mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 11 May 2026

787 papers

  1. TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAGRetrieval-augmented generation → Privacy and security of RAG
  2. Making Open-Source Text LLM Watermarks Durable Against MergingLLM safety and security → Watermarking generated content and models
  3. When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMsMultimodal LLMs / vision-language models → Medical vision-language models
  4. Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and AccentsLLM reasoning → Audio-language model reasoning
  5. Temporal Preference Concepts and their Functions in a Large Language ModelMechanistic interpretability → Activation steering methods
  6. Fewer, Better Frames: A Compute-Normalized Proof of Concept for Coherence-First World-Model Rendering with Model-Guided FSR4 Frame GenerationWorld models → Video-generation world models and simulators
  7. EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-DistillationKnowledge distillation → Speech and audio distillation
  8. Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and AffectMechanistic interpretability → Activation steering methods
  9. Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval TimeRetrieval-augmented generation → RAG robustness and adaptive retrieval
  10. RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation AgentsLLM agents and tool use → Agentic recommender systems
  11. PROWL: Prioritized Regret-Driven Optimization for World Model LearningWorld models → World model security and GUI agents
  12. ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic ReasoningLLM reasoning → Reinforcement learning for reasoning
  13. HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts ModelsMixture-of-experts → Mixture of LoRA experts
  14. Trust or Abstain? A Self-Aware RAG ApproachRetrieval-augmented generation → RAG robustness and adaptive retrieval
  15. Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal ScoringMultimodal LLMs / vision-language models → Medical vision-language models
  16. Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic ReasoningLLM reasoning → Spatial and embodied reasoning
  17. ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series PredictionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  18. An Information-Theoretic Criterion for Efficient Data SynthesisSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  19. An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food RecommendationsRetrieval-augmented generation → Medical and biomedical RAG
  20. Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time AssuranceDeep reinforcement learning methods → Safe and constrained RL
  21. CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health ScreeningLLM agents and tool use → Medical and scientific domain agents
  22. ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer InferenceDiffusion models → Diffusion foundations and sampling
  23. Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New InsightsLLM reasoning → Hallucination detection and mitigation
  24. SOMA: Efficient Multi-turn LLM Serving via Small Language ModelEfficient LLM inference and serving → Prompt and context compression
  25. Couple to Control: Joint Initial Noise Design in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  26. Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code GenerationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  27. CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest RadiographyLLM reasoning → Clinical and biomedical applications +1
  28. LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?LLM reasoning → Multimodal reasoning +1
  29. Can Graphs Help Vision SSMs See Better?State-space sequence models (S4, Mamba) → Vision Mamba backbones
  30. Primal Generation, Dual Judgment: Self-Training from Test-Time ScalingLLM reasoning → Reasoning for agents, planning and code
  31. ReAD: Reinforcement-Guided Capability Distillation for Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  32. Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  33. Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational WavesLLM agents and tool use → Web, search, and research agents
  34. Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
  35. gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave AstronomyLLM agents and tool use → Web, search, and research agents
  36. Latent Chain-of-Thought Improves Structured-Data TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  37. Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI ValidationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  38. Unlocking LLM Creativity in Science through Analogical ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  39. HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language ModelMixture-of-experts → MoE large language models
  40. The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving StackLLM reasoning → Reasoning for agents, planning and code +1
  42. Comment and Control: Hijacking Agentic Workflows via Context-Grounded EvolutionLLM agents and tool use → Software engineering coding agents
  43. PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory RefinementLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. Training-Free Refusal of MCP Exploits via Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG +3
  46. ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy ReductionLLM agents and tool use → GUI and mobile agents
  47. Continuous Discovery of Vulnerabilities in LLM Serving Systems with FuzzingEfficient LLM inference and serving → Serving systems and request scheduling
  48. CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference AccelerationEfficient LLM inference and serving → Speculative decoding
  49. The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and FixesKnowledge distillation → On-policy and self-distillation for LLMs
  50. Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public DataLLM safety and security → Machine unlearning
  51. OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct AgentsLLM reasoning → Reasoning for agents, planning and code +1
  52. RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action RankingOffline RL and imitation learning from data → Offline RL algorithms
  53. Control Charts for Multi-agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  54. Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie TrainingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  55. USEMA: a Scalable Efficient Mamba Like Attention for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  56. Language Modeling with Hyperspherical FlowsDiffusion models → Discrete and text diffusion
  57. GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical AlgorithmsLLM agents and tool use → Web, search, and research agents +1
  58. SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric CollectionVision-language-action models → 3D and spatial-aware VLA
  59. Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. Newton's Lantern: A Reinforcement Learning Framework for Finetuning AC Power Flow Warm Start ModelsDeep reinforcement learning methods → RL for energy, networks and operations
  61. ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?LLM agents and tool use → Agent threats, guardrails and governance
  62. Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation ProtocolsLLM agents and tool use → Agent threats, guardrails and governance
  63. On Problems of Implicit Context Compression for Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  64. ForceFlow: Learning to Feel and Act via Contact-Driven Flow MatchingDiffusion models → Diffusion and flow policies for robotics +1
  65. Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClawLLM agents and tool use → Agent threats, guardrails and governance +1
  66. The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning BottleneckLLM reasoning → Reasoning for agents, planning and code +1
  67. Sequential Behavioral Watermarking for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  68. HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action ModelsWorld models → Embodied and robot world models
  69. ELF: Embedded Language FlowsDiffusion models → Discrete and text diffusion
  70. Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage ShapingLLM reasoning → Reinforcement learning for reasoning
  71. Personal Visual Context Learning in Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  72. DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side DevicesMixture-of-experts → Expert routing strategies
  73. Evaluating the False Trust Engendered by LLM ExplanationsLLM reasoning → Reasoning benchmarks and evaluation
  74. PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  75. Dynamic Skill Lifecycle Management for Agentic Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution
  76. Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character RecognitionDiffusion models → Image generation, text-to-image and editing
  77. Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution TracesLLM agents and tool use → Software engineering coding agents
  78. WildClawBench: A Benchmark for Real-World, Long-Horizon Agent EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  79. Equivariant Reinforcement Learning for Clifford Quantum Circuit SynthesisDeep reinforcement learning methods → Quantum reinforcement learning
  80. Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with k-step Policy GradientsDeep reinforcement learning methods → RL theory and sample complexity
  81. MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent SystemsEnd-to-end autonomous driving → Cooperative and V2X driving
  82. CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization
  83. Beyond Red-Teaming: Formal Guarantees of LLM Guardrail ClassifiersLLM safety and security → Safety alignment, refusal and guardrails
  84. RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable RewardsLLM agents and tool use → Web, search, and research agents
  85. Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive RankingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  86. Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and WhyLLM reasoning → Prompting and chain-of-thought reasoning +1
  87. Count Anything at Any GranularityMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  88. AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and AgentsLLM agents and tool use → Medical and scientific domain agents
  89. Compute Where it Counts: Self Optimizing Language ModelsEfficient LLM inference and serving → Early exit and edge inference
  90. DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  91. RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM SystemsRetrieval-augmented generation → RAG pipeline design and evaluation +1
  92. Masked Generative Transformer Is What You Need for Image EditingDiffusion models → Image generation, text-to-image and editing
  93. Is Your Driving World Model an All-Around Player?World models → World models for autonomous driving +1
  94. Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  95. Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQAMultimodal LLMs / vision-language models → Medical vision-language models
  96. Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?LLM reasoning → Knowledge- and tool-augmented reasoning +1
  97. Training-Free Cultural Alignment of Large Language Models via Persona DisagreementLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  98. Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient TrajectoriesWorld models → Medical and surgical world models
  99. From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-WorldLLM agents and tool use → Agent threats, guardrails and governance
  100. Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search AgentsLLM reasoning → Multimodal reasoning
All 787
  1. SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular EditingLLM reasoning → Clinical and biomedical applications
  2. Predicting 3D structure by latent posterior samplingDiffusion models → 3D, point cloud and scene generation
  3. The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context ReasoningLLM reasoning → Reasoning benchmarks and evaluation +2
  4. UniSteer: Unified Noise Steering for Efficient Human-Guided VLA AdaptationVision-language-action models → Efficient VLA inference and adaptation
  5. ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining +1
  6. Policy Gradient Methods for Non-Markovian Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  7. NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research AutomationLLM agents and tool use → Web, search, and research agents
  8. PhyGround: Benchmarking Physical Reasoning in Generative World ModelsWorld models → Latent predictive world models
  9. Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-JudgeLLM reasoning → Test-time compute and efficient thinking
  10. The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption StudiesLLM reasoning → Prompting and chain-of-thought reasoning
  11. Can You Keep a Secret? Involuntary Information Leakage in Language Model WritingLLM reasoning → Prompting and chain-of-thought reasoning
  12. Elucidating Representation Degradation Problem in Diffusion Model TrainingDiffusion models → Diffusion foundations and sampling
  13. ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool SandboxLLM agents and tool use → Tool learning and function calling
  14. MASS-DPO: Multi-negative Active Sample Selection for Direct Policy OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  15. Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVRLLM reasoning → Prompting and chain-of-thought reasoning +1
  16. LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance +1
  17. Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  18. Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy MaximizationLLM safety and security → Vision-language and text-to-image safety
  19. MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case StudyLLM agents and tool use → Agent threats, guardrails and governance
  20. GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMsLLM reasoning → Multimodal reasoning
  21. Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching ModelsDiffusion models → Diffusion and flow policies for robotics
  22. TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  23. The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation AgentsLLM reasoning → Reasoning for agents, planning and code +1
  24. C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  25. Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  26. XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior PoliciesDeep reinforcement learning methods → RL theory and sample complexity
  27. Conformity Generates Collective Misalignment in AI Agents SocietiesLLM agents and tool use → Social simulation and multi-agent debate
  28. Heteroscedastic Diffusion for Multi-Agent Trajectory ModelingDiffusion models → Diffusion and flow policies for robotics
  29. What should post-training optimize? A test-time scaling law perspectiveLLM reasoning → Reinforcement learning for reasoning +1
  30. The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative InteractionsLLM reasoning → Reasoning for agents, planning and code +1
  31. Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting CodesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  32. Behavioral Guarantees for Proxy-Based UnlearningLLM safety and security → Machine unlearning
  33. Step Rejection Fine-Tuning: A Practical Distillation RecipeLLM agents and tool use → Reinforcement learning for LLM agents
  34. Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator FrameworkDeep reinforcement learning methods → RL theory and sample complexity
  35. Surviving Partial Rank Failures in Wide Expert-Parallel MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  36. Prompt-Activation Duality: Improving Activation Steering via Attention-Level InterventionsMechanistic interpretability → Activation steering methods
  37. Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  38. Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN AutomationDeep reinforcement learning methods → RL for energy, networks and operations
  39. diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic TrajectoriesDiffusion models → Robustness, privacy and adversarial aspects
  40. A Single-Layer Model Can Do Language ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language +1
  41. Composing diffusion priors with explicit physical context via generative Gibbs samplingDiffusion models → Diffusion foundations and sampling
  42. LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  43. Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMsLLM safety and security → Safety alignment, refusal and guardrails
  44. Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI ReconstructionDiffusion models → Medical imaging and segmentation
  45. Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate HallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  46. PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM PipelinesLLM agents and tool use → Agent threats, guardrails and governance
  47. Re-Triggering Safeguards within LLMs for Jailbreak DetectionLLM safety and security → Jailbreaking
  48. CrackMeBench: Binary Reverse Engineering for AgentsLLM agents and tool use → Software engineering coding agents
  49. Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial IntelligenceLLM reasoning → Spatial and embodied reasoning +1
  50. Controllability in preference-conditioned multi-objective reinforcement learningDeep reinforcement learning methods → RL for games and combinatorial optimization
  51. An agentic framework for gravitational-wave counterpart association in the multi-messenger eraLLM agents and tool use → Web, search, and research agents
  52. Guaranteed Jailbreaking Defense via Disrupt-and-Rectify SmoothingLLM safety and security → Jailbreaking
  53. Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attentionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  54. SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  55. DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +3
  56. EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference ServingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  57. Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  58. A Reflective Storytelling Agent for Older Adults: Integrating Argumentation Schemes and Argument Mining in LLM-Based Personalised NarrativesLLM agents and tool use → Medical and scientific domain agents
  59. Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge DiscoveryLLM agents and tool use → Web, search, and research agents
  60. Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical PhysicsLLM agents and tool use → Social simulation and multi-agent debate
  61. Infinite Mask Diffusion for Few-Step DistillationDiffusion models → Discrete and text diffusion +1
  62. CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge GraphsMixture-of-experts → Medical and biomedical MoE
  63. DeepRefine: Agentic Knowledge Refinement via Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  64. VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  65. Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  66. ASIA: an Autonomous System Identification AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  68. TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel AgentsLLM agents and tool use → Financial trading and forecasting agents
  69. Filtering Memorization from Parameter-Space in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  70. WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State PredictorsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  71. CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous DrivingWorld models → World models for autonomous driving +2
  72. Equilibrium Residuals Expose Three Regimes of Matrix-Game Strategic Reasoning in Language ModelsLLM reasoning → Reasoning for agents, planning and code
  73. VISOR: A Vision-Language Model-based Test Oracle for Testing RobotsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  74. Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API AccessKnowledge distillation → On-policy and self-distillation for LLMs
  75. SF-Flow: Sound field magnitude estimation via flow matching guided by sparse measurementsDiffusion models → Audio, speech and music
  76. AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded RefutationLLM agents and tool use → Software engineering coding agents
  77. Temporal Sampling Frequency Matters: A Capacity-Aware Study of End-to-End Driving Trajectory PredictionEnd-to-end autonomous driving → Generative simulation for driving
  78. GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety LogicEnd-to-end autonomous driving → Large language models for driving
  79. Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured InputsDiffusion models → Diffusion foundations and sampling
  80. Agentic Performance at the Edge: Insights from BenchmarkingLLM agents and tool use → General LLM agent frameworks and benchmarks
  81. Agent-X: Full Pipeline Acceleration of On-device AI AgentsLLM agents and tool use → Software engineering coding agents
  82. PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context DistillationDeep reinforcement learning methods → RL for games and combinatorial optimization
  83. SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  84. Toward Multi-Database Query Reasoning for Text2CypherLLM reasoning → Knowledge- and tool-augmented reasoning
  85. AgentGR: Semantic-aware Agentic Group Decision-Making Simulator for Group RecommendationLLM agents and tool use → Agentic recommender systems
  86. Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent ValuesLLM agents and tool use → General LLM agent frameworks and benchmarks
  87. CellDX AI Autopilot: Agent-Guided Training and Deployment of Pathology ClassifiersLLM agents and tool use → Medical and scientific domain agents
  88. How Mobile World Model Guides GUI Agents?World models → World model security and GUI agents +2
  89. TMAS: Scaling Test-Time Compute via Multi-Agent SynergyLLM reasoning → Reasoning for agents, planning and code +1
  90. EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied AgentsLLM agents and tool use → Agent skill learning and evolution +1
  91. Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss IntegrationMixture-of-experts → MoE for time series and graphs
  92. SCALAR: A Neurosymbolic Framework for Automated Conjecture and Reasoning in Quantum Circuit AnalysisLLM reasoning → Reinforcement learning for reasoning
  93. Verifiable Process Rewards for Agentic ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  94. Active Tabular Augmentation via Policy-Guided Diffusion InpaintingDiffusion models → Flow matching, time series and science
  95. Follow the Mean: Reference-Guided Flow MatchingDiffusion models → Flow matching, time series and science
  96. Robust Probabilistic Shielding for Safe Offline Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
  97. AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction TasksLLM agents and tool use → Medical and scientific domain agents
  98. MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided RereadingLLM agents and tool use → Agent memory systems
  99. Towards Autonomous Railway Operations: A Semi-Hierarchical Deep Reinforcement Learning Approach to the Vehicle Rescheduling ProblemDeep reinforcement learning methods → RL for autonomous driving and traffic
  100. Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  101. Teaching LLMs to See Graphs: Unifying Text and Structural ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  102. When Does Non-Uniform Replay Matter in Reinforcement Learning?Deep reinforcement learning methods → Deep RL algorithms and representations
  103. FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated QueriesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  104. Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI ExecutionLLM agents and tool use → Agent threats, guardrails and governance
  105. Relative Score Policy Optimization for Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  106. LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative RecommendationLLM reasoning → LLM reasoning for recommendation
  107. Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  108. Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative ExplorationLLM reasoning → Test-time compute and efficient thinking
  109. STEPS: Selective On-Policy Self-Distillation for ReasoningKnowledge distillation → On-policy and self-distillation for LLMs
  110. ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein DesignLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
  111. SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning EvaluationLLM reasoning → Multimodal reasoning
  112. What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion TransformersDiffusion models → Robustness, privacy and adversarial aspects +1
  113. MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving +1
  114. When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven ApplicationsLLM safety and security → Prompt injection and agent security
  115. V-ABS: Action-Observer Driven Beam Search for Dynamic Visual ReasoningLLM reasoning → Multimodal reasoning +1
  116. Balancing Efficiency and Fairness in Traffic Light Control through Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  117. Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  118. Unsupervised Process Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  119. NyayaAI: An AI-Powered Legal Assistant Using Multi-Agent Architecture and Retrieval-Augmented GenerationRetrieval-augmented generation → Legal and financial RAG +1
  120. Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge EditingLLM reasoning → Reasoning for agents, planning and code
  121. FormalRewardBench: A Benchmark for Formal Theorem Proving Reward ModelsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  122. GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM InferenceEfficient LLM inference and serving → Speculative decoding
  123. MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute GraphLLM reasoning → Multimodal reasoning +1
  124. Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied NavigationLLM reasoning → Spatial and embodied reasoning +1
  125. Generating Symmetric Materials using Latent Flow MatchingDiffusion models → Flow matching, time series and science
  126. SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented ExecutionRetrieval-augmented generation → Agentic RAG, agents and memory +1
  127. CFSPMNet: Cross-subject Fourier-guided Spatial-Patch Mamba Network for EEG Motor Imagery Decoding in Stroke PatientsState-space sequence models (S4, Mamba) → Physiological signal modeling
  128. ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +2
  129. Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAsVision-language-action models → Reinforcement learning and post-training
  130. PoDAR: Power-Disentangled Audio Representation for Generative ModelingDiffusion models → Audio, speech and music
  131. FERA: Uncertainty-Aware Federated Reasoning for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  132. Active Testing of Large Language Models via Approximate Neyman AllocationLLM reasoning → Test-time compute and efficient thinking
  133. Agentic Fuzzing: Opportunities and ChallengesLLM agents and tool use → Software engineering coding agents
  134. Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy OptimizationSynthetic data and self-improvement for LLMs → Safety of self-evolving systems +1
  135. MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge GraphsLLM agents and tool use → General LLM agent frameworks and benchmarks
  136. EFGCL: Learning Dynamic Motion through Spotting-Inspired External Force Guided Curriculum LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  137. Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce TrustLLM agents and tool use → Financial trading and forecasting agents
  138. STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal ReasoningLLM reasoning → Spatial and embodied reasoning +1
  139. EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMsEfficient LLM inference and serving → Visual token pruning in multimodal models
  140. Adaptive Action Chunking via Multi-Chunk Q Value EstimationOffline RL and imitation learning from data → Robot manipulation imitation learning
  141. Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization FrameworkLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  142. Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure VariablesLLM agents and tool use → Software engineering coding agents
  143. TimeClaw: A Time-Series AI Agent with Exploratory Execution LearningLLM agents and tool use → Financial trading and forecasting agents
  144. Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RANLLM agents and tool use → Agentic AI for wireless networks
  145. Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  146. PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker ReasoningLLM reasoning → Clinical and biomedical applications
  147. TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory GenerationDiffusion models → Diffusion and flow policies for robotics
  148. Combining Mechanical and Agentic Specification Inference for MoveLLM agents and tool use → Educational agents and math problem solving
  149. Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language ModelsLLM reasoning → Hallucination detection and mitigation +1
  150. Muninn: Your Trajectory Diffusion Model But FasterDiffusion models → Diffusion and flow policies for robotics
  151. Continual Harness: Online Adaptation for Self-Improving Foundation AgentsLLM agents and tool use → Software engineering coding agents +1
  152. Omni-Persona: Systematic Benchmarking and Improving Omnimodal PersonalizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  153. Attention Drift: What Autoregressive Speculative Decoding Models LearnEfficient LLM inference and serving → Speculative decoding
  154. StereoPolicy: Improving Robotic Manipulation Policies via Stereo PerceptionOffline RL and imitation learning from data → Robot manipulation imitation learning
  155. ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  156. HiDrive: A Closed-Loop Benchmark for High-Level Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  157. HapticLDM: A Diffusion Model for Text-to-Vibrotactile GenerationDiffusion models → Video generation
  158. Tensor Product Representation Probes Reveal Shared Structure Across Linear DirectionsMechanistic interpretability → Sparse autoencoder training and evaluation
  159. G-Zero: Self-Play for Open-Ended Generation from Zero DataLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +1
  160. LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  161. HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph EvolutionLLM agents and tool use → Agent memory systems
  162. TRACER: Verifiable Generative Provenance for Multimodal Tool-Using AgentsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  163. PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  164. TeleResilienceBench: Quantifying Resilience for LLM Reasoning in TelecommunicationsLLM reasoning → Test-time compute and efficient thinking
  165. Evolving Knowledge Distillation for Lightweight Neural Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
  166. expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum samplingLLM reasoning → Reinforcement learning for reasoning
  167. Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  168. RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure GenerationLLM reasoning → Reasoning for agents, planning and code +1
  169. Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-ThoughtLLM reasoning → Audio-language model reasoning
  170. Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature AlignmentMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  171. The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard BenchmarkLLM reasoning → Multimodal reasoning +1
  172. Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
  173. Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and ActionsLLM reasoning → Reasoning benchmarks and evaluation
  174. Skill Description Deception Attack against Task Routing in Internet of AgentsLLM agents and tool use → Agent threats, guardrails and governance
  175. The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling LawsMechanistic interpretability → Sparse autoencoder training and evaluation
  176. Network-Efficient World Model Token StreamingWorld models → Video-generation world models and simulators
  177. The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate SpaceLLM reasoning → Multimodal reasoning +1
  178. Dissecting Jet-Tagger Through Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  179. M2A: Synergizing Mathematical and Agentic Reasoning in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  180. EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video UnderstandingLLM reasoning → Spatial and embodied reasoning
  181. Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional DistributionsDiffusion models → Flow matching, time series and science
  182. Nautilus Compass: Black-box Persona Drift Detection for Production LLM AgentsLLM agents and tool use → Agent memory systems
  183. When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language ReasoningLLM reasoning → Spatial and embodied reasoning
  184. Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object TrackingLLM reasoning → Multimodal reasoning
  185. Concordia: Self-Improving Synthetic Tables for Federated LLMsSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  186. Exploration-Driven Optimization for Test-Time Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  187. Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute ExtractionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  188. Neuromorphic Satellite Intelligence: A Formal Framework for Event-Driven Architectures, Spike-Based Algorithms, and Quantitative Energy-Accuracy Trade-offs
  189. QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction
  190. SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series
  191. Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices
  192. Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
  193. Break Through the Compression Bottleneck: From Theory to Practice
  194. A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges
  195. LLM-Based Code Documentation Generation and Multi-Judge Evaluation
  196. AI in the Enterprise: How People Use M365 Copilot Chat
  197. Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling
  198. QUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems
  199. From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
  200. Game-Theoretic Modeling of Heterogeneous Investor Interactions for Stock Price Forecasting
  201. Strategic Coercion Within Alliances: The Greenland Sovereignty Game as an AI Stress Test
  202. The Cognitive Kardashev Scale: Quantifying the Material Envelope of Civilisational Computation
  203. Network-Based Interventions for HIV Prevention via Cascade-Aware Suppression of Transmission
  204. Block-Based Double Decoders
  205. Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning
  206. A Nonlinear Complexity Index for Wearable PPG Cardiovascular Stability: Multiscale Validation, Systematic Evaluation Correction, and Bayesian Parameter Optimization
  207. Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
  208. Theory-optimal Quantization Based on Flatness
  209. Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
  210. Simply Stabilizing the Loop via Fully Looped Transformer
  211. UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing
  212. Robust Basis Spline Decoupling for the Compression of Transformer Models
  213. Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
  214. SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation
  215. VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos
  216. Inducing Spatial Locality in Vision Transformers through the Training Protocol
  217. Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity
  218. ChronoSC: Task-Oriented Semantic Communication via Temporal-to-Color Encoding
  219. Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition
  220. Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
  221. A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification
  222. StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
  223. Mixing Times of Glauber Dynamics on Masked Language Models
  224. Consciousness as Uncommon Self-Knowledge: A Synergistic Information Framework
  225. PREPING: Zero-Task Agent Memory Construction via Self-Practice
  226. Brain Tumor Classification in MRI Images: A Computationally Efficient Convolutional Neural Network
  227. M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement
  228. ChannelKAN: Multi-Scale Dual-Domain Channel Prediction via Hybrid CNN-KAN Architecture
  229. Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario
  230. Much of Geospatial Web Search Is Beyond Traditional GIS
  231. VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference
  232. MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
  233. Epistemic Uncertainty for Test-Time Discovery
  234. Neural Statistical Functions
  235. Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval
  236. varepsilon-Good Action Identification in Fixed-Budget Monte Carlo Tree Search
  237. Error whitening: Why Gauss-Newton outperforms Newton
  238. Natural Language based Specification and Verification
  239. Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort
  240. Constraint-Data-Value-Maximization: Utilizing Data Attribution for Effective Data Pruning in Low-Data Environments
  241. Predicting Psychological Well-Being from Spontaneous Speech using LLMs
  242. A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
  243. Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets
  244. Beyond Similarity: Temporal Operator Attention for Time Series Analysis
  245. Rethinking external validation for the target population: Capturing patient-level similarity with a generative model
  246. Generative AI for Visualizing Highway Construction Hazards Through Synthetic Images and Temporal Sequences
  247. Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
  248. Real-Scale Island Area and Coastline Estimation using Only its Place Name or Coordinates
  249. PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
  250. DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction
  251. Curriculum Learning-Guided Progressive Distillation in Large Language Models
  252. A Proof-of-Concept Simulation-Driven Digital Twin Framework for Decision-Aware Diabetes Modeling
  253. Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
  254. RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting in Rubric-based Scoring for German
  255. When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
  256. A Dual Representation of Influence Functions for Linearizable Models
  257. DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift
  258. Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
  259. A Comparative Study of Model Selection Criteria for Symbolic Regression
  260. LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection
  261. A Stable Distance Persistence Homology for Dynamic Bayesian Network Clustering
  262. ABRA: Agent Benchmark for Radiology Applications
  263. Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?
  264. ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models
  265. Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows
  266. ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
  267. Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
  268. Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks
  269. Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation
  270. Instructions Shape Production of Language, not Processing
  271. The Scaling Law of Evaluation Failure: Why Simple Averaging Collapses Under Data Sparsity and Item Difficulty Gaps, and How Item Response Theory Recovers Ground Truth Across Domains
  272. Multi-Agent System Identification with Nonlinear Sheaf Diffusion
  273. How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing
  274. Operator-Guided Model Reduction for Generative Sampling in Lattice Field Theory
  275. Variational Linear Attention: Stable Associative Memory for Long-Context Transformers
  276. How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
  277. Exploring Token-Space Manipulation in Latent Audio Tokenizers
  278. Adaptive Policy Learning Under Unknown Network Interference
  279. Deep Learning for Protein Complex Prediction and Design
  280. Adversarial SQL Injection Generation with LLM-Based Architectures
  281. Muon is Not That Special: Random or Inverted Spectra Work Just as Well
  282. Interpretable Machine Learning for Spatial Science: A Lie-Algebraic Kernel for Rotationally Anisotropic Gaussian Processes
  283. Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
  284. From raw data to neutrino candidates: a neural-network pipeline for Baikal-GVD
  285. Optimistic Dual Averaging Unifies Modern Optimizers
  286. Variational predictive resampling
  287. The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
  288. Unpacking the Eye of the Beholder: Social Location, Identity, and the Moving Target of Political Perspectives
  289. COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication
  290. Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions
  291. Interpretability Can Be Actionable
  292. CORE: Cyclic Orthotope Relation Embedding for Knowledge Graph Completion
  293. The Price of Proportional Representation in Temporal Voting
  294. Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction
  295. Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary
  296. Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
  297. ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
  298. Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
  299. EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
  300. Steerable Neural ODEs on Homogeneous Spaces
  301. HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series
  302. Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
  303. FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
  304. Sensor Design for Accuracy-Bounded Estimation via Maximum-Entropy Likelihood Synthesis
  305. A Cascaded Generative Approach for e-Commerce Recommendations
  306. LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR
  307. ShardTensor: Domain Parallelism for Scientific Machine Learning
  308. Deploying Self-Supervised Learning for Real Seismic Data Denoising
  309. Enabling Performant and Flexible Model-Internal Observability for LLM Inference
  310. ASD-Bench: A Four-Axis Comprehensive Benchmark of AI Models for Autism Spectrum Disorder
  311. HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
  312. SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels
  313. Uniform Scaling Limits in AdamW-Trained Transformers
  314. The first global agricultural field boundary map at 10m resolution
  315. Read, Extract, Classify: A Tool for Smarter Requirements Engineering
  316. Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies
  317. MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining
  318. Variational Inference for L'evy Process-Driven SDEs via Neural Tilting
  319. Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
  320. Pixal3D: Pixel-Aligned 3D Generation from Images
  321. Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schr"odinger Bridges
  322. Engineering Robustness into Personal Agents with the AI Workflow Store
  323. DataMaster: Data-Centric Autonomous AI Research
  324. V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction
  325. Counterfactual Stress Testing for Image Classification Models
  326. Shields to Guarantee Probabilistic Safety in MDPs
  327. LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
  328. Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentation
  329. Neural Weight Norm = Kolmogorov Complexity
  330. Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs
  331. CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
  332. Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography
  333. Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
  334. BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data
  335. BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
  336. Grounded Satirical Generation with RAG
  337. Generalizing the Turing Test to Interactive Agents
  338. Conditional anomaly detection methods for patient-management alert systems
  339. BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation
  340. Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
  341. MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection
  342. NoRIN: Backbone-Adaptive Reversible Normalization for Time-Series Forecasting
  343. Benchmarking Sensor-Fault Robustness in Forecasting
  344. MaD Physics: Evaluating information seeking under constraints in physical environments
  345. On periodic distributed representations using Fourier embeddings
  346. CLEF: EEG Foundation Model for Learning Clinical Semantics
  347. Probing Cross-modal Information Hubs in Audio-Visual LLMs
  348. Switching-Geometry Analysis of Deflated Q-Value Iteration
  349. Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities
  350. Mistake-Bounded Language Generation
  351. Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights
  352. LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges
  353. New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach
  354. Muown: Row-Norm Control for Muon Optimization
  355. Interpretable Machine Learning for Football Performance Analysis: Evidence of Limited Transferability from Elite Leagues to University Competition
  356. Factual recall in linear associative memories: sharp asymptotics and mechanistic insights
  357. ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
  358. Implicit Neural Optimal Transport via Fixed-Point Optimization
  359. Reward on Path: Learning Intermediate Supervision Signals for Knowledge Graph Question Answering
  360. Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction
  361. TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding
  362. Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
  363. Locking Pretrained Weights via Deep Low-Rank Residual Distillation
  364. On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities
  365. When Are Trade-Off Functions Testable from Finite Samples?
  366. Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition
  367. DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures
  368. MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation
  369. RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology
  370. Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs
  371. AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery
  372. iPay: Integrated Payment Action Recognition via Multimodal Networks and Adaptive Spatial Prior Learning
  373. Qwen-Image-2.0 Technical Report
  374. Kernel-Gradient Drifting Models
  375. AgentMV: A State-Guided Multi-Agent Framework for Budget-Aware Music Video Generation
  376. On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints
  377. An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum
  378. UAV-Assisted Scan-to-Simulation for Landslides Using Physics-Informed Gaussian Splatting
  379. Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish
  380. Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data
  381. RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings
  382. TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
  383. DANCE: Detect and Classify Events in EEG
  384. The finite expression method for turbulent dynamics with high-order moment recovery
  385. GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing
  386. Is Data Shapley Not Better than Random in Data Selection? Ask NASH
  387. Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
  388. Neuromorphic Monocular Depth Estimation with Uncertainty Modeling
  389. Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization
  390. A Spectral Framework for Closed-Form Relative Density Estimation
  391. Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
  392. When Can Digital Personas Reliably Approximate Human Survey Findings?
  393. Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory
  394. BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization
  395. Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
  396. A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
  397. A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks
  398. GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks
  399. Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
  400. Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks
  401. Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies
  402. Hyper-FSAD: Training-Free and Language-Free Few-Shot Anomaly Detection via Sparse Hyper Matching
  403. Interpretable Coreference Resolution Evaluation Using Explicit Semantics
  404. Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control
  405. Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
  406. MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
  407. Responsible Benchmarking of Fairness for Automatic Speech Recognition
  408. Exact Fixed-Point Constraints in Neural-ODEs with Provable Universality
  409. Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science
  410. Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
  411. Where do aspectual variants of light verb constructions belong?
  412. Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems
  413. Segment Anything with Robust Uncertainty-Accuracy Correlation
  414. The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime
  415. Budget-Efficient Automatic Algorithm Design via Code Graph
  416. LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation
  417. A Resilient Solution for Sewer Overflow Monitoring across Cloud and Edge
  418. Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks
  419. CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations
  420. FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
  421. VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios
  422. Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims
  423. LLM Jaggedness Unlocks Scientific Creativity
  424. Online Sharp-Calibrated Bayesian Optimization
  425. Set-Based Groupwise Registration for Variable-Length, Variable-Contrast Cardiac MRI
  426. Deep Arguing
  427. VeloGauss: Learning Physically Consistent Gaussian Velocity Fields from Videos
  428. Affine Tracing: A New Paradigm for Probabilistic Linear Solvers
  429. ThreatCore: A Benchmark for Explicit and Implicit Threat Detection
  430. ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression
  431. Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems
  432. It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction
  433. Multi-domain Multi-modal Document Classification Benchmark with a Multi-level Taxonomy
  434. PhysEDA: Physics-Aware Learning Framework for Efficient EDA With Manhattan Distance Decay
  435. Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
  436. TIE: Time Interval Encoding for Video Generation over Events
  437. Bridging Sequence and Graph Structure for Epigenetic Age Prediction
  438. Mela: Test-Time Memory Consolidation based on Transformation Hypothesis
  439. HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds
  440. ConfoundingSHAP: Quantifying confounding strength in causal inference
  441. PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
  442. GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
  443. Improving Human Image Animation via Semantic Representation Alignment
  444. DuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis
  445. Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
  446. SoK: A Systematic Bidirectional Literature Review of AI & DLT Convergence
  447. Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining
  448. SLASH the Sink: Sharpening Structural Attention Inside LLMs
  449. SkillEvolver: Skill Learning as a Meta-Skill
  450. Simultaneous Long-tailed Recognition and Multi-modal Fusion for Highly Imbalanced Multi-modal Data
  451. M2E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection
  452. Multi-layer attentive probing improves transfer of audio representations for bioacoustics
  453. A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems
  454. OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
  455. Priority-Driven Control and Communication in Decentralized Multi-Agent Systems via Reinforcement Learning
  456. Regret Minimization in Bilateral Trade With Perturbed Markets
  457. Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes
  458. Cavity-Enhanced Collective Quantum Processing with Polarization-Encoded Qubits
  459. Adaptive Context Matters: Towards Provable Multi-Modality Guidance for Super-Resolution
  460. Can Muon Fine-tune Adam-Pretrained Models?
  461. Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition
  462. Automated Detection of Abnormalities in Zebrafish Development
  463. Coherency through formalisations of Structured Natural Language, A case study on FRETish
  464. QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
  465. AxiomOcean: Forecasting the Three-Dimensional Structure of the Upper Ocean
  466. Don't Fix the Basis -- Learn It: Spectral Representation with Adaptive Basis Learning for PDEs
  467. Automated high-frequency quantification of fish communities and biomass using computer vision
  468. Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation
  469. Statistical Model Checking of the Keynes+Schumpeter Model: A Transient Sensitivity Analysis of a Macroeconomic ABM
  470. Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
  471. StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
  472. Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure
  473. DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
  474. Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation
  475. Physical probes expose and alleviate chemical-environment collapse in molecular representations
  476. Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI
  477. Can Language Models Analyze Data? Evaluating Large Language Models for Question Answering over Datasets
  478. Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
  479. Remember to Forget: Gated Adaptive Positional Encoding
  480. Progressive Photorealistic Simplification
  481. Multi-Fidelity Quantile Regression
  482. Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
  483. Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable
  484. Every finite group admits a just finite presentation
  485. LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
  486. Causal Explanations from the Geometric Properties of ReLU Neural Networks
  487. Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
  488. Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection
  489. The Polynomial Counting Capabilities of Message Passing Neural Networks
  490. Phoenix-VL 1.5 Medium Technical Report
  491. Multifidelity Gaussian process regression for solving nonlinear partial differential equations
  492. Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
  493. Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
  494. Halo Separation-guided Underwater Multi-scale Image Restoration
  495. Autonomous FAIR Digital Objects: From Passive Assertions to Active Knowledge
  496. EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents
  497. DeepL'evy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series
  498. DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
  499. RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
  500. Foundations of Reliable Inference: Reliability-Efficiency Co-Design
  501. Portable Active Learning for Object Detection
  502. BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization
  503. EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
  504. PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
  505. An Annotation Scheme and Classifier for Personal Facts in Dialogue
  506. CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
  507. PowerStep: Memory-Efficient Adaptive Optimization via ℓp-Norm Steepest Descent
  508. The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection
  509. ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
  510. LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
  511. Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering
  512. Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
  513. Signature Approach for Contextual Bandits with Nonlinear and Path-dependent Rewards
  514. Positive Alignment: Artificial Intelligence for Human Flourishing
  515. PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
  516. Nearly-Optimal Algorithm for Adversarial Kernelized Bandits
  517. Set Prediction for Next-Day Active Fire Forecasting
  518. Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
  519. DECO-MWE: building a linguistic resource of Korean multiword expressions for feature-based sentiment analysis
  520. LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
  521. Generative AI Fuels Solo Entrepreneurship, but Teams Still Lead at the Top
  522. Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
  523. Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift
  524. BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
  525. Scalable Gaussian process inference via neural feature maps
  526. Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs
  527. DeepLog: A Software Framework for Modular Neurosymbolic AI
  528. Predictive Radiomics for Evaluation of Cancer Immune SignaturE in Glioblastoma: the PRECISE-GBM study
  529. Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
  530. PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction
  531. DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
  532. Increasing the Efficiency of DETR for Maritime High-Resolution Images
  533. IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs
  534. E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability
  535. A Cold Diffusion Approach for Percussive Dereverberation
  536. Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation
  537. SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems
  538. When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection
  539. Building Korean linguistic resource for NLU data generation of banking app CS dialog system
  540. MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
  541. AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting
  542. The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently
  543. Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
  544. FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
  545. VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection
  546. Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery
  547. Stellar Age Compression Reshapes Interpretations of the Milky Way Thick-Disk Formation History
  548. Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses
  549. The Impact of Editorial Intervention on Detecting Native Language Traces
  550. To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification
  551. Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation
  552. Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
  553. Unveiling High-Probability Generalization in Decentralized SGD
  554. 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects
  555. Task-Aware Calibration: Provably Optimal Decoding in LLMs
  556. HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions
  557. How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue
  558. Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
  559. DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer
  560. LegalCiteBench: Evaluating Citation Reliability in Legal Language Models
  561. DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imagings
  562. Developing a foundation model for high-resolution remote sensing data of the Netherlands
  563. Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
  564. A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection
  565. One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
  566. Joint sparse coding and temporal dynamics support context reconfiguration
  567. BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry
  568. When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews
  569. Automated Approach for Solving Infinite-state Polynomial Reachability Games
  570. ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
  571. Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation
  572. Hyperparameter Transfer for Dense Associative Memories
  573. Coarsening Linear Non-Gaussian Causal Models with Cycles
  574. Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images
  575. OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
  576. jNO: A JAX Library for Neural Operator and Foundation Model Training
  577. MolSight: Molecular Property Prediction with Images
  578. Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators
  579. APEX: Audio Prototype EXplanations for Classification Tasks
  580. Learning to Sparsify Stochastic Linear Bandits
  581. Improving Temporal Action Segmentation via Constraint-Aware Decoding
  582. MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers
  583. Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
  584. PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks
  585. Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks
  586. Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection
  587. Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
  588. Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
  589. Useful for Exploration, Risky for Precision: Evaluating AI Tools in Academic Research
  590. Complex-Valued Phase-Coherent Transformer
  591. Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver
  592. Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces
  593. Refresh-Scaling the Memory of Balanced Adam
  594. Think as Needed: Geometry-Driven Adaptive Perception for Autonomous Driving
  595. GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
  596. Arcane: An Assertion Reduction Framework through Semantic Clustering and MCTS-Guided Rule Exploring
  597. HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation
  598. TopoU-Net: a U-Net architecture for topological domains
  599. Initiation of Interaction Detection Framework using a Nonverbal Cue for Human-Robot Interaction
  600. Unlocking air traffic flow prediction through microscopic aircraft-state modeling
  601. SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
  602. A Stability Benchmark of Generative Regularizers for Inverse Problems
  603. Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning
  604. MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization
  605. NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
  606. Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear
  607. Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging
  608. Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
  609. Guided Streaming Stochastic Interpolant Policy
  610. Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
  611. PixelFlowCast: Latent-Free Precipitation Nowcasting via Pixel Mean Flows
  612. ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
  613. Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection
  614. From Single-Step Edit Response to Multi-Step Molecular Optimization
  615. Slum Detection and Density Mapping with AlphaEarth Foundations: A Representation Learning Evaluation Across 12 Global Cities
  616. Speech-based Psychological Crisis Assessment using LLMs
  617. MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Driving
  618. Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
  619. The two clocks and the innovation window: When and how generative models learn rules
  620. The Value of Mechanistic Priors in Sequential Decision Making
  621. Differentially Private Sampling from Distributions via Wasserstein Projection
  622. Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
  623. Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout
  624. Anchor-guided Hypergraph Condensation with Dual-level Discrimination
  625. Annotations Mitigate Post-Training Mode Collapse
  626. BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training
  627. Learning Graph Foundation Models on Riemannian Graph-of-Graphs
  628. Optimizer-Induced Mode Connectivity: From AdamW to Muon
  629. Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference
  630. Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage
  631. Prospective Compression in Human Abstraction Learning
  632. Geometric 4D Stitching for Grounded 4D Generation
  633. Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation
  634. INFANiTE: Implicit Neural representation for high-resolution Fetal brain spatio-temporal Atlas learNing from clinical Thick-slicE MRI
  635. OZ-TAL: Online Zero-Shot Temporal Action Localization
  636. Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
  637. GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
  638. The Truth Lies Somewhere in the Middle (of the Generated Tokens)
  639. Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning
  640. Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
  641. Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach
  642. Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning
  643. Total Generalized Variation regularization closes the gap between neural-eld and classical methods in seismic travel-time tomography
  644. SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis
  645. Beyond Majority Voting: Agreement-Based Clustering to Model Annotator Perspectives in Subjective NLP Tasks
  646. JODA: Composable Joint Dynamics for Articulated Objects
  647. Generating synthetic electronic health record data using agent-based models to evaluate machine learning robustness under mass casualty incidents
  648. Novel GPU Boruta algorithms for feature selection from high-dimensional data
  649. From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
  650. Selection of the Best Policy under Fairness Constraints for Subpopulations
  651. Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
  652. Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning
  653. FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
  654. Frequency Adapter with SAM for Generalized Medical Image Segmentation
  655. Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
  656. NaiAD: Initiate Data-Driven Research for LLM Advertising
  657. The Observable Wasserstein Distance
  658. Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
  659. Voice Biomarkers for Depression and Anxiety
  660. Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
  661. TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models
  662. Deep Learning under Fractional-Order Differential Privacy
  663. Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
  664. Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
  665. ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
  666. Continuous Latent Contexts Enable Efficient Online Learning in Transformers
  667. DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment
  668. UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
  669. Flag Varieties: A Geometric Framework for Deep Network Alignment
  670. Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
  671. Unified Approach for Weakly Supervised Multicalibration
  672. MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery
  673. Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
  674. Probing Routing-Conditional Calibration in Attention-Residual Transformers
  675. Efficient Neural Architectures for Real-Time ECG Interpretation on Limited Hardware
  676. ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation
  677. Sub-Footprint Effect Correction in FW-LiDAR Point Clouds via Intra-Footprint Target Unmixing
  678. The Metacognitive Probe: Five Behavioural Calibration Diagnostics for LLMs
  679. Yield Curve Forecasting using Machine Learning and Econometrics: A Comparative Analysis
  680. Free Energy Manifold: Score-Based Inference for Hybrid Bayesian Networks
  681. The Association of Transformer-based Sentiment Analysis with Symptom Distress and Deterioration in Routine Psychotherapy Care
  682. Supercharging Bayesian Inference with Reliable AI-Informed Priors
  683. Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling
  684. Modeling Atomic Conformational Ensembles of Proteins via Test-Time Supervision of Boltz-2 on Cryo-EM Density Maps
  685. Loom: Hybrid Retrieval-Scoring Outfit Recommendation with Semantic Material Compatibility and Occasion-Aware Embedding Priors
  686. EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
  687. Pretraining large language models with MXFP4 on Native FP4 Hardware