mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 1 Oct 2026

736 papers

  1. FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching ModelsDiffusion models → Flow matching, time series and science
  2. Token Utility for On-Policy Distillation via Local Trust-Region OptimizationKnowledge distillation → On-policy and self-distillation for LLMs
  3. Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt CollectionLLM agents and tool use → Financial trading and forecasting agents
  4. Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only DataLLM reasoning → Prompting and chain-of-thought reasoning +1
  5. SLVR: Structured Latent Visual Reasoning via Human-like Reasoning FlowsLLM reasoning → Multimodal reasoning +1
  6. WAMJET: A Harness for World Action Model AccelerationWorld models → Embodied and robot world models +1
  7. ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based AgentsLLM agents and tool use → Software engineering coding agents
  8. GRAFT: Growing Agglomerative Foundation Models via Continual Teacher DistillationKnowledge distillation → Multimodal distillation
  9. Open-Endedness Bench: Measuring Epistemic Process from Agent RecordsLLM agents and tool use → Web, search, and research agents
  10. Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed ComputeMixture-of-experts → Expert routing strategies
  11. Mitigating Social Sycophancy via Pluralistic Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  12. DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative RenderingDiffusion models → 3D, point cloud and scene generation
  13. OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game EngineLLM agents and tool use → Reinforcement learning for LLM agents
  14. Test-time Multi-agent Coordination by Decomposed Value Gradient FlowLLM agents and tool use → Reinforcement learning for LLM agents +1
  15. Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction TasksLLM reasoning → Reasoning benchmarks and evaluation
  16. Reward Inflation: A Healthy Stimulus for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  17. How To Train Your World Model: Fine-tuning vs RAG for LM-based World ModelingWorld models → World models for language agents
  18. CriticHack: Evaluating Visual Rewards Under Robot Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  19. Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research AgentsLLM agents and tool use → Web, search, and research agents
  20. Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term MemoryWorld models → Video-generation world models and simulators
  21. Instance-Dependent Regret for CMDPs with Step-Wise ConstraintsDeep reinforcement learning methods → RL theory and sample complexity
  22. On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI TutorRetrieval-augmented generation → Agentic RAG, agents and memory
  23. World Action Modeling with Progressive Visual PlanningWorld models → Embodied and robot world models
  24. MeshQuery: Agentic Seam Planning for UV ParametrizationLLM agents and tool use → Multimodal and embodied agents
  25. Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  26. What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token ComputeLLM agents and tool use → Tool learning and function calling
  27. Harnessing LLMs as Agents: What Does It Cost?LLM agents and tool use → Agent memory systems
  28. MEA: A Reward-Driven Multi-Agent System for Faithful Model ExplanationsLLM agents and tool use → Web, search, and research agents
  29. Tropical Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  30. APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term MemoryLLM agents and tool use → Agent memory systems
  31. OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor PoliciesLLM agents and tool use → Multimodal and embodied agents
  32. SideKernel: A Usable microVM Sandbox for AI Coding Agents on macOSLLM agents and tool use → Software engineering coding agents
  33. Reinforcement Learning Techniques for the Optimization of Target Polarization in Nuclear Physics Scattering ExperimentsDeep reinforcement learning methods → RL for energy, networks and operations
  34. A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and ReportingLLM agents and tool use → Multimodal and embodied agents
  35. Bandits via Additive Quantized RepresentationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  36. Evaluating and Improving the Robustness of Large Language Models to Input Sequence VariationsLLM safety and security → Backdoor and data poisoning attacks
  37. Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  38. Mitigating Private Data Leakage in LLMs with WhiteoutLLM safety and security → Membership inference attacks
  39. Prompted to Discriminate: Generalizing Malicious-Input Probes in the WildLLM agents and tool use → Agent threats, guardrails and governance +1
  40. Trained Agentic Context ManagementLLM agents and tool use → Agent memory systems
  41. Energy Saving in 5G and Beyond Networks: A Quantum Reinforcement Learning ApproachDeep reinforcement learning methods → Quantum reinforcement learning
  42. Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution InheritanceLLM agents and tool use → Software engineering coding agents
  43. Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation SteeringMechanistic interpretability → Activation steering methods
  44. Latent-MOPD: Latent Multi-Teacher On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  45. Flow Matching for Fast Posterior Sampling in Bayesian Inverse ProblemsDiffusion models → Flow matching, time series and science
  46. Coco: An Agentic Copilot for the Hardware--Software Co-Design LifecycleLLM agents and tool use → Software engineering coding agents
  47. Traversing the Satisfaction-Diversity Frontier in Text-to-Image DiffusionDiffusion models → Image generation, text-to-image and editing
  48. Rethinking World-Action Model for Compositional and In-Context Robotic ManipulationWorld models → Embodied and robot world models
  49. SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search AgentsLLM agents and tool use → Agent memory systems
  50. SocialVLA: A Social Perception Gateway for Human-Reaction-Based Failure Detection and Recovery in VLA ManipulationVision-language-action models → Failure recovery and robustness
  51. Lexicographic Multi-Objective On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  52. DeReAct: Decomposed Reasoning and Acting for Reliable AI AgentsLLM reasoning → Reasoning for agents, planning and code +1
  53. MIRROR: Multipath Quorum Integrity for LLM Multi-Agent CommunicationLLM agents and tool use → Agent threats, guardrails and governance
  54. From Behavior to Provenance: Attributing Tabular Foundation Models to Synthetic Pretraining DataSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  55. Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality RegularizationDiffusion models → Flow matching, time series and science
  56. World Editing: Intervening on Executable Worlds at Increasing DepthWorld models → World models for language agents
  57. Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use AgentsLLM agents and tool use → Tool learning and function calling
  58. Slow-Fast Multi-Teacher On-Policy Distillation for Capability PreservationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  59. World-Calibrated Proposal-to-Action Flow for Vision-Language-Action ModelsVision-language-action models → World model-based VLA
  60. DeskForge: Dense Supervision from Desktop Environments for Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  61. Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional AttacksLLM safety and security → Jailbreaking
  62. EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe ModelingLLM agents and tool use → Multimodal and embodied agents
  63. Awomo-SimDataEngine: Agentic Simulation-ReadyWorld GenerationLLM agents and tool use → Multimodal and embodied agents
  64. Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  65. From Mathematical to Executable Certificates for Machine UnlearningLLM safety and security → Machine unlearning
  66. Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent HarnessesLLM agents and tool use → Tool learning and function calling
  67. KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable RewardsLLM agents and tool use → Agent threats, guardrails and governance
  68. ROWBench: Do Video Models Render What the Program Specifies?World models → Video-generation world models and simulators
  69. Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied AgentsLLM agents and tool use → Agent skill learning and evolution +1
  70. Embedding Prediction Helps Image GenerationDiffusion models → Diffusion foundations and sampling
  71. VISTA: A Visual Harness for Reasoning in an Interactive WorldLLM reasoning → Multimodal reasoning
  72. FERPO: Forward Entropy-Regularized Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  73. Hierarchical Continuous Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  74. The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language ModelsLLM reasoning → Mathematical reasoning
  75. Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder featuresMechanistic interpretability → Interpreting biomedical and science models
  76. DMAD: Distribution Matching as Adversarial Distillation for Fast Visual GenerationDiffusion models → Robustness, privacy and adversarial aspects
  77. OmniSeek: Native Tool Integration for Multi-turn Audio-Visual ReasoningLLM reasoning → Audio-language model reasoning +1
  78. From Gradients to Capabilities: Understanding Multi-Teacher On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  79. AutoCompact: Learning When to Compact Context in Long-Horizon Coding AgentsLLM agents and tool use → Software engineering coding agents
  80. World Observer: Joint Actor-Observer Generation for Persistent World ModelingWorld models → Video-generation world models and simulators
  81. DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic CommunicationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  82. 4Director: Controlling Video World Models with Rigid 3D GeometryWorld models → Video-generation world models and simulators
  83. When Do Intrinsic Rewards Lead to Exploration?Deep reinforcement learning methods → Deep RL algorithms and representations
  84. Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language ModelsLLM agents and tool use → Tool learning and function calling
  85. Finetuning with Sampling: SFT Learns Better Than You ThinkDeep reinforcement learning methods → Deep RL algorithms and representations
  86. Sample complexity bounds for categorical Markov random fields via Discrete DiffusionsDiffusion models → Diffusion foundations and sampling
  87. Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient AdaptationMixture-of-experts → Mixture of LoRA experts
  88. SkeleWAM: Skeleton World-Action Modeling for Efficient Robotic ManipulationWorld models → Embodied and robot world models
  89. Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic ScenesKnowledge distillation → Multimodal distillation
  90. Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  91. GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D ReasoningLLM reasoning → Spatial and embodied reasoning +1
  92. Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption ConstraintsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  93. External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State ProbingLLM reasoning → Hallucination detection and mitigation
  94. UniWAM: Unified World-Action ModelWorld models → Embodied and robot world models +3
  95. Form and Void: Entangled Composition through an Autonomous AI AgentLLM agents and tool use → Multimodal and embodied agents
  96. DiDE:Direct Injection with Color-Texture DEcoupling for 3D StylizationDiffusion models → 3D, point cloud and scene generation
  97. CARM: Cancellation-Aware Response Masking for LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  98. Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation ControlLLM reasoning → Reasoning for agents, planning and code +1
  99. Task-Adaptive Grounded 3D-Programmers Using 2D VLMsLLM reasoning → Spatial and embodied reasoning +1
  100. On Language Drift during RLVR Post-TrainingLLM reasoning → Reinforcement learning for reasoning
All 736
  1. Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering ChaosDeep reinforcement learning methods → RL for robot locomotion and manipulation
  2. Exploring Weaknesses of Generative Image Watermarks against Latent Frequency MaskingLLM safety and security → Watermarking generated content and models
  3. Mem++: Non-Destructive Memory for Long-Term Organizational LLM AgentsLLM agents and tool use → Agent memory systems
  4. From Reasoning Failures to Composable Video Spatial IntelligenceLLM reasoning → Spatial and embodied reasoning +1
  5. Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit InterferenceDiffusion models → Robustness, privacy and adversarial aspects
  6. Token-Level Video Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  7. RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
  8. SIEVE: Selective attention-value Suppression for Vision-Language Models UnlearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  9. Do Your Own Research: Learning to Forecast by Learning to SearchLLM agents and tool use → Financial trading and forecasting agents
  10. Latent JEPA: Abstract Future Prediction for Latent Reasoning in ChemistryLLM reasoning → Clinical and biomedical applications
  11. Latent-Foresight: End-to-End Learning Predictable Representations for Latent World ModelsWorld models → Latent predictive world models
  12. Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer TokensMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  13. A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combinedLLM reasoning → Clinical and biomedical applications
  14. Graph Representation via Elements of Discrete Morse and Cobordism TheoriesDiffusion models → Flow matching, time series and science
  15. Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  16. Error-Corrected Inference-Time Scaling for Imperfect Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. Cross-Lingual Alignment for Decoder-Only Models using MoE RoutersMixture-of-experts → MoE large language models
  18. MoLE: Mixture of Latent Experts for Complementary Visual ReasoningLLM reasoning → Multimodal reasoning
  19. Asynchronous LLM Post-Training: Group-Mass Capping and Convergence AnalysisLLM reasoning → Reinforcement learning for reasoning
  20. Unsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow MatchingDiffusion models → Flow matching, time series and science
  21. TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic DesignLLM agents and tool use → Software engineering coding agents
  22. Walking the Embedding Space: Datastore Extraction from Multimodal RAGMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +2
  23. LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene ReconstructionLLM agents and tool use → Multimodal and embodied agents
  24. ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive ManufacturingVision-language-action models → 3D and spatial-aware VLA
  25. Detecting Inconsistencies in Model Specifications with LLM-as-Verifier ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  26. On the Divergence of Accuracy and Mechanism Consistency in Time Series World ModelsWorld models → World models for language agents
  27. Continuous Process-Level Evaluation for Evolving Enterprise AI Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  28. The Asymptotics of Language Model Alignment with MemoryLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  29. Debias Anything: Fairness with Diversity without Supervision in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  30. LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series IdentificationDeep reinforcement learning methods → RL training of language and agent models
  31. SkillEvoLean: Mutation-enhanced skill evolution for Lean proversLLM agents and tool use → Agent skill learning and evolution
  32. Continuous Conditioning of VLAs with Augmenting EMG and Visual Task DescriptorsVision-language-action models → VLA architectures and generalization
  33. iADD: Improving Alignment and Diversity in Diffusion Policy OptimizationDiffusion models → Diffusion and flow policies for robotics
  34. SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified ExamplesLLM safety and security → Backdoor and data poisoning attacks
  35. Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI AgentsLLM agents and tool use → GUI and mobile agents
  36. VETO: Video Efficient Token Optimization for Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  37. Q-Learning for Reachability in MEC-Free MDPsDeep reinforcement learning methods → RL theory and sample complexity
  38. CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code GenerationLLM agents and tool use → Software engineering coding agents
  39. The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web FetchingLLM safety and security → Prompt injection and agent security
  40. A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  41. VideoEvolve: Evolving Agent Harnesses for Video Temporal GroundingLLM agents and tool use → Multimodal and embodied agents
  42. TopK-Guided: Adaptive, Budget-Aware Activation Sparsity for Efficient LLM InferenceEfficient LLM inference and serving → Early exit and edge inference
  43. PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce MeasurementsDiffusion models → Flow matching, time series and science
  44. Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and UnderstandingLLM reasoning → Multimodal reasoning
  45. End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving SystemsEnd-to-end autonomous driving → End-to-end system architecture
  46. ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive InjectionVision-language-action models → World model-based VLA
  47. Function-Structured Reinforcement Learning with Executable Verifiers for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  48. Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text ConditioningDiffusion models → Image generation, text-to-image and editing
  49. AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized RecommendationLLM agents and tool use → Agentic recommender systems
  50. ActiveWAM: Evidence-Aware Active Vision for World-Action ModelsWorld models → Embodied and robot world models
  51. Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  52. Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality PreservationMultimodal LLMs / vision-language models → Image editing and quality assessment
  53. Iterative Policy Refinement through Semantic Rollout AnalysisOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  54. Not All Error Yields to Scale: Where Scaling Stops in Vision-Language InferenceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  55. Measuring the Stability Assumption Behind Action ChunkingOffline RL and imitation learning from data → Imitation learning methods
  56. Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  57. Agents Are Systems, Not Models: Rethinking Agentic EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Oneira: From Open-Ended Generation to Open-World Interaction in Video World ModelsWorld models → Video-generation world models and simulators
  59. Hob-VL: A Benchmark for Visually Grounded Boolean ReasoningLLM reasoning → Multimodal reasoning
  60. Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMsLLM reasoning → Multimodal reasoning
  61. Continual Reinforcement Learning with NeuroevolutionDeep reinforcement learning methods → Deep RL algorithms and representations
  62. Managing Context and Communication in Distributed Agentic UAV SwarmsLLM agents and tool use → Agentic AI for wireless networks
  63. Towards Optimal Policy ImprovementDeep reinforcement learning methods → RL theory and sample complexity
  64. Chaining Skills to Hijack LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  65. AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language ModelsLLM reasoning → Audio-language model reasoning
  66. Completion Aware Guidance for World Action ModelsWorld models → Embodied and robot world models
  67. Range-GRPO: Policy Optimization via Pairwise Relations among Reward IntervalsLLM reasoning → Reinforcement learning for reasoning
  68. Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear ProgrammingDeep reinforcement learning methods → RL for games and combinatorial optimization
  69. Towards Reliable Vision-Language Models for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  70. Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box FeedbackDiffusion models → Flow matching, time series and science
  71. Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  72. GAW-PO: Preference Optimization with Gradient-Aligned Token WeightsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  73. Sharpening Tax in Post-TrainingLLM agents and tool use → Reinforcement learning for LLM agents
  74. OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling AgentsLLM agents and tool use → Agent threats, guardrails and governance
  75. MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  76. Learned End-to-End Guidance Schedules for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  77. SALD: Self-Referenced Advantage Learning for Diffusion ModelsDiffusion models → Discrete and text diffusion
  78. No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning CollapseSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  79. Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and TrajectoriesLLM agents and tool use → Web, search, and research agents
  80. Rethinking Probability-Based Reinforcement Learning From Posterior ConcentrationLLM reasoning → Reinforcement learning for reasoning +1
  81. Repurposing Obsolete Representations for Post-Deployment AdaptationLLM safety and security → Machine unlearning
  82. A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and GuidanceLLM agents and tool use → Medical and scientific domain agents
  83. DRelay: Global Draft Context for Prefix-Aware Parallel Speculative Decoding RepairEfficient LLM inference and serving → Speculative decoding
  84. Distillation of Tabular Foundation Models into Efficient PredictorsKnowledge distillation → General knowledge distillation methods
  85. MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  86. SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  87. Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief StatesLLM agents and tool use → Agent memory systems
  88. Optimal Transport Meets Reinforcement Learning: A SurveyOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  89. Smoother Flow Matching via Contrastive Trajectory RepulsionDiffusion models → Flow matching, time series and science
  90. Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?Deep reinforcement learning methods → Deep RL algorithms and representations
  91. PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal AnalogiesLLM reasoning → Multimodal reasoning
  92. Learning Commute-Time-Preserving World Models for PlanningWorld models → Latent predictive world models
  93. LLM-Driven Multi-Agent Control for Skill-Based Smart ManufacturingLLM agents and tool use → Software engineering coding agents
  94. MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal ReasoningLLM reasoning → Multimodal reasoning
  95. Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation TasksVision-language-action models → Failure recovery and robustness
  96. PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  97. Reachability-Informed Reinforcement Learning for Multi-Impulse Interplanetary TransfersDeep reinforcement learning methods → RL for robot navigation and UAV control
  98. CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One HypernetworkDiffusion models → Image generation, text-to-image and editing
  99. PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled TradingDeep reinforcement learning methods → Adversarial robustness and RL in finance
  100. TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn SafetyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  101. ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series ForecastingDiffusion models → Flow matching, time series and science
  102. Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget TrainingDiffusion models → Diffusion foundations and sampling +1
  103. ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  104. Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  105. PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  106. DeFA: Dependency-Guided Failure Attribution for LLM AgentsLLM agents and tool use → Software engineering coding agents
  107. Context-Aware Error Mitigation Orchestration for Hybrid Quantum Reinforcement Learning on NISQ SystemsDeep reinforcement learning methods → Quantum reinforcement learning
  108. When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated PromptsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  109. Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budgetLLM reasoning → Reasoning for agents, planning and code
  110. ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note GenerationLLM reasoning → Clinical and biomedical applications
  111. Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing OptimizationDiffusion models → Diffusion and flow policies for robotics
  112. Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model PlanningWorld models → Latent predictive world models
  113. AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  114. AutoGUIWorld: Image Generators as Visual World Models for GUI AgentWorld models → World model security and GUI agents +1
  115. Dependency-Aware Reward Shaping for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  116. Federated Agent OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  117. Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End RatesDiffusion models → Flow matching, time series and science
  118. FlashBack: Knowing When to Remember in Streaming Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  119. ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal ReasoningLLM reasoning → Reasoning for agents, planning and code
  120. Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  121. Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  122. CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI AssessmentLLM reasoning → Clinical and biomedical applications
  123. PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation ModelsWorld models → Embodied and robot world models
  124. My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  125. Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  126. Auditing Action Settlement in LLM Agent Environments: Order, Progress, and ReplayLLM agents and tool use → Software engineering coding agents
  127. Does Scaling Reinforcement Learning Really Require More Training?Deep reinforcement learning methods → Deep RL algorithms and representations
  128. AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent PipelinesLLM agents and tool use → Software engineering coding agents +1
  129. MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill BlendingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  130. YouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research AgentsLLM agents and tool use → Web, search, and research agents
  131. WBAG: A Whole-Body and Attached-Geometry Safety Framework for Vision-Language-Action ManipulationVision-language-action models → Safety and adversarial attacks
  132. Improving Math Reasoning through Value-guided Informative SearchLLM reasoning → Reinforcement learning for reasoning
  133. GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR EventsLLM reasoning → Clinical and biomedical applications
  134. Kernelized Activation SteeringMechanistic interpretability → Activation steering methods
  135. MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMsLLM safety and security → Jailbreaking
  136. Network World Models as Environments for Algorithm Design on Complex SystemsWorld models → Latent dynamics models and model-based RL
  137. Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  138. LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded EvidenceRetrieval-augmented generation → Legal and financial RAG +1
  139. Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding AgentsLLM agents and tool use → Software engineering coding agents
  140. FutureWorlds: Learning Robotic World Models from Alternative FuturesWorld models → Embodied and robot world models
  141. Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow OptimizationLLM agents and tool use → Software engineering coding agents
  142. Scaling and Distilling Text Embeddings for Better DiffusibilityDiffusion models → Discrete and text diffusion
  143. From Discovery to Decision: Finite-Budget Recoverability in LLM VotingLLM reasoning → Test-time compute and efficient thinking
  144. Calibration-risk routing for controlled world-model adaptationWorld models → Latent dynamics models and model-based RL +1
  145. Distilling Directional VerificationKnowledge distillation → Knowledge distillation for LLMs
  146. Closed-Loop Refinement and Execution for Learned Driving PlannersEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  147. Adapter Thickets: Splitting an RLVR Budget Beats Concentrating ItLLM reasoning → Reinforcement learning for reasoning
  148. Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA PoliciesVision-language-action models → Reasoning and chain-of-thought in VLA
  149. NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity FieldsVision-language-action models → Human-video and latent-action pretraining
  150. RISED: RubrIcs for agentic multi-environment Selection and sElf-DistillationLLM agents and tool use → Reinforcement learning for LLM agents +1
  151. VeriHarness: Scaling Agentic Verification for Long-Horizon TasksLLM agents and tool use → Software engineering coding agents
  152. The Other Half of Workflow Portability: Evidence-Backed HPC Site Profiles with Agentic DiscoveryLLM agents and tool use → Software engineering coding agents
  153. Cybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic DelegationLLM agents and tool use → General LLM agent frameworks and benchmarks
  154. Beyond Leaderboards: Tokenomics of Agentic Small Language Model EnsemblesLLM agents and tool use → General LLM agent frameworks and benchmarks
  155. Two Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales UnfoldDiffusion models → Discrete and text diffusion
  156. GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness EvolutionLLM agents and tool use → GUI and mobile agents +1
  157. ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based ReasoningLLM reasoning → Reasoning for agents, planning and code
  158. ReHoPER: Receding-Horizon Planning for Enhanced ReasoningLLM reasoning → Test-time compute and efficient thinking
  159. Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free GuidanceDiffusion models → Diffusion foundations and sampling
  160. Rate-Optimal Algorithm for Adversarial Linear CMDPsDeep reinforcement learning methods → RL theory and sample complexity
  161. A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and PlatformEnd-to-end autonomous driving → End-to-end system architecture
  162. In CEM, a World Model Is Also a Proposal MechanismWorld models → World models for language agents
  163. Finding the Right Fit: Model-Harness Interactions across Agent TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  164. eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token RoutingVision-language-action models → Reinforcement learning and post-training
  165. ActiveSaddler: Automated Curriculum Learning for Agent Harness OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  166. Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  167. Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  168. TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  169. When Do Biological Reasoning Models Use Their Biological Inputs?LLM reasoning → Clinical and biomedical applications
  170. Clock Diffusion: Efficient Semi-Autoregressive Continuous Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  171. Cross-Benchmark Transfer from RL on Agentic Coding TasksLLM agents and tool use → Reinforcement learning for LLM agents
  172. FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software VerificationLLM agents and tool use → Software engineering coding agents
  173. Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype ReweightingDiffusion models → Flow matching, time series and science
  174. MemFit: Efficient Long-Term Agentic MemoryLLM reasoning → Knowledge- and tool-augmented reasoning +1
  175. An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database DesignLLM agents and tool use → Educational agents and math problem solving
  176. Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation ModelsDiffusion models → Diffusion and flow policies for robotics
  177. CtrlWAM: Controllable World Action Models with Aligned Intent and ForesightWorld models → Embodied and robot world models
  178. Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point TransformersMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  179. Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent ArenaMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  180. AuraForge: Scaling Security Supervision for Training Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
  181. Learning Multiple Timescales for Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  182. Geometric Similarity in VLM Low-Level Vision RepresentationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  183. Exploring the Design Space of Permutation Diffusion LLMs
  184. Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
  185. Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders
  186. Lotus: Learning to Understand Time-series by Learning to Forecast
  187. Strategic Governance of AI Models in Earth Science
  188. Nonlocal Hamiltonian Dynamics on Sparse L'evy Graphs: Spectral Analysis and Multimodal Sampling
  189. Image-Based Breast Implant Detection for Mammography Dataset Curation and Near-Real-Time Deployment: Comparing Foundation Models and Task-Specific Convolutional Models
  190. Least Squares for Time Series Forecasting
  191. Fine-Grained Emotion Classification from Mobile App Reviews: An Empirical Study with Large Language Models
  192. StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
  193. TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods
  194. Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights
  195. How Causality Bridges the Semantic Gap
  196. Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models
  197. Labels Override Definitions in Jev-Style Typed Decision Models
  198. Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces
  199. High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning
  200. Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models
  201. DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
  202. Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting
  203. Pincer: Resource Authorization for Agents using a Digital Twin
  204. Learning Closure of Dynamical Systems with Kernel Ridge Regression
  205. Oracle headroom without signal: null-calibrated evaluation of candidate selection for thermal heart rate estimation
  206. Neuron merging via inverse-activation regression for post-training compression of sigmoid neural networks
  207. How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate
  208. Out of Sync, Out of Sight: Phantom State Attacks against IIoT Intrusion Detection
  209. ENCORE: Exact Non-equilibrium COntrol with Replica Exchange for Diffusion Generation
  210. A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs
  211. Autoregressive Differentiable Method for Integer Programming
  212. BaCP: Backbone Contrastive Pruning for Preserving Representations in Extremely Sparse Neural Networks
  213. Hypothesis-guided discovery of cognitive algorithms via program refinement
  214. Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation
  215. Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers
  216. IGNITE Tokamak World Model Architecture
  217. From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models
  218. Post-Training Quantization of Autoregressive Weather Models
  219. HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems
  220. Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents
  221. LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing
  222. "I just assumed that it would translate": examining MT risk awareness among healthcare staff with abbreviations as a use case
  223. DeepStratNet: A Context-Aware Coordinate Regression Framework for Seismic Horizon Tracking under Sparse Labels
  224. Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement
  225. Threshold-Aware Conformal Routing
  226. From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders
  227. Windfoil: Closed-Form Coverage for Real-Time and Differentiable Vector Graphics
  228. SD-DPC: Sparse Dictionary Differentiable Predictive Control
  229. Capability Scaling-Down Laws for LLM Compression
  230. A Composable AI-Accelerated Iterative Solver for 3D-IC Thermal Modeling
  231. CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking
  232. FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms
  233. Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs
  234. AI-driven Thermal-aware Data Center Capacity Planning
  235. A Generative Model of Complex Networks Using Graphons and Neural Inverse Operators
  236. Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
  237. Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks
  238. CRISP: A Framework for Clause-Reconstructed Interpretable NeuroSymbolic Propositions
  239. Geometry-Aware Time Reparameterization for Flow-Map Distillation
  240. An AI-Based Multi-Stage Approach for Androgenetic Alopecia Assessment from Low-Magnification Scalp Images
  241. The AI Theorist reveals excitonic structure in α-RuCl3
  242. Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
  243. When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge
  244. VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
  245. Validated Data Onboarding for AI Demand Forecasting on U.S. Building Meter Data: Design, Controlled Evaluation, and a Corrected Negative Result
  246. FlashSinkhorn 2: Block-Sparse Entropic Optimal Transport
  247. Octrees as an Explicit 3D Language
  248. Social bot detection in the age of ChatGPT: Challenges and opportunities
  249. The Surprising Effectiveness of Shared Memory in Looped Transformers
  250. FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering
  251. THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS
  252. EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision
  253. Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM
  254. Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning
  255. Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI
  256. Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization
  257. Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift
  258. ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time
  259. Conformal Prediction for Time Series with Deep Sequence Models
  260. Why Does Adaptive Batching Help LLM Pretraining? A Perspective from Unbounded Variance
  261. Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation
  262. Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
  263. SCOPE-4D: Endoscopic 4D Geometry Foundation Models
  264. A Multi Method Importance and Performance Efficiency Analysis of Topological Metrics for Natural Visibility Graph Based Cyber Attack Detection
  265. NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches
  266. SoTa: Soft Tactile Skins for Dexterous Manipulation
  267. Joint Movement and Compression Ratio Design for Mobile Embodied AI Networks (MEAN)
  268. SCION: Scene Composition with Instanced Neural Primitives
  269. SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
  270. PowerBench: Measuring Language Model Bias in Power-shifting Requests
  271. Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
  272. Psi-Resilience: Model-Free Feature Importance from 1D Topological Signals
  273. HakemBench: A Turkish Benchmark of Typed Decisions
  274. Diffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition
  275. Expected Utility Regret Rule: Minimax and Bayes Optimal Portfolio Choice
  276. Effects of interpulse-interval variation on deep-learning classification of bat vocalizations
  277. MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning
  278. The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
  279. CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation
  280. Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging
  281. Event-guided Neural Video Compression
  282. ZAGNet: Zone-Aware Graph Aggregation Network for Patient-Level Lung Ultrasound Diagnosis
  283. Moore, Escher, Penrose: A Conformal Golden Braid
  284. Sphere Encoder 2
  285. One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
  286. ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
  287. SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
  288. TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning
  289. HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
  290. InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation
  291. Cost-augmented Schr"odinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
  292. Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
  293. Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry
  294. Decoding Looped Transformers Better for (Almost) Free
  295. SoftServe: A Scalable Quasi-Newton Method for Deep Learning
  296. Generative Cinematographer: Composing Camera and Object Motion in 3D
  297. Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
  298. Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
  299. Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination
  300. Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
  301. MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation
  302. From Knowledge Access to Source Learning: Developing Source-Specific Competence
  303. Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
  304. Faynt: Scaling and Optimizing Policies for Competitive Melee
  305. MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI
  306. Linear Programming Representations and Strongly Polynomial Algorithms for Robust Markov Decision Processes
  307. Local Support Learning
  308. Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows
  309. A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification
  310. Surface-volume self-supervised representation learning of brain MRI for genetic discovery
  311. Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)
  312. HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution
  313. Kolmogorov-Arnold Networks for Free-Boundary Partial Differential Equations
  314. Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
  315. LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
  316. PyPottery: an AI-powered end-to-end suite for pottery processing and publication
  317. Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval
  318. AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure
  319. Sequential Capacity of Quantum Processes with Finite Memory
  320. Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA
  321. Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
  322. Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal
  323. HydroJEV: A one-second, training-free screen for cyber-attack and fault attribution in water distribution networks
  324. Distributionally Robust Schr"odinger Bridge
  325. Typological Alignment of Stack-Based Language Models on Mildly Context-Sensitive Artificial Languages
  326. Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration
  327. Relative Transitions, Not Absolute Destinations: A Transfer-and-Ground Framework for Target-Trajectory-Free Human Mobility Generation
  328. SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL
  329. Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation
  330. Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
  331. Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
  332. BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials
  333. Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries
  334. Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks
  335. Weather-Aware Domain Adaptation for Street-View Weather Recognition
  336. Can AI Oversight Be Zero Knowledge?
  337. Comparing a gradient boosting algorithm to the GOES FDC for wildfire detection
  338. Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities
  339. Universal interpolation for deep residual self-attention networks
  340. The Curvature of Regret in Contextual Linear Optimization
  341. Sim+Real: Joint Simulation-Experiment Training Improves Balanced Prediction in Physical Systems
  342. FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks
  343. Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage
  344. Training-Free Diffusion Planning with Analytical Local Scores
  345. EndoLive: Real-Time Style Transfer for Endoscopic Endonasal Skull Base Surgical Video
  346. Sharp Non-Asymptotic Analysis of the Penalized Challenger in β-EB-TCI for Bernoulli Bandits
  347. A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
  348. Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models
  349. Pragmatic DML with AI-Learned Representations
  350. Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
  351. CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
  352. LAST: Looped Audio Spectrogram Transformer
  353. DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction
  354. Same Reward, Different Skills: When Multimodal RL Learns to Look
  355. MapLightning: Online Vectorized HD Map Construction with 1D Map Tokens
  356. Higher-Order Positional Encodings for Graph Representation Learning
  357. A foundation for systematic analysis of transformers and RNNs for tractography
  358. A Structured State Space Sequence Model for Multi-Class Classification of Malware
  359. Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
  360. Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2
  361. Memory-Guided B-Roll Generation from User Video Collections
  362. Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies
  363. EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation
  364. Where LLMs Fail with Visualization DSLs
  365. From Network Intrusion Detection to Blockchain-Backed Endpoint Detection and Response: Mapping the Landscape of Decentralized Detection-and-Response Architectures
  366. From Pixels to Policy: A Multi-Agent System for Intervention and Geo-Spatial Decision Support
  367. From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment
  368. AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes
  369. Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
  370. Temporal-Difference Learning for Dragonchess
  371. Optimal Stochastic Bilevel Optimization with First-Order Oracles
  372. Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography
  373. Code Owns the Simulation, Jev Owns the Evaluation
  374. Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention
  375. Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings
  376. Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities
  377. Generalized Engression Models
  378. Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
  379. MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
  380. AI-assisted mitotic counting improves reproducibility and efficiency across multiple tumour types
  381. PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization
  382. A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings
  383. Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift
  384. Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
  385. RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
  386. GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design
  387. CODesign: Consistency from Data to Trajectory in All-Atom Protein Binder Co-Design
  388. Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs
  389. OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
  390. GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking
  391. SoK: Decentralized Agent Economic Infrastructure
  392. Evidence-Gated Research: Statistically Controlled Model Adoption in Adaptive Search
  393. FFBL-Coop: Association-Decoupled Cooperative 3D Multi-Object Tracking
  394. Designing for Interpretation Uncertainty: Architecture and Principles for Topological Learning Analytics Dashboards
  395. 3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability
  396. World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
  397. Fixed-point neural samplers on discrete spaces
  398. Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses
  399. Removing spurious minima for planar features by skip connections
  400. RelICL: Training-free Relational Learning with Tabular Foundation Models
  401. Anomaly Detection and Localization for the Pantograph-Catenary System
  402. vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning
  403. Architecture Without an Architect? Global Governance of Artificial Intelligence in a Divided World
  404. In-context Learning of Single-index Targets: Comparing Kernel and Feature Learners
  405. CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement
  406. MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation
  407. Task-Oriented Rank Adaptation for Continual Learning in Text Classification
  408. Learning PDE Dynamics between Submanifolds Using Green's Observation Operators
  409. Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information
  410. Artifact Annotations Partially Substitute for Per-User Calibration: SAFE-EDA and a Normalization-Controlled Evaluation of Wrist-EDA Affect Recognition
  411. Compound interpretation is based on analogy
  412. MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization
  413. Beyond Leaderboard Scores: A Deployment-Focused Protocol for Interpretable Tracking Evaluation in Pedestrian-Centric Environments
  414. When Text-to-Image Helps Editing: The Effects of Conditioning During Denoising
  415. Invent a Dataset: Measuring dataset generation abilities with zero seed
  416. pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
  417. Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization
  418. DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models
  419. CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations
  420. Towards a Cloud Fog Edge System for Smart Building
  421. Beyond Demographic Balance: Multi-Metric and Intersectional Evaluation of Fairness in MIMIC-IV Mortality Prediction
  422. MCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees
  423. FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices
  424. Fusing Visual and Textual Representations via Multi-layer Fusing Transformers for Vietnamese Visual Question Answering
  425. Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yor`ub'a
  426. Generalization in Neural Networks Through the Lens of Magnitude Potential
  427. What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language
  428. FedLore: Communication and Memory Efficient Federated Learning via Shared Gradient Low-Rank Projection
  429. Exposing the Cost of Deep Learning Audio Development
  430. Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
  431. Permutation-Robust Decision Modeling with Candidate-Independent Block-Causal Attention
  432. Convergence Analysis of STORM Under Different Geometries
  433. Which LLM to pick? Online Active Model Selection for Large Language Models
  434. Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize
  435. PAGER: Partial-to-global Alignment via Geometric and Relational Distillation
  436. Evaluating Physical Consistency and Plausibility in Generative Scenario Models for Autonomous Driving
  437. Beyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling
  438. The hidden advantage of mask resampling: a theory of masked autoencoders
  439. Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization
  440. QK-Wanda: Coupling Queries and Keys for Unstructured Pruning
  441. From Rules to Neural Graphs: Scalable Structured Prediction for Patent Prior Art Search
  442. Revisiting Cross-Reconstruction for Generalizable Deepfake Detection
  443. Synthetic training for long-tail haemorrhagic lesion segmentation in data-scarce settings
  444. The AI Assessment Sandbox Configurator: A Framework to Support Technical Assessment in AI Regulatory Sandboxes
  445. FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization
  446. False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift
  447. Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)
  448. Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction
  449. Exact Distinguishability in Non-Markovian Decision Processes
  450. Auto-Formalizing Neuro-Symbolic Predictors
  451. SuperMotion: Source-Preserving Denoising for Text-Driven Human Motion Editing
  452. FedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training
  453. How the Audit Rule Shapes Faithful Factor Explanations in LLMs
  454. VoxelSynth3D: Interpretable Volumetric Image-Domain Metal Artifact Reduction with a Paired Synthetic CLINIC Benchmark
  455. FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains
  456. VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
  457. OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation
  458. Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers
  459. Let the Heads Talk: Beyond Diagonal Graph Attention
  460. Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization
  461. The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents
  462. Multi-Party Backchannel Prediction: a Diagnosis, a Benchmark, and a Ceiling
  463. FiVOS: A Fish Segmentation Algorithm Based on Interactive Video Object Segmentation and Filter Enhancement
  464. ALFRED: Requirement-driven development of an open-source mobile manipulator for long-term plant monitoring
  465. Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
  466. When Does a Second Model Help? Cross-Model Review in LLM Verification
  467. LESS: Lightweight Evolutionary Supernet Search in Minutes
  468. NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video
  469. Tight Transition Time Bounds for Separable Logistic Regression at the Edge of Stability
  470. Streaming algorithms for robust max-min diversification
  471. Uncertainty-Guided Handshake: Efficient Human-in-the-Loop Refinement for Surgical-Grade Glioma Segmentation
  472. Code-Switching Spoken Language Identification as Multi-Label Set Prediction
  473. On skew-symmetric distributions and their use in Monte Carlo sampling algorithms: coordinate-free, Gibbs-style and manifold versions of the Barker proposal
  474. ibUMAP: Coherent and Scalable Field Evaluation for UMAP Optimization
  475. The Impact of Processing Parameters on High-Accuracy Measurements in UAV Photogrammetry
  476. A Deterministic and Auditable AI Security Risk Assessment Framework with ATLAS Aligned Executable Rules and Formal Verification
  477. Learning ab initio phase-field models
  478. Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
  479. SHAMS: An Audio-Grounded Pronunciation Benchmark for Levantine Arabic
  480. Least-time Gradient Flow
  481. Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones
  482. Localisation-Aware Uncertainty for Pretrained Object Detection
  483. Contrastive Attention Mitigates Spectral Bias in Spiking Transformers
  484. AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models
  485. LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction
  486. AiSearch: Interactive Multi-Modal Search with VLMs
  487. Supervising Sound Localization by In-the-wild Egomotion
  488. Is it Possible to Generate Irreversible PolyProtected Templates from Face Embeddings using System-Specific Keys?
  489. Robust Evidential Learning Through Latent Consistency
  490. Gacha Decoding: Eliciting Diverse Generations Through Instruction Following
  491. SupraTITO: Transferable Generative Molecular Dynamics for Supramolecular Systems
  492. Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
  493. Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness
  494. Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
  495. From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics
  496. Degree-Corrected Joint Matrix Factorization for Multilayer Community Detection
  497. Fold'EM: Direct atomic structure inference from Cryo-EM particles
  498. Port-Hamiltonian Neural Networks for Systems with Multiple Asymptotically Stable Equilibria
  499. Discrete Wasserstein Flows for One-Step Generative Modeling
  500. Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions
  501. Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents
  502. ARCCS: An Automated Regulatory Compliance Checking System
  503. Robust Non-Clairvoyant Scheduling with Classification Models
  504. An ontology for cross-sectoral crisis management: core and public health modules
  505. Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes
  506. Clifford Sheaf Neural Networks
  507. Prediction-powered Neural Architecture Search
  508. What Wins a Vote? Formatting, Length, and Lexical Diversity in the French Compar:IA LLM Arena
  509. EP-Flow: Disordered Crystal Structure Prediction without Site-Level Annotations
  510. ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wild
  511. DAYJOB: A Benchmark for Long-Horizon Professional Work
  512. Federated Learning for LLMs over Mobile Networks: Issues and Solutions in the RAN Transport
  513. STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
  514. Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations
  515. Questionnaire-Guided Disaggregation of Energy Appliance Use for Domestic Smart Meter Data
  516. ODDR: One-Step Deshadow Diffusion via Reward Guidance
  517. Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models
  518. Model validation in machine learning: A scenario-based guide from hold-out splits to nested group cross-validation in biomedical and applied research
  519. ShelfChange3D: Object-Level 3D Change Detection for Retail Shelf Monitoring
  520. Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics
  521. PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
  522. SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents
  523. Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders
  524. IQS-BO: In-Context Query Selection for Bayesian Optimisation
  525. Feedback Without the Wait: Piloting a Generative AI Practice Platform in a Large Maths Class
  526. Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
  527. Revision-Aware Independent Agent Graphs for Dynamic Reasoning
  528. Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration
  529. Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
  530. Mixture-Trained Merging for Unified Multi-Objective Models
  531. Harness Annealing: Learning to Act with Less External Control
  532. Judgement in the Age of Jev: From Evaluation Scarcity to Evaluation Abundance
  533. HHR: Hierarchical Hash Retrieval for Efficient LLM Generation
  534. A Compact Explicit 4D Representation for Dynamic Scenes
  535. Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
  536. Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models
  537. EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes
  538. Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction
  539. Semantic RGB--Depth Based Surgical Skill Assessment in Microscopic Stereo Videos
  540. Autoregressive Drillhole Modelling Under Distribution Shift
  541. iSEE: Object Permanence Through Self-Supervision
  542. Low-Budget Active Learning through Entropic Optimal Transport
  543. Color Independent Word Segmentation From Transcribed Bangla Passages
  544. When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design
  545. Fully Online Decentralized Learning in Stochastic Games with Unknown Independent Chains
  546. Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions
  547. CAGE-NAS: Certified Functional Descent for Efficient Model Growth
  548. Learning Rate Transfer for Hybrid Transformer-SSM Architectures
  549. HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
  550. Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability
  551. Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
  552. BanglaDial-Abuse: A Corpus-Grounded Dataset for Regional Dialect Identification in Abusive Bangla Text
  553. When Is Deletion Ordering Tractable? From Update Dynamics to Permutation Structure
  554. OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots
  555. Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift
  556. Classical Hardness of Learning Functions of Hamiltonians
  557. ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation
  558. Do Multilingual Encoders Produce Language-Consistent Semantic IDs?
  559. The RSNA Intracranial Aneurysm (RSNA-ICA) Dataset
  560. Open Vocabulary Word Recognition From Transcribed Bangla Texts
  561. Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting
  562. Counting and Min-Cost Encoding for Tokenization in Large Language Models
  563. Latent Information Sharing for Accelerating Federated Learning
  564. CortexBridge: Cortical Alignment of EEG Montages for Foundation Models
  565. AbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers
  566. Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives
  567. Beyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research
  568. Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation
  569. How Much Can Language Models Gain from Test-Time Computation?
  570. MVDG: Efficient Multi-view 3D Disambiguation on Unconstrained Real-World Images
  571. Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain
  572. OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous
  573. Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
  574. Polylogarithmic Sparsity of Randomly Reweighted NPMLEs for Gaussian Mixtures
  575. Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models
  576. Jev-IDS: System One Models for Network Intrusion Detection
  577. Overcoming Kernel Redundancy for Scaling Logic Gate Networks
  578. Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability
  579. JoinGR: Learning to Traverse Join Graphs for Table Retrieval
  580. HierGF: Hierarchical Gaussian Fields via Geometry-perception Message Passing for Sparse-view 3D Reconstruction
  581. Capturing In-Context Learning Dynamics with Task Operators
  582. Towards Subject Consistency over Dynamic Subject Sets in Video Generation
  583. Gradient-Guided Density Peak Clustering
  584. Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study
  585. Empty Commitments: When Agents Promise What They Cannot Deliver
  586. Bootstrapping Video Interaction Generation with Synthetic State Transitions
  587. SLIM: Simplex-Lattice Interpolation Merging
  588. Posterior sampling by source-space MCMC via prior-based few-step transport maps
  589. Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
  590. It Takes Workflows to Evolve Better Workflows
  591. Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation
  592. Initial condition recovery in nonlinear damped viscous photoacoustic tomography using a convolutional neural network-guided gradient-free optimization framework
  593. VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction
  594. Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning
  595. Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model
  596. Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening
  597. What Can Analogy Tell Us About Artificial Consciousness?
  598. Evaluating LLM-Generated Preference Distributions
  599. Reliability-aware short-term roll prediction for unmanned surface vehicles via multi-task learning and adaptive centralization
  600. VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations
  601. The Price of Correlated Tests: How Strict Should a Model Release Gate Be?
  602. Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures
  603. Neural scaling laws and evolution of learnable activation functions of Kolmogorov-Arnold networks
  604. HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record
  605. The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization
  606. Can AI Scientists Coordinate at Runtime?
  607. Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection
  608. Variational Streaming Flow: Probabilistic Forecasting in Physical Time
  609. Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack
  610. RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation
  611. A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models
  612. Structure-agnostic Causal Representation Learning
  613. RPTune: Learned Context Curation for LLM Catalog Search
  614. Video-Index: A Curated Meta-Benchmark for Video Understanding
  615. Role-aware Heuristic Episodic Attention for Conversational LLMs
  616. A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions
  617. PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
  618. Platonic Task Arithmetic
  619. Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations
  620. EyeTAG: Eye Trajectory-Aware Gaze Estimation
  621. OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework
  622. Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
  623. The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention
  624. STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling
  625. Screw Attention: Rigid-Body Algebra Inside a Transformer
  626. Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident
  627. Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
  628. Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
  629. DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
  630. Machine Translation for Sign Languages
  631. UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking
  632. Don't Waste the Noise: Importance-Guided Perturbation Allocation under Joint Global and Local Constraints
  633. MorphoBranch: A Fine-Structure-Preserving Workbench for Morphometric Analysis of Branched Cellular Structures
  634. Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction
  635. Child-Adapted Structured Phonological Representations for Interpretable Speech Sound Analysis
  636. SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing