL algorithms and representations
  19. Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from VideosDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. Task-Relevant Representation Decoupling for Visual Reinforcement Learning GeneralizationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  21. LeVLJEPA: End-to-End Vision-Language Pretraining Without NegativesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  22. SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive InferenceMixture-of-experts → Vision mixture-of-experts +1
  23. Accelerating Discrete Diffusion Models with Parallel-In-Time SamplingDiffusion models → Diffusion foundations and sampling
  24. Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image PersonalizationDiffusion models → Image generation, text-to-image and editing
  25. MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  26. Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  27. Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric AbsorptionEfficient LLM inference and serving → Fast autoregressive visual generation
  28. Self-GC: Self-Governing Context for Long-Horizon LLM AgentsLLM agents and tool use → Agent memory systems
  29. M2Note: Continual Evolution of Vision Language Models via Mistake Notebook LearningLLM reasoning → Multimodal reasoning
  30. AdaBoosting Text Prompts for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  31. ABot-M0.5: Unified Mobility-and-Manipulation World Action ModelWorld models → Embodied and robot world models
  32. Path Planning in Physically Viable World ModelsWorld models → World models for navigation
  33. Domain Arithmetic: One-Shot VLA Adaptation under Environmental ShiftsVision-language-action models → Generalist VLA models and benchmarks
  34. Linguistic Relative Policy Optimization for Video Anomaly ReasoningLLM reasoning → Chain-of-thought reasoning for driving +1
  35. Not All Prediction Targets Keep Training-Free Diffusion Guidance on the ManifoldDiffusion models → Diffusion foundations and sampling
  36. Coachable agents for interactive gameplayLLM agents and tool use → Reinforcement learning for LLM agents +1
  37. Learning-based control of a single-DOF Aero systemDeep reinforcement learning methods → RL for robot navigation and UAV control
  38. Loss Smoothing for Stable Adaptation Under Distribution ShiftDeep reinforcement learning methods → Deep RL algorithms and representations
  39. AGI Maze as a Benchmark Framework for World-Modeling AgentsWorld models → World models for language agents +1
  40. Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed GapLLM reasoning → Multimodal reasoning
  41. Auditing Forgetting in Limited Memory Language ModelsLLM safety and security → Machine unlearning
  42. Multi-Turn Agentic Scientific Literature Search via Workflow InductionLLM agents and tool use → Web, search, and research agents
  43. Low Perplexity is Repetition: A One-Dimensional Self-Conditioning Attractor in Continuous Diffusion LMsDiffusion models → Discrete and text diffusion
  44. HARC: Coupling Harmfulness and Refusal Directions for Robust Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  45. Dual-Confidence Contrastive Decoding for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  46. EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent ScenesLLM agents and tool use → Multimodal and embodied agents
  47. GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data EngineLLM reasoning → Multimodal reasoning +1
  48. Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic CompositionLLM reasoning → Reinforcement learning for reasoning +1
  49. Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange SystemsOffline RL and imitation learning from data → Robot learning from demonstration
  50. Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  51. AnF-DiffPET: Anatomy- and Frequency-Guided Diffusion for PET/CT DenoisingDiffusion models → Medical imaging and segmentation
  52. When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning ProblemsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  53. A Task-State Representation for Long-Horizon Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents
  54. MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild PhotosLLM reasoning → Spatial and embodied reasoning +1
  55. PAPA: Online Personalized Active Preference AlignmentDiffusion models → Diffusion and flow policies for robotics +1
  56. Efficient Multilingual Reasoning Transfer via Progressive Code-SwitchingLLM reasoning → Reasoning benchmarks and evaluation
  57. VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  58. Know When to Stop: Segment-Level Credit Assignment for Reducing OverthinkingLLM reasoning → Test-time compute and efficient thinking
  59. Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation TracesLLM agents and tool use → Agent threats, guardrails and governance +1
  60. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE ServingMixture-of-experts → Efficient MoE training and inference systems +1
  61. StochasT: Learning with Stochastic Turn Depth for Visual Instruction TuningLLM reasoning → Multimodal reasoning +1
  62. Multimodal Continuous Reasoning via Asymmetric Mutual Variational LearningLLM reasoning → Multimodal reasoning +1
  63. Multi-scale Mixture of World Models for Embodied Agents in Evolving EnvironmentsWorld models → World models for language agents +1
  64. Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory GenerationLLM agents and tool use → Multimodal and embodied agents
  65. Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  66. Understanding Why Language Models Hallucinate: Testing Reasoning Against PriorsLLM reasoning → Hallucination detection and mitigation
  67. Learning Gait-Aware Quadruped Locomotion with Temporal Logic SpecificationsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  68. Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward TrackingLLM agents and tool use → Agent threats, guardrails and governance
  69. PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator AgentsLLM agents and tool use → Web, search, and research agents
  70. Information-Regularized Attention for Visual-Centric ReasoningLLM reasoning → Multimodal reasoning +1
  71. Selective Test-Time Debiasing for CLIP via Reward GatingMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  72. KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG +1
  73. Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural DenoisingLLM agents and tool use → Multimodal and embodied agents
  74. The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +2
  75. DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  76. When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval BuffersLLM agents and tool use → Agent memory systems
  77. Learning Generalizable Skill Policy with Data-Efficient Unsupervised RLDeep reinforcement learning methods → Deep RL algorithms and representations
  78. Vitality-Aware Compression for Efficient Image-to-Shape Diffusion TransformersDiffusion models → 3D, point cloud and scene generation
  79. MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of ExpertsMixture-of-experts → Vision mixture-of-experts
  80. Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech SynthesisDiffusion models → Audio, speech and music
  81. ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  82. Personalized Object Identification and Localization via In-Context Inference with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  83. Unleashing More Actions via Action Compositional Training for VLA ModelsVision-language-action models → Human-video and latent-action pretraining
  84. Registry-Governed Agent Lifecycle:Completing EDDOps with Evaluation-DrivenRegistration, Promotion, and Retirement on AWS AgentCoreLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  86. Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical SystemsLLM agents and tool use → Agent threats, guardrails and governance
  87. (A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile AgentsLLM agents and tool use → Agent threats, guardrails and governance
  88. Queue-Aware Graph Reinforcement Learning for UAV-ISAC-Assisted Maritime Data CollectionDeep reinforcement learning methods → RL for robot navigation and UAV control
  89. RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in RetailWorld models → Video-generation world models and simulators +1
  90. Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent ConditionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  91. EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  92. Rosetta: Composable Native Multimodal PretrainingMixture-of-experts → Multimodal MoE models
  93. What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  94. Optimizing AI Inference Across the Deployment Stack
  95. Physics-informed neural networks by Gradient-Guided Gaussian Adaptive Sampling (3GAS-PINNs)
  96. Counterexamples as Feedback for Agent Self-Correction
  97. Accelerating LLM Inference via Vector Index Based Output Embeddings
  98. Explainable Artificial Intelligence for Customer Churn Prediction in Telecommunications: A Framework for CRM Integration
  99. Leveraging Large Language Models for Systematic Literature Review of Disease Spread Models
  100. Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reuse
  101. Self-Supervised Speech Representations Track Spoken Language Convergence to Adult Models in Infants and Children Who Are Deaf/Hard-of-Hearing
  102. A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer
  103. Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition
  104. EweAcT: Ewe behaviour aligned to accelerometer data for activity monitoring in extensive grazing systems
  105. Automatic Detection of Deaths from Social Networking Sites
  106. JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation
  107. Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models
  108. STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification
  109. SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
  110. Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule
  111. Challenges of Explainability in Continual Learning for Time Series Forecasting
  112. Air Quality Arena: A Large-Scale Multi-Region Ground Monitoring Dataset and Benchmark for Air Quality Forecasting with Time-Series Foundation Models
  113. CruiseBench: A Real-Flight-Aligned N-CMAPSS Benchmark for Engine RUL Prediction
  114. Bayesian Wind Tunnels for Model Selection
  115. Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
  116. Reliability-Aware Hard--Soft Physics-Informed Neural Networks for Robust Learning of Challenging Partial Differential Equations
  117. AV-JEPA: Extending LeJEPA to Audio-Visual Self-Supervised Learning
  118. Privacy-Preserving Industrial Ergonomics: mmWave-Based Automated REBA Scoring and Pose Estimation
  119. Knowledge-Centric Information Systems
  120. Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
  121. Scaling Weisfeiler-Leman Expressiveness Analysis to Massive Graphs with GPUs
  122. CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning
  123. CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness
  124. An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks
  125. CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification
  126. The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines
  127. Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits
  128. Reliability-Aware CT-MRI Registration: A Quality Engineering Framework with Stability Analysis and Risk Classification
  129. RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation
  130. Learning Effective Soliton Dynamics from Scattering Data
  131. MMAO-Cls: Metabolic Multi-Agent Optimization for Joint Feature Selection and Classifier Tuning
  132. Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
  133. Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Models
  134. IntentTune: Using user demand and personalization to resolve "unknown" query intents for e-commerce search
  135. Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score
  136. Robust and Explainable 3D Mode Shape Recognition Using Region-Aware Graph Neural Networks
  137. Parameter Golf: What Really Works?
  138. Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
  139. Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games
  140. Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
  141. How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
  142. Fully Unsupervised Detection of Physical Contacts on Subsea Cables via State-of-Polarization Monitoring
  143. Boundary-Aware Quantization: Finite-Scale Decision Geometry of Neural Classifiers
  144. Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
  145. World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments
  146. Comparing Architectures for Supervised Political Scaling
  147. Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
  148. Ember: A Kilobyte-State Optimizer for Token Interfaces
  149. Geometry-Aware R-Structured Kolmogorov-Arnold Networks
  150. Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes
  151. From Forgeries to Foundation Models: A Systematic Survey of Identity Document Attack and Detection
  152. How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation
  153. Sign in the Air to Unlock: An Interface for authentication in Virtual and Augmented Reality Powered by Point-Voxel Cross-Attention Network
  154. When Should Service Agents Reconsider? Difficulty-Routed Control in Customer-Service Operations
  155. MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
  156. Conditional Inference Trees and Forests for Feature Selection
  157. Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation
  158. BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer
  159. GPUAlert: A Zero-Instrumentation Process-Boundary Monitor for Diagnosing GPU Training-Job Failures
  160. Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks
  161. NeuroBridge: Bridging Multi-Task MRI Knowledge for Neurodegenerative Disease Diagnosis
  162. A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps
  163. Computer Vision for Wildlife Monitoring: Detecting Brown Howler Monkeys using YOLO
  164. Rethinking Generic Object Tracking Toward Human-Level Perceptual Intelligence
  165. The Wiola Architecture for Efficient Small Language Models
  166. How Should Transformers Encode Numeric Values in Electronic Health Records?
  167. Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search
  168. MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation
  169. AI-enabled gravitational-waves searches for binary neutron stars at optimal sensitivity
  170. Multi-modal Rail Crossing Safety Analysis
  171. Enerzyme: A Framework for Efficient Training of Reactive Neural Network Potentials for Enzyme Catalysis with Application to Methyltransferases
  172. Spatial-Temporal Expert Learning for Video-based Person Re-identification
  173. TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
  174. Ravines in quantum cost landscapes: opportunities for improved VQA predictions
  175. Black-Box Inference of LLM Architectural Properties with Restrictive API Access
  176. KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives
  177. From Approximation to Emergence: A Theory of Deep Learning
  178. A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation
  179. PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations
  180. Generative AI and Federated Learning for Intrusion Detection Systems: A Survey
  181. CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detection
  182. Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes
  183. CNN Models for Microphone Array Covariance Matrix Upsampling and Acoustic Imaging
  184. RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules
  185. AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting
  186. Adaptive Companionship for Group-Following Robots: Handling Dynamically Changing Group Formations
  187. IonSense-QKG: A Quantum-Readiness Metadata Framework for Lithium-Ion Battery Dataset Discovery
  188. Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
  189. Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition
  190. Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
  191. Itextsuperscript2RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
  192. Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
  193. Embedding Inference Attack
  194. Measuring the Gap Between Human and LLM Research Ideas
  195. Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
  196. AutoMem: Automated Learning of Memory as a Cognitive Skill
  197. Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
  198. The State-Prediction Separation Hypothesis
  199. Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
  200. Linkify: Learning from Interface-Augmented Assembly Graphs
  201. TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
  202. GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
  203. World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
  204. Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
  205. Optimal Resource Utilization for Autonomous Laboratory Orchestrators
  206. Neural Certificate Pricing for Combinatorial Optimization Problems
  207. High-dimensional Embedding Prior for Noisy K-space Domain MRIReconstruction
  208. Decision-Aware Training for Sample-Based Generative Models
  209. Structured 4D Latent Predictive Model for Robot Planning
  210. Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
  211. Disentangling Speaker and Language Effects in Cross-Lingual Speaker Verification for Iberian Languages
  212. AGC-Bench: Measuring Artificial General Creativity
  213. Hierarchical Self-Supervised Representation Learning Framework for Multivariate Time Series Grounded in ECG Analysis
  214. Relation-Centric Open-Vocabulary 3D Gaussian Segmentation
  215. SD-RouteFusion: Ego-Trajectory Prediction with SD-Map Route Conditioning
  216. Towards Metric-Agnostic Trajectory Forecasting
  217. Autonomous Scientific Discovery via Iterative Meta-Reflection
  218. GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
  219. LogbQuant: Quantizing Language Models in Logarithmic Space
  220. ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces
  221. Muon as a Residual Connection
  222. MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models
  223. Towards Developing a Multimodal Chat Assistant for University Stakeholders: RAG-based Approach
  224. FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
  225. CausalMix: Data Mixture as Causal Inference for Language Model Training
  226. Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention
  227. CPDDNet: Color-Polarization Denoising and Demosaicking Network
  228. Group-invariant Coresets for Data-efficient Active Learning
  229. When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
  230. Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
  231. Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
  232. Characterizing and Identifying Separable Graphical Models
  233. DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation
  234. EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology
  235. How Much Do RF Drone Benchmarks Overstate? A Controlled Study and Theory of Data Leakage in UAV Signal Identification
  236. Evidence-Supported Credit Risk Report Generation Using News-Centric Financial Knowledge Graphs
  237. Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
  238. PedNStream: Scalable Network Flow Simulation for Pedestrian Traffic Management
  239. Reading Order Inference for Complex Document Layouts
  240. SuperFlex: Deformable Superquadrics for Point Cloud Decomposition
  241. Generative Model Proposal based Particle Filtering for Data Assimilation
  242. Function-Counting Theory for Low-Dimensional Data Structures
  243. Understanding Large Language Models
  244. Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
  245. Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
  246. KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers
  247. Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
  248. Automatic Detection of Stress from Speech in the Trier Social Stress Test
  249. QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding
  250. Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications
  251. TRCGL-Net: A Long-Tailed Multi-Label Chest X-Ray Classification Framework with Generative Data Augmentation and Label Co-Occurrence Modeling
  252. QuaMoE-DRF: Proactive Beam and Rate Adaptation via Multimodal Dynamic Radio Map Forecasting in ISAC Networks
  253. Svarna: An Open Corpus Workbench for Modern Greek
  254. Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics
  255. Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies
  256. Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution
  257. Bridging Quantum Computing Paradigms toward Semiconductor Yield: A Controlled CV-versus-DV Comparison on Wafer-Map Defect Classification
  258. GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting
  259. LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
  260. Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
  261. Learning Cardiac Motion Priors for Implicit Neural Representations
  262. Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
  263. Diffeomorphic Optimization
  264. Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions
  265. Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions
  266. Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm
  267. GMO-E2DIT: Grounded Multi-Operation Editing for E-Commerce Images
  268. Condensing Large-Scale Datasets Directly with Minimal Information Loss
  269. Two AI Metrics Diverged: Will it Make All the Difference?
  270. Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
  271. MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
  272. MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages
  273. Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensing
  274. Beyond Pixel Overlap: A Framework for Decomposing Segmentation Evaluation Metrics
  275. Improving Sparse-View 3DGS Generalization via Flat Minima Optimization
  276. Hierarchical Variational Kalman Filtering
  277. The Binary Tree Mechanism is Optimal for Differentially Private Continual Counting
  278. How Ethos and Pathos Appeals Resonate in Reader Interpretations of Social Media Messages
  279. Self-Evolving Agents with Anytime-Valid Certificates
  280. Dynamic Bidirectional Pattern Memory: A Production-Scale Empirical Characterisation of Inference-Time Gating in Clinical NLP
  281. EFlow: Learning Evidence Flow for Long-Video Reasoning with Adaptive Reflection
  282. Constrained Bayesian Optimisation with Multiple Information Sources
  283. TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
  284. Meta-Transfer Learning for mmWave Beam Alignment
  285. MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
  286. Shapley in Context: Explaining Financial Language with Domain Expertise
  287. Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models
  288. Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
  289. The Course of News Events: A Comparison of Bottom-Up and Top-Down Approaches for Collecting Text-Based Data about Disasters
  290. MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors
  291. Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook
  292. Spectroscopy Analysis with Machine Learning Regression for the Quantification of Carbon and Nitrogen Contents in Inceptisol and Oxisol Soil Types: Comparing Different Preprocessing and Validation methods as well as Feature Importance
  293. Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences
  294. Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns
  295. Streaming LRAT Certificates into Lean Theorems
  296. Spotted: Location-informed Reidentification of Hyenas and Leopards in Camera Trap Surveys
  297. ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction
  298. Which Metric Reflects the Spelling Rate Accuracy in Event-Related Potential-Based Brain-Computer Interfaces?
  299. Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
  300. Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
  301. Forensic-Oriented Intrusion Detection Using Synthetic Network Traffic Data and Explainable Artificial Intelligence
  302. GKDT: General Keypoint Detection Transformer
  303. FrameONE: Hierarchical Motion Modeling for Universal Multi-View Echocardiographic Keyframe Detection
  304. Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines
  305. GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception
  306. Foundation Model-driven Key Anatomy Frame Selection for Blind-sweep Ultrasound Fetal Birth Weight Estimation
  307. Prototype Memory-Guided Training-Free Anomaly Classification and Localization in Prenatal Ultrasound
  308. Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences
  309. Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
  310. ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition
  311. LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
  312. AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization
  313. MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
  314. Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning
  315. Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach
  316. Self-conditioned Flow Map Language Models via Fixed-point Flows
  317. ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
  318. Creating Impactful Autonomous Driving Datasets: A Strategic Guide from Research Gap to Benchmark
  319. LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution
  320. Imprint: Online Memory Compression for Long-Horizon Egocentric QA
  321. Generative Refinement for Low-Budget Black-Box Optimization
  322. LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
  323. Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations
  324. DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding
  325. Multi-Label Node Classification with Label Influence Propagation
  326. Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
  327. YOMI-Bench: A Benchmark for Evaluating Kanji Reading and Phonological Understanding of LLMs for Japanese
  328. Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications
  329. Approximate full-conformal multi-task regression with reproducing kernels
  330. What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
  331. Uncertainty-aware tree height change regression
  332. Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization
  333. Identifying Latent Concepts and Structures for Generalized Category Discovery
  334. Diffusion-Based Multi-Class Normality for OOD Detection: An Application to CDP Authentication
  335. Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment
  336. "Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo
  337. Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs
  338. GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
  339. Optimal scaling of MCMC algorithms: the Hamiltonian approach
  340. How Environment and Urbanization Shape Bird Diversity in Sri Lanka
  341. Decision-focused Sparse Tangent Portfolio Optimization
  342. Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers
  343. EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
  344. Caption Bottleneck Models
  345. Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine
  346. BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure
  347. A Methodology for Investigating AI Patterns Prevalence in Software Repositories
  348. Group-Equivariant Poincar'e Convolutional Networks
  349. Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
  350. ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
  351. From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping
  352. NoPA: Non-Parametric Online 3D Scene Graph Generation
  353. AI Native Games: A Survey and Roadmap
  354. SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation
  355. AI, Trust, and Teaming: The Humans-as-Handlers Approach for Autonomous and Opaque AI Systems
  356. Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration
  357. Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning
  358. From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
  359. Prototype Language Models
  360. BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
  361. Closed-loop coupling of personalised and foundation models for real-time treatment guidance with MRI
  362. Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation
  363. Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations
  364. HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
  365. GenSP: Consistent Spherical Parameterization via Learning Shape Generative Models
  366. Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
  367. Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
  368. How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction
  369. Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
  370. Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
  371. MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
  372. A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction
  373. Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval
  374. VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
  375. Search-Based Spatiotemporal and Multi-Robot Motion Planning on Graphs of Space-Time Convex Sets
  376. Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins
  377. HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
  378. Speech Playground: An Interactive Tool for Speech Analysis and Comparison
  379. EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction
  380. DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble
  381. A Mechanistic View of Authority Hierarchy in LLM Sycophancy
  382. MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
  383. MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation
  384. Holographic Quantum Transformer: A Generalist Neuro-Symbolic Architecture for Solving Frustrated Systems via Generative Attention
  385. NeuroCogMap Reveals Cognitive Organization of Large Language Models
  386. MalariAI: A Label-Resilient Decoupled Framework for Annotation-Agnostic Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears
  387. Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval
  388. Radial Interaction Tomography: Recognizing Non-Transitive Evolutionary Games from One Range-Expansion Image
  389. SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
  390. LIST3R: Long-sequence Instance-aware 3D Reconstruction
  391. Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
  392. SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions
  393. Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
  394. When AI meets quantum information: A comprehensive review
  395. SoK: Attack and Defense Landscape of Mobile On-device AI Systems
  396. PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition
  397. TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data
  398. DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
  399. K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
  400. Watermarking for Proprietary Dataset Protection
  401. CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild
  402. From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
  403. Calibrated Multichannel Monocular Ranging From Standardized License Plates With Metrology-Exact Validation
  404. A Text-Steerable Instrument for Sketching Procedural Soundscapes via Language Models
  405. Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
  406. Generative Modeling of Quantum Distribution with Functional Flow Matching
  407. Learning When to Listen: Gated Affect Fusion for Human Motion Prediction
  408. An LLM-Based Framework for Intent-Driven Network Topology Design
  409. OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization
  410. Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings
  411. Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example