mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 5 Oct 2026

673 papers

  1. CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household TasksLLM agents and tool use → Multimodal and embodied agents
  2. LRCC: Generalizing Low-Rank Compression with Conditional ComputationMixture-of-experts → MoE large language models
  3. Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark KnowledgeLLM safety and security → Safety alignment, refusal and guardrails
  4. Task-Space Imitation Guidance for Efficient Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  5. Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  6. From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  7. On Open-Ended Information Seeking for Information Elicitation AgentsLLM agents and tool use → Social simulation and multi-agent debate
  8. Adapting to Changes in Agent Behavior via Finite-Depth Policy SensitivityDeep reinforcement learning methods → RL theory and sample complexity
  9. PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic ReasoningLLM reasoning → Clinical and biomedical applications +1
  10. COMPASS: Finding Where Reasoning Lives in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  11. Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious EditingDiffusion models → Robustness, privacy and adversarial aspects
  12. ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative AdaptationLLM reasoning → Spatial and embodied reasoning
  13. AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationEfficient LLM inference and serving → KV cache quantization
  14. Fork-and-Flush: Escaping Idea Basins in Autoresearch AgentsLLM agents and tool use → Web, search, and research agents
  15. What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-TrainingLLM reasoning → Reinforcement learning for reasoning
  16. Inference and learning in sparse autoencoders as natural gradient flowMechanistic interpretability → Sparse autoencoder training and evaluation
  17. Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  18. GeoWM: Efficient Direct World Modeling in Explicit GeometryWorld models → World models for autonomous driving
  19. MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen EnvironmentsLLM agents and tool use → Agent memory systems
  20. Dynamic Budget Allocation for LLM Evaluation under Hard Resource ConstraintsLLM agents and tool use → Tool learning and function calling +1
  21. Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?LLM agents and tool use → Agent threats, guardrails and governance
  22. Tracking Is Not Permanence: What Video World Models Keep of a Hidden ObjectWorld models → Video-generation world models and simulators
  23. Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help?LLM reasoning → Test-time compute and efficient thinking +1
  24. RELACE: retrospective likelihood-based action credit estimation for long-horizon language agentsLLM reasoning → Reinforcement learning for reasoning
  25. Stepped MoE: Segment-Level Routing with Configurable Inference ComplexityMixture-of-experts → Efficient MoE training and inference systems
  26. Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale ScaffoldingLLM reasoning → Reinforcement learning for reasoning
  27. Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic SurgeryDiffusion models → Image generation, text-to-image and editing
  28. Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision MakingLLM agents and tool use → Reinforcement learning for LLM agents
  29. Weight Oracles: Reading Neural Network Weights with Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  30. Memory-Efficient Expert Routing for Distributed MoE TrainingMixture-of-experts → Expert routing strategies
  31. Structuring MoE Expert Selection for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  32. Understanding and Mitigating Inference-Time Overreliance Using Agentic MemoryLLM agents and tool use → Agent memory systems
  33. Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google ScaleLLM agents and tool use → Software engineering coding agents
  34. SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  35. What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-LocalizationLLM reasoning → Spatial and embodied reasoning
  36. Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling PlannerLLM agents and tool use → Software engineering coding agents
  37. Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  38. MemMux: Runtime Verification and Honest Resource Attribution for Fleets of Parallel Coding AgentsLLM agents and tool use → Software engineering coding agents
  39. Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context DistillationDiffusion models → Diffusion and flow policies for robotics +1
  40. Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
  41. Conditional Flow Matching for Transport Between Markov ProcessesDiffusion models → Flow matching, time series and science
  42. Minimal Witness Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  43. Cascadia: Resident 975B MoE Inference on Eleven AI PCsMixture-of-experts → Efficient MoE training and inference systems
  44. Distributionally Robust Mixture-of-Experts TrainingMixture-of-experts → Expert routing strategies
  45. Energy-Conditioned Noise Schedule and Whitening for Spectral DiffusionDiffusion models → Inverse problems and image restoration
  46. SPEAR: Five Principles for Interactive Human-Agent AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  47. Exact Unlearning via Quantized Sufficient StatisticsLLM safety and security → Machine unlearning
  48. Interleaved Projected Gradient Descent for Safe Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  49. Jailbreaking Open-Weight LLMs via Random Embedding PerturbationsLLM safety and security → Jailbreaking
  50. SoloQ: Calibration-Free Quantization for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  51. AMBER: Training Long-Horizon Web Agents through Append-Only MemoryLLM agents and tool use → Agent memory systems
  52. Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream ActivationsMechanistic interpretability → Probing deception, bias and beliefs
  53. Evaluating Inference Compute for Generative AI: A Framework for Enterprise WorkloadsLLM agents and tool use → Software engineering coding agents
  54. Towards a Unified Misuse Monitoring BenchmarkLLM agents and tool use → Agent threats, guardrails and governance +1
  55. SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative DecodingLLM agents and tool use → Tool learning and function calling +1
  56. Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State MachineLLM agents and tool use → Tool learning and function calling +1
  57. Behavioral Cloning MysteryOffline RL and imitation learning from data → Robot manipulation imitation learning
  58. SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech SeparationMixture-of-experts → Multimodal MoE models
  59. TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  60. One Figure, Every Canvas: Editable Flowchart Relayout via Agentic PipelineLLM agents and tool use → Multimodal and embodied agents
  61. Base Models Can Reason By Taking a Cue From Training DataLLM reasoning → Prompting and chain-of-thought reasoning
  62. S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video GenerationDiffusion models → Video generation
  63. Learning to Read the Contextual Tokens in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  64. Recursive Video In-Context Learning for Agentic RobotVision-language-action models → Reinforcement learning and post-training +1
  65. Direct Intermediate Initialization for Tilted Diffusion SamplersDiffusion models → Flow matching, time series and science
  66. Towards Looped Models Done Right, Part II: Rethinking at Fixed PointsLLM reasoning → Reinforcement learning for reasoning +1
  67. MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM AgentsLLM agents and tool use → Agent memory systems
  68. CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time ScalingLLM reasoning → Reasoning for agents, planning and code +2
  69. TAPDreamer: Transferable Adversarial Patches for World Action ModelsWorld models → Embodied and robot world models
  70. Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation ModelsEfficient LLM inference and serving → Token pruning and merging for ViTs
  71. H-JEPA: End-to-End Learning of Hierarchical World Models for Visual PlanningWorld models → Embodied and robot world models
  72. Sharpen Without Search: On-Policy Distillation of Sequence-Level Power DistributionKnowledge distillation → Knowledge distillation for LLMs
  73. MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion TransformersDiffusion models → Video generation
  74. Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design VerificationLLM reasoning → Reasoning for agents, planning and code +1
  75. T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step SearchLLM agents and tool use → Web, search, and research agents
  76. BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  77. BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding ModelsMixture-of-experts → Expert routing strategies
  78. MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA TasksMultimodal LLMs / vision-language models → Medical vision-language models +1
  79. Programmatic Search Agents: Extending Agentic Search Beyond Query ReformulationLLM agents and tool use → Web, search, and research agents
  80. OVAL: Output-Aware Local Page Bases for KV Cache RetrievalEfficient LLM inference and serving → KV cache optimization
  81. How Sparse Probability Maps Shape Mixture-of-Experts RoutingMixture-of-experts → Expert routing strategies
  82. VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video UnderstandingLLM agents and tool use → Agent memory systems
  83. Learning What to Imitate: Entropy-Aware Distribution MixingLLM reasoning → Test-time compute and efficient thinking
  84. Reward Stealing Attack on Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  85. What Matters for Latent Reasoning with Flow MatchingLLM reasoning → Prompting and chain-of-thought reasoning
  86. Considering Context: When World Models Need Context EncodersWorld models → Latent dynamics models and model-based RL +1
  87. Wikidata Search Traces: A Dataset for Training Knowledge Graph Search AgentsLLM agents and tool use → Web, search, and research agents
  88. Representation-Space MMD for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  89. Long-Horizon Textual World Modeling through Structured ReasoningWorld models → World models for language agents
  90. RealtimeWAM: One-Step Asynchronous World Action ModelsWorld models → Embodied and robot world models
  91. SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World ModelsWorld models → Embodied and robot world models
  92. Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM ServingLLM agents and tool use → Software engineering coding agents +1
  93. Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice AssistantsLLM reasoning → Audio-language model reasoning
  94. Mind the Execution Gap: Action-Semantic Mismatch in World-Model ControlWorld models → World model security and GUI agents
  95. Before Agent Tells The Lie: Has Deception Already Been Represented?LLM agents and tool use → Agent threats, guardrails and governance
  96. BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  97. HERA: Harness-Environment Co-Evolution for Reliable Agentic AbstentionLLM agents and tool use → General LLM agent frameworks and benchmarks
  98. Conditional Flow Matching for Single-Neuron Electrophysiology: Capturing Multimodal Responses Across StimuliDiffusion models → Flow matching, time series and science
  99. Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric MemoryLLM reasoning → Test-time compute and efficient thinking
  100. ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior AuditingLLM agents and tool use → Agent threats, guardrails and governance
All 673
  1. Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation LimitationsLLM safety and security → Vision-language and text-to-image safety
  2. GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed PlacementDeep reinforcement learning methods → RL for energy, networks and operations
  3. Behavior-Preserving KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  4. Smorph: Playable Sound Morphing with Diffusion ModelsDiffusion models → Audio, speech and music
  5. Odyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation RoutesEnd-to-end autonomous driving → End-to-end system architecture
  6. Latent Flow Matching for Molecular Graph GenerationDiffusion models → Flow matching, time series and science
  7. AgentPrivArena: Evaluating and Auditing Real-world AI Agent PrivacyLLM agents and tool use → Agent threats, guardrails and governance
  8. The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  9. Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  10. SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMsLLM reasoning → Spatial and embodied reasoning +1
  11. From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?LLM agents and tool use → Medical and scientific domain agents
  12. Quantifying the Stability of Multi-Step Reasoning via Error AmplificationLLM reasoning → Test-time compute and efficient thinking
  13. RAISED: Self-Distillation for Robustness to Prompt Injection in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  14. Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid DesignDeep reinforcement learning methods → RL for robot navigation and UAV control
  15. CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  16. Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction DetectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  17. Steering by Influence: Curvature Aware Data Weighting for Activation SteeringMechanistic interpretability → Activation steering methods
  18. Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability ReasoningLLM reasoning → Reasoning for agents, planning and code
  19. Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question AnsweringLLM alignment / RLHF / preference optimisation → Medical LLM alignment +1
  20. KineWorld: Action-Induced Transport Fields for Embodied World ModelingWorld models → Embodied and robot world models
  21. ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-ImprovementSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  22. MeSD: Multi-Evidence Self-Distillation for VideoLLMKnowledge distillation → On-policy and self-distillation for LLMs
  23. BabelFake: A Multilingual Audio-Visual DeepFake BenchmarkSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  24. SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic NeighborhoodsDiffusion models → Robustness, privacy and adversarial aspects
  25. Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders RetainMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. CRAFTER: Causality-based Self-adaptation for Autonomous IoT SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  27. RollPlace: Improving Macro Placement via Monte Carlo Rollout SearchDeep reinforcement learning methods → RL for energy, networks and operations
  28. VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event PredictionMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  29. DeferKV: Rethinking Eviction Timing for One-Shot KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  30. Future Anchored Verification and Online Recovery for World Action ModelsWorld models → Embodied and robot world models
  31. VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  32. DPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic LearningLLM reasoning → Test-time compute and efficient thinking
  33. Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better DiscoveriesLLM reasoning → Reinforcement learning for reasoning
  34. Ramp Metering Control via Hybrid State Deep Reinforcement Learning in Partially Observable Connected Vehicle EnvironmentsDeep reinforcement learning methods → RL for autonomous driving and traffic
  35. CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean CenteringDiffusion models → Diffusion foundations and sampling
  36. Generative World Models Enable Predictive Control of Laser Melt Pool DynamicsWorld models → Latent predictive world models
  37. Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  38. APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twinsLLM agents and tool use → Medical and scientific domain agents
  39. Frequency-Decoupled Diffusion Guidance for Non-Blind Image DeblurringDiffusion models → Inverse problems and image restoration
  40. Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained SellersLLM agents and tool use → Reinforcement learning for LLM agents
  41. Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding AgentsLLM agents and tool use → Software engineering coding agents
  42. Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent SystemsLLM agents and tool use → Web, search, and research agents
  43. Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide DesignLLM agents and tool use → Medical and scientific domain agents
  44. Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety EvaluationEnd-to-end autonomous driving → Generative simulation for driving
  45. Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability RepairLLM agents and tool use → Software engineering coding agents
  46. Efficient Test-time Adaptation through Candidate Verification and Divergence ShiftsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  47. I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  48. Benchmarking Jailbreak Guardrails for Embodied AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  49. Diffusion Meets Unrolling: Compressive SAR Image Reconstruction with Interleaved Learned CorrectionsDiffusion models → Inverse problems and image restoration
  50. Flash-OPD: Fast On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  51. Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action ChunksOffline RL and imitation learning from data → Robot manipulation imitation learning
  52. From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment SimulationWorld models → World models for language agents +1
  53. Anatomy-preserving unpaired cone-beam CT refinement for image-guided radiotherapy using pseudo-label guided diffusionDiffusion models → Medical imaging and segmentation
  54. Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PIILLM safety and security → Backdoor and data poisoning attacks
  55. Adaptive Mean Flow for Responsive Closed-Loop Robot ControlOffline RL and imitation learning from data → Robot manipulation imitation learning
  56. Boosting Transferable Adversarial Attacks against Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  57. Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems HelpLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. TrustMI: Causally controlling how assistants trust their usersLLM safety and security → Safety alignment, refusal and guardrails
  59. ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  60. Backdooring Sparse AutoencodersLLM safety and security → Backdoor and data poisoning attacks +1
  61. MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic ForecastingDiffusion models → Flow matching, time series and science
  62. Adaptive Expert Guidance for Efficient On-Policy Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  63. D-Loop: Looped Diffusion Drafting for Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  64. Ultrasound Operator Guidance Using World Modeling and Retrieval Based Action PlanningWorld models → Medical and surgical world models
  65. P3: Persistent Particle Planning for Constrained Diffusion ControlDiffusion models → Diffusion and flow policies for robotics
  66. AgentSpy: Making AI Agent Behavior ObservableLLM agents and tool use → Agent threats, guardrails and governance
  67. EpicWorldModel: Exploration-driven Planning with Latent World ModelsWorld models → Latent predictive world models
  68. How (and How Not) to Use Data Augmentation in VLA Post-TrainingVision-language-action models → Reinforcement learning and post-training
  69. From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image RetrievalLLM reasoning → Multimodal reasoning
  70. Can Language Models Learn to Reject Their Own Bad Reasoning Steps?LLM reasoning → Test-time compute and efficient thinking
  71. Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning TeachersLLM reasoning → Reinforcement learning for reasoning +1
  72. Reachability-Aware Diffusion Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  73. From Social Reasoning to Embodied Interaction: An Agentic Framework for Social RobotsLLM agents and tool use → Multimodal and embodied agents
  74. ReMem: Streaming Video Understanding With Long Context RetentionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  75. ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  76. VERA: Scaling Verifiable Environments for Agentic co-EvolutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. Beyond Transport Cost: Routing Differences between Flow Matching and Optimal TransportDiffusion models → Flow matching, time series and science
  78. Safe Image Generation via Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  79. Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation SteeringDiffusion models → Discrete and text diffusion +1
  80. The Optimization Landscape of Learning Compacted Context ModelsEfficient LLM inference and serving → Efficient reasoning and agent inference
  81. Mulligan: Performance-Guided Data Collection for Efficient On-Robot LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  82. Off-Policy Merging Beats On-Policy Self-Distillation for Continual LearningKnowledge distillation → On-policy and self-distillation for LLMs
  83. Weave Mamba Fusion: Global Cross-Scale Interaction for Lightweight Face DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  84. Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent TrainingWorld models → World model security and GUI agents +2
  85. Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated BipedDeep reinforcement learning methods → RL for robot locomotion and manipulation
  86. CACFG: Curvature-Aware Classifier-Free Guidance and Optimal ControlDiffusion models → Diffusion foundations and sampling
  87. Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling AgentsLLM agents and tool use → Agent memory systems +1
  88. Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer ValidationLLM agents and tool use → Agent threats, guardrails and governance
  89. Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular DataDiffusion models → Diffusion foundations and sampling
  90. Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  91. Level-of-Token DiffusionDiffusion models → Video generation
  92. A Testable Theory of Atomic FeaturesMechanistic interpretability → SAE features and their applications
  93. Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent SystemLLM agents and tool use → Agent threats, guardrails and governance +1
  94. Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust EnforcementLLM agents and tool use → Agent threats, guardrails and governance
  95. MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical TasksLLM agents and tool use → Medical and scientific domain agents
  96. Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor ImitationDiffusion models → Diffusion and flow policies for robotics +1
  97. Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation PoliciesDiffusion models → Diffusion and flow policies for robotics
  98. Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex TasksLLM agents and tool use → Web, search, and research agents
  99. The Unexpired Plan: A Free Monitor for Accelerated Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  100. Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented TuningKnowledge distillation → On-policy and self-distillation for LLMs
  101. CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE TrainingMixture-of-experts → Efficient MoE training and inference systems
  102. HLA-WM: Hybrid Linear Attention for Long-Horizon Video World ModelsWorld models → Video-generation world models and simulators
  103. End-to-End Safe Social Navigation via Multi-Task Reinforcement Learning and Probabilistic PerceptionDeep reinforcement learning methods → RL for robot navigation and UAV control
  104. PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM AgentsLLM agents and tool use → Agent memory systems
  105. When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  106. Rotated, but How Far? Diagnosing and Improving Object-Rotation Reasoning in VLMsLLM reasoning → Spatial and embodied reasoning +1
  107. SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence ConstraintsLLM safety and security → Watermarking generated content and models
  108. Nexus: An Execution Fabric for AI Agents Across Cloud, Edge, and DevicesLLM agents and tool use → Software engineering coding agents
  109. Difference Feature Map Distillation: Transferring Inter-Sample Relational Knowledge Towards Efficient Transformer-Based TrackingKnowledge distillation → Detection and dense prediction distillation
  110. Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  111. Learning Coordinated Visuomotor Box-Pushing from Solo DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
  112. StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  113. Spacecraft Rendezvous Trajectory Generation with Modular Constraints via Diffusion Model CompositionDiffusion models → Diffusion and flow policies for robotics
  114. Visual Grounding Safety in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  115. Geometry-Aware Diffusion Approximate Posterior Sampling for Sparse-View and Limited-Angle CT
  116. Adversarial RL for Port-Scan Evasion: Attacker Feature Visibility in Edge-Deployed IDS
  117. Climbing the Design Ladder: Sequential Knowledge Distillation for Early-Stage Circuit Timing Prediction
  118. Targeted search shows that random-device testing underestimates worst-case error in a simulated wave-based neural operator
  119. Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
  120. Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI
  121. Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
  122. MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation
  123. Jarvis: A Proactive Speech Agent for Multi-Party Conversations
  124. MARS: Multi-resolution Adaptive Routing for Sequential Recommendation
  125. Two-Sample Testing for Random Graphs without Vertex Correspondence
  126. Closing Ambient Clinical Documentation Gaps with Automated Provider Queries
  127. Source-Learned Reliance for Selective Test-Time Adaptation of Multimodal Time Series
  128. Does Muon Need Fine-Grained Spectral Shaping?
  129. The interface of data assimilation and machine learning
  130. Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning
  131. Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security
  132. Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures
  133. SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction
  134. In With the Old: Enhancing 'Classical' Document Automation with Generative AI
  135. Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance
  136. Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits
  137. Efficient Multimodal Inference through Adaptive Acquisition and Sequential Fusion
  138. Auditable Claims about AI Agents
  139. Interpretable Hypergraph Learning via Neural Additive Models
  140. Active Feature Acquisition for Cost-Efficient Temporal Prediction with Reduced Participant Burden
  141. Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?
  142. Artifact removal improves electrodermal waveforms but not downstream classification in a virtual-reality balance task
  143. When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability
  144. StaFIR: Convex Learning of Stationarity-Aware Causal Filters
  145. Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability
  146. AccentCL: Robust Accent Classification with Incremental Expansion
  147. 2d-fet-bench: from spatial reasoning to fet design on flakes
  148. Benchmarking Label-Revealed Online Updates for EEG BCI Decoding
  149. Learnable Spectral Activations
  150. Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds
  151. Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models
  152. Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy
  153. Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering
  154. A perspective note on likelihood approximation and inference for complex simulation models using a chain of aggregated normalizing flows
  155. DeepAJM: Deep Association Joint Model for Irregularly Sampled data
  156. WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification
  157. HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generation
  158. SimCortex v2: Joint Cortical Surface Reconstruction with Near-Zero Collisions and Self-Intersections
  159. Multigroup Fairness and Omniprediction: Separations and Equivalences
  160. Identity-Conditioned Score Fusion for Open-Set Person Re-Identification
  161. Who Wrote It Is Not Enough: Detecting Who Contributed the Insight
  162. Redundancy and synergy in multivariate Gaussians via the Blackwell order
  163. Towards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow Prediction
  164. A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models
  165. Evaluating Escalation Signals for LLM Routing: Targets, Controls, and Five Ways to Fool Yourself
  166. Evaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud Environments
  167. CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
  168. A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care
  169. Logbook: Extremely Long-form Audio Event Understanding
  170. Advantage of Entangled Learning Rules in Quantum Measurement Class Learning
  171. SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents
  172. Localize Any Object in X-Ray Security Scans without Human Annotation
  173. Scale-Invariant Training for Time Series Foundation Models
  174. ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning
  175. Rule-Based Languages for Neurosymbolic AI
  176. From Sandbox to Enforcement: Confidence-Qualified Threat Intelligence for Critical Infrastructure
  177. The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory
  178. Kurate: Scalable Scientific Quality Analysis
  179. Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation
  180. Assumption-lean logistic regression with missing covariates
  181. A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization
  182. FlexiFlow: Bandit-based Model Switching in ML Workflows
  183. Empirical-Bayes spectral partial pooling across related tasks
  184. Lock-in EP: An In-Situ Training Algorithm for Oscillatory Hardware
  185. A Trust Layer for Agent Evaluation
  186. Algorithmically Aligned Neural Agglomerative Tree Construction
  187. Does the Model Use the Feature? Separating Steering from Mechanism in LLMs
  188. Neural Algorithmic Reasoning for Graph Saddle Point Problems
  189. Neural Fields Encode Adaptation Geometry
  190. Can Semantic Geometry Teach an AI Judgement?
  191. Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings
  192. SPECTRUM: Proximal Spectral Modulation for Looped Self-Distillation
  193. Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty
  194. Monocular Navigation Relative to Unknown Spacecraft Using a Transformer-Aided Kalman Filter
  195. How Inefficient Is Natural Gradient Descent? From Exact Optimality to Theta ( √ log d ) Divergence
  196. TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes
  197. Deep Learning Based Illegal Bowling Action Detection
  198. Data, Numbers, and Geometry: Three Tutorials on Numerical Methods, Machine Learning, and Evaluation
  199. Constant-Curvature Sliced Gromov-Wasserstein for Heterogeneous Cross-Curvature Alignment
  200. RoboCap: A New Platform for Egocentric Robot Learning
  201. Reward-Driven Learning under Prompt-Level Differential Privacy
  202. An overview of machine learning-enhanced iterative methods for systems of linear and nonlinear equations
  203. Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage
  204. Can LLM-assisted regularization increase forecast accuracy for migration flows in low data regimes?
  205. Responsible Institutional Analytics: Interpreting Bias with AI Support
  206. Learning Disentangled Representations with Quantum Variational Autoencoders
  207. Sim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile Robot
  208. Agentic Design Space Exploration for Joint Hardware Configuration Selection and Mapping of AI Inference Workloads on Heterogeneous Edge SoCs
  209. Poisson empirical Bayes estimation of sums of random variables via minimum-distance methods
  210. Identifying Introspection From the Inside
  211. Learning Scientific Exploration from Human Research Decision Trajectories
  212. CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks
  213. CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression
  214. A theory of platonic representations in language models
  215. Adversarial Training for Deep Hedging in Nonstationary Markets
  216. CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
  217. The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective
  218. Is this machine playing?
  219. Aggregating User Preferences while Ensuring Equity, Diversity, and Inclusion using Graph Summarization
  220. PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence
  221. R2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot Interaction
  222. Sample-Optimal Estimation of the Fr'echet Inception Distance
  223. LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library
  224. MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs
  225. JudgeMoE: Distributional Aggregation for LLM-as-a-Judge
  226. Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation
  227. Muon Is Theoretically Wrong For Convolutions, But Empirically Effective
  228. When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory
  229. T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator
  230. Verified, not generated: expert-verified AI study materials and the distribution of learning gains in a university course
  231. Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach
  232. Smart Content Ingestion for Generative AI Workloads
  233. A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture
  234. A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral
  235. Graph-Based Recognition of Simulated Train-Driver States From Facial and Upper-Body Keypoints
  236. Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin
  237. When Attention Does Not Explain the Peak: Temporal Reference vs. Forecast Output in Attention-Based Time-Series Forecasting
  238. Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity
  239. What Must Replay Preserve? Separating Correctable Bias from Class Correspondence
  240. CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration
  241. Learning Decision-Stump Thresholds in Context: Dynamics of Softmax Attention
  242. On Color Alignment in VAE Latent Spaces and Its Applications
  243. A BEMD-Based Quaternion Filtering Approach Sharp-to-Soft Kernel CT Image Conversion
  244. Decomposition-Guided Curvelet Thresholding for Sharp-to-Soft CT Kernel Conversion
  245. Learning to Simulate Individuals from Macro Social Signals
  246. ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering
  247. Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction
  248. Crop Yield Prediction for Punjab, Pakistan: A Tree-Ensemble and Leaf-Health Prototype, and What Random Validation Hides
  249. sHAIL-Causal: A Sequential Staircase Procedure for Invariant Causal Predictor Discovery
  250. Data Fusion for Errors-in-Variables
  251. GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting
  252. Multi-Task Active Learning with Efficient Resource Allocation
  253. InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation
  254. BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
  255. Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report
  256. UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
  257. PlotGround: Grounding Plot Digitization in Real Scientific Figures and Their Source Data
  258. TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
  259. Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
  260. Private online learning and prediction for Littlestone classes
  261. Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
  262. Finding Gaussian Structure in Bosonic States
  263. Block Disentanglement in CRL: Bridging Identifiability and Visual State Estimation
  264. A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63
  265. Round-Trip KNN Clustering: multiscale hierarchical cluster detection on directed nearest-neighbour graphs
  266. How to scale your HEP ML models: A recipe for robust architecture comparisons at scale
  267. IdeaLens: Detecting AI Ideas in Long-form Writing
  268. On Learning Optimal Corners in Orthogonal Partially Observable Cooperative Guard Art Galleries
  269. Singular parameters and missing limits in neural PDE solvers
  270. Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
  271. MatrixFormer: A Foundation Model for Matrix Completion
  272. Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
  273. Hyperbolic Graph Representation Learning: Embed in One Metric, Optimize with Another
  274. ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring
  275. Improving Diversity in LLM Short Story Generation
  276. Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging
  277. Domain adaptation of Russian ModernBERT for long legal documents
  278. Out-of-control Hamiltonian Learning
  279. SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection
  280. Extending Dynamic World Surface Water Mapping to Sentinel-1 with AlphaEarth Embeddings
  281. Reading the Mood: Emotion-Guided Book-to-Music Recommendation via CGANs and LLMs
  282. A Solvable Model of Adaptive Learning Rate Rescaling: Acceleration, Stability & Scaling
  283. To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks
  284. Adapting prior-data fitted networks for tabular anomaly detection
  285. Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood
  286. GS-Pool: Object-Level Change Detection in 3D Gaussian Splatting
  287. ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections
  288. Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs
  289. Closing the Context Gap: Activation Alignment for Tabular In-Context Learning
  290. Improved Convergence of Large Stepsize Gradient Descent for Logistic Regression
  291. Detecting Nighttime Anomalies from NASA Black Marble Using a Generalized Spatio-Temporally Robust Framework of Machine Leaning Ensembles
  292. The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
  293. Language models can notice an impossible engineering problem yet still report it as solved
  294. Cross-dataset harmonization for robust endoscopic image analysis
  295. Talk Like You: Imitating How You Speak in Real-Time Talking Head Generation
  296. TrustmeWatcher: An Application for Workplace Micro-Sensing and Explainable Well-Being Feedback
  297. The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction
  298. Collective intelligence through aggregation
  299. LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
  300. AffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images
  301. Beyond the Model: The Critical Role of Data Filtering in Clinical Machine Learning
  302. Differentially Private Mixing of Public Datasets Improves Private Learning
  303. Inverse Cross-spectral Neural Networks for Multivariate Time Series
  304. On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck
  305. JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications
  306. Large Language Model-Guided Discovery of Weight-Five Bivariate Bicycle Codes
  307. Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA
  308. Video Encoders Built on Image Representations
  309. COMPASS 2.0: psychometric representational similarity analysis distinguishes symptom structure from personal signal
  310. FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification
  311. Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding
  312. The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits
  313. Separators Make Carry Propagation Learnable:The Geometry of Latent Carry in a Multiplication Transformer
  314. Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
  315. Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable T1ρ and T2 Quantification Without High-Resolution Morphological Images
  316. Molecules of a Story: Community Detection in PMI-weighted Narrative Networks
  317. Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems
  318. VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges
  319. The Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)
  320. Keepsake: Selective Spatial Memory for Long-Horizon Video Generation
  321. Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
  322. LinearPFN: Amortized Variable Selection for Linear Models with Interactions
  323. DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon
  324. FrontVeg V2: A Training-Free Software Framework for Foreground-Aware Zero-Shot Plant Trait Segmentation in High-Resolution Images of Trellised Crops
  325. Synthetic Cultural Agents from Aggregate Anchors
  326. MIRT: Transformers for Truthful Generative Auctions with Whole-feed Permutation Externalities
  327. Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice
  328. Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning
  329. Empirical Variational Autoencoder
  330. A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data Selection
  331. WaveGSSM: Graph Wave State Space Models for Propagating Spatio-Temporal Patterns
  332. Symmetry and AI-assisted discovery of magic-state factories
  333. Anatomy of LLM Sycophancy: What a Flip Rate Hides
  334. GCTAuto-encoder: A Cross modal Framework for Security Flaw Detection in IoT Networks
  335. SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics
  336. ArtifactArena: Evaluating Models by What They Build in the Physical World
  337. Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior
  338. A General Pipeline for Dense Illuminant Estimation via Physically Based Synthetic Data
  339. Improving Proactive AI Assistance with Hierarchical Procedural Understanding
  340. NeuroCBIR: A Fast and Accurate Image Retrieval System for Whole-Brain and Region-Specific MRI
  341. You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue
  342. Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI
  343. polyview: A Python package for multi-view machine learning
  344. FairProp: Fair Node Representation Learning via Differentiable Propagation Layers
  345. AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
  346. MaRO-GS: Mask-Robust Object-Centric Gaussian Splatting from Inconsistent Multi-view Masks
  347. A Physics-Guided Transformer Framework for Electromigration Analysis in Multi-Segment Interconnects
  348. Normality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection
  349. Multimodal Safety Evaluation Should Measure Controllability Beyond Classification
  350. EMG-FM-Bench: A Comprehensive Benchmark for Foundation Model Transfer and Adaptation on Electromyography
  351. Time-series Foundation Models for Predictive Control: The Role of Excitation
  352. Choosing an energy-efficient software architecture for building system diagnostic support
  353. ARO: Aligned Representation learning for multi-Omics data
  354. HeuFouFT: Task-Guided Metaheuristic Coordinate Search for Fourier Fine-Tuning
  355. KESurv: A Kernel Ensemble Method for Patient-Specific Survival Prediction
  356. Valid Stopping in Adaptive Generator-Verifier Loops
  357. Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?
  358. SoK: Semantic Decision Engines in Network Control Loops
  359. Toward Reliable Infant Pose Estimation: A Training-Dynamics Approach to Noisy Annotation Detection
  360. On the Comparison of Optimizers for Imbalanced Learning
  361. Efficient Secure Federated Learning via Information-Theoretically Secure Key Distribution: A Medical Imaging Case Study
  362. Training-Free Transformer Merging via Sequential Local Operator Alignment
  363. FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials
  364. What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
  365. Learning Pareto Stationary Fronts via Single-Pass Backpropagation
  366. Multi-Task Partially Supervised Learning for Super-Resolution and Semantic Segmentation on Earth Observation data
  367. Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models
  368. MTOR: Generalizable AI-Generated Video Detection with Multimodal Semantics and Temporal Over-Regularity
  369. Environmental sensor readings in two crop disease image datasets identify the session in which each image was taken
  370. Multimodal Deep Survival Analysis for Sinkhole Susceptibility
  371. Capability-Driven Self-Evolution of Agent Memory
  372. Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support
  373. GraphDecisionBench: Benchmarking System One Models on Graph Tasks
  374. IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs
  375. Breaking Bureaucracy: Evaluating open-source LLMs for legal document review
  376. Stability-Shaped Deep Graph Learning
  377. Dynamic Minimax Regret Optimization for Robust LLM Post-Training
  378. Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation
  379. Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training
  380. Agentic schema-guided extraction of materials process knowledge from scientific literature
  381. Wiring Matters: Injection Topology and Initialization of Affordance Heads in Vision-Language-Action Policies
  382. Watermarking: from Impossibility to Auditable Compliance
  383. SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts
  384. Sharp dimensional analysis of midpoint methods for Langevin sampling
  385. Teaching a Minimalist Machine to Discover Recursive Programs for Arithmetic
  386. DialectSentEval 2026: Arabic Dialect Sentiment Analysis and Swapping Shared Task
  387. Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data
  388. GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories
  389. Trajectory-Guided Tokenization of Complex CSI for Wi-Fi Sensing
  390. From Abusive Language Classification to Sequence Labeling Identification
  391. When Are Concept Bottleneck Model Explanations Faithful and Compact?
  392. dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
  393. What May an Agent Change About Itself? A Containment Floor for Self-Configuring Agent Runtimes
  394. Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists
  395. OCL-PDE: A Generative Framework for PDE Inverse Problems with Observation-Complementary Latents
  396. SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring
  397. Lipschitz Thinking: Ten Years of Certifiable-by-Design Robust Neural Networks
  398. Shared Stopping Decisions Change Answers in HQQ Cache Quantization
  399. From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models
  400. RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning
  401. Few-Shot Prototype Head Adaptation for On-Device ECG Personalization on PSoC~6
  402. Artificial Intelligence and the New Science of Culture
  403. Certification-Enhanced Generalization Bounds
  404. Bradley-Terry model under general comparison graphs
  405. DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
  406. Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies
  407. Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning
  408. AUTOPILOT An Advanced Perception, Localization and Path Planning Techniques for Autonomous Vehicles Using YOLOv7 and MiDaS
  409. Parameter Estimation in Machining Dynamics with Regenerative Delay and Nonsmooth Friction using Physics-Informed Neural Networks
  410. SO(3)-RoPE for Spherical Transformers
  411. LeAVJEPA: A Minimalist Architecture for Audio-Visual Self-Supervised Learning
  412. Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing
  413. Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime
  414. Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant?
  415. MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting
  416. AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation
  417. EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations
  418. Loss-Invariant Projections as Passive Probes of Learned Representations
  419. Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
  420. Two-Point Local Optimality in k-Means via Boundary-Point Screening
  421. Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision
  422. Auditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs
  423. What Does It Cost to Simulate a Quantum Sentence Classifier? An Energy and Compute Perspective on Near-Term QNLP
  424. Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate
  425. MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge
  426. Bayesian Optimization in Sequence-to-Architecture Latent Space for Zero-Shot NAS
  427. Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training
  428. TIGER: Time-Series Classification with In-Context-Learning Gated Ensemble of Representations
  429. Reinforcement Learning-Based Optimization of Workload-Aware Power Delivery Networks
  430. Impact of Data Augmentation on Confidence Calibration in Melanoma Classification
  431. On Impact of Loss Function on the Performance of Neural Networks in Melanoma Diagnosis
  432. Co-Optimizing Graph Sparsification and Approximate Computing for Energy-Efficient FPGA-Based GCN Inference
  433. AnchorGen: Anchored Optimization for Customizable Generative 3D Design
  434. Machine learning for journal entry testing: A type-aware evaluation of anomaly detectors under a review budget
  435. Integrating Survival-Based Aging Models with Data-Driven RUL Prognostics
  436. Mind the Drift: Diagonal Linear Networks Under Large Learning Rates
  437. ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training
  438. Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation
  439. On the Geometry of Multimodal Saturation: Riemannian VICReg
  440. Transmission Factors for Lossy Compression of PDE Training Data: Measuring What Reaches a Trained Operator
  441. Rethinking Least-Core Computation in Contextual-Distractor Games
  442. DAG-CLIP: A DAG Learning Framework in the Presence of Latent Variables
  443. Gaussian Universality and Its Breakdown in Tensor-Network Machine Learning
  444. Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?
  445. Quantum data loading from the learned shared structure of real signals
  446. Last-Iterate Convergence Rate of Normalized Gradient Descent under H"older Smoothness
  447. Vision Transformer Ensembles for Panoramic Street Segmentation
  448. Pay to Learn, Share to Earn: Incentivized Federated Multi-Player Bandits
  449. A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models
  450. Local2Mesh: Spatially Localized Contour-to-Mesh for Left Ventricular Reconstruction from Sparse 2D Cardiac MRI
  451. RocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers
  452. GO-Based Clustering for Learning Cluster-Level Causal Gene Regulatory Networks
  453. Representation Disentanglement for Fair Chest X-Ray Diagnosis
  454. Casual Flash Lighting for Gaussian Splat Inverse Rendering
  455. How well do routinely collected demographic and clinical variables aid point-of-care lung ultrasound TB classification
  456. Polynomial neural surrogates for designing photonic quantum experiments
  457. LightMTP: Lightweight Latent Multi-Token Prediction
  458. Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression
  459. Grounded Joint-Attention Other-Play for Zero-Shot Coordination
  460. Joint Precision Neural Networks: Task-Aware Dependency and Predictive Learning
  461. Scalable Minimal-Change Learning for Controllable Image Editing
  462. Patch-based Querying Identifies Structures of Interest in Electron Microscopy
  463. Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding
  464. Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce
  465. Spectral Geometry of Attention: From Information Routing to Uncertainty
  466. Learning While Scheduling Jobs under Context-Dependent Service Rates: An Anytime Rate-Optimal Algorithm
  467. Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling
  468. Label-Free Coreset Selection with Foundation Models for Efficient Annotation in Computational Pathology
  469. Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models
  470. Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation
  471. StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs
  472. Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback
  473. JLD: Perceptual Distance Through A Jacobian Lens
  474. HuatuoGPT-3: RL-Only Domain Adaptation from Base Models
  475. Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football
  476. Physics-Informed but Not Physics-Consistent: Error Geometry and Subspace Projection for Neural AC Power Flow
  477. MEND: RL For Flow Models via Proximal Velocity Matching
  478. Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery
  479. Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco
  480. OntoInk: Interactive Ontology Visualization, Validation, and Reasoning
  481. Runaway Reaction: When Benign Skills Compose into Malicious Behavior
  482. Process Constitutions and Process Stewards: Towards the Next Generation of BPM for Agentic Organizations
  483. Structural Foundations of Nonlinear Systems with Unknown Inputs: The UID-Induced Normal Form and Minimal-Sensing Structure-from-Motion
  484. Combining Improvements in Uplink AI-RAN
  485. UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance
  486. The Arbitrary-Placement Problem in Entropy-Minimizing Selection, and a Residual-Entropy Formulation
  487. Incentive Alignment in Online Experimentation
  488. Non-invasive Seizure Detection Using Wearable Wrist-worn Accelerometry and Deep Learning
  489. Prompt and Refinement: Asymmetric Mutual Learning for Infrared Small Target Detection with Noisy Labels
  490. Large Stepsizes Federated Learning on Logistic Regression with Linearly Separable Data: The Case of Heterogeneous Devices
  491. CoHyFuse: Condition-wise Hypergraph Fusion with Global Connectome in Task-fMRI
  492. MiniCorp: The Last Mile to an AI Agent Corporation
  493. Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation
  494. AstraSR: Real-World Thermal Super-Resolution with GPT-6 Astra
  495. On Hyperparameter Tuning on the Test Set
  496. End-to-End Autonomous Recursive Arborescence Deformable Flow and Non-Linear Hemodynamics for Patient-Specific Coronary Centerline Extraction
  497. LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery
  498. Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
  499. Fitting Vision Adapters at Frontier Scales
  500. TasteRoute: Personalized Routing for Video Generation
  501. Spatial Supervision Without Attribution Optimization: Improving Post-Hoc Class Activation Maps via Box-Guided Evidence Routing
  502. fMRI-TAMCL: Text-Anchored Supervised Multimodal Contrastive Learning for fMRI-Based Brain Disorder Classification
  503. Learning to Learn a Language
  504. OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies
  505. Global Communication or Graph-Specific Memory?
  506. Certification of Real Images through Calibrated Content Authentication
  507. Finite-Sample Distribution Theory and Efficient Large-Scale Inference for Online Quantile Regression
  508. CCQ: A Multi-State Child Care Quality Dataset to Support AI for Children's Health Research
  509. Curriculum Brain: Constructing Curriculum Knowledge Graphs as a Substrate for Cognitive Diagnosis
  510. On the Sequentially Semiseparable Structure of SDE-Induced Kernels and Efficient Algorithms for Kernel-Based Estimation Problems
  511. TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel
  512. The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors
  513. RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces
  514. PhaseMatcher: Autoregressive Phase-Set Identification with Spectral Decomposition
  515. AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation
  516. HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
  517. Dual-Rate Force-Image Control with Model-Based Orientation Limits for Robotic Ultrasound
  518. Adaptive-Shot Hybrid Quantum Anomaly Detection for Tactile Internet Security: Reliability-Aware Measurement Allocation Under Resource Constraints
  519. HiER-BLS: A Hierarchy-Guided and Error-Correcting Robust Incremental Broad Learning System
  520. Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
  521. Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
  522. Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation
  523. Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation
  524. Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows
  525. Feature identification for parameter extraction and defect detection using machine learning
  526. Online AutoML: Evaluating Poisoning Attacks on Cost-Utility Adversarial Training Defence Strategy for IoT Networks
  527. Image resolution enhancement for advanced semiconductor nodes
  528. DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
  529. Protocol-Sensitive Evaluation of Log Anomaly Detection: Component Costs and Target-Access Sensitivity on HDFS and BGL
  530. Gauss-Map Variation for Image Denoising: Geometric Analysis and an Anderson--Accelerated Majorization--Minimization Method
  531. Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
  532. FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models
  533. Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization
  534. CLARA: Can AI Assess Developmental Appropriateness in Children's Stories?
  535. Isotropic Gaussian Processes Improve Vanilla Bayesian Optimization in High Dimensions
  536. A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos
  537. Mining Agent Skills from Production Traces
  538. InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems
  539. AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill
  540. Controllable Road Marking Generation
  541. Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation
  542. Global error estimators for parametric monotone nonlinearities and neural approximations
  543. A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction
  544. Vision-enabled detection of safety helmet compliance in construction zones
  545. A new design of a fall detection system integrating landmark identification and deep learning techniques
  546. Robust Local Optimization Done Right
  547. T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations
  548. FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
  549. Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
  550. ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection
  551. Retrieval-Based In-Context Learning: A Domain Adaptation Framework
  552. From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model
  553. Second-Order Problem Solving for Recursive Self-Improvement in Formal Verification
  554. Voltic: Distinguishing Volatility from Stochasticity in Recurrent Memory
  555. Planetary Geospatial Foundation Models: A New Paradigm for Global Public Health
  556. From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity
  557. Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts
  558. Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems
  559. Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness
  560. Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability
  561. Two-Sample Testing via Path-based Inference
  562. RESOLVE: Language-Agnostic Validation of GPU Kernels Through Testing, Reduction, and Proof
  563. Knowing the Rules, Applying the Rules: Evaluating Language Models on Traditional Chinese Bazi
  564. Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions
  565. Sharp Integrality Gaps in Calibration Distance
  566. An evolutionary origin of collective decision making in humans and machines
  567. Bayesian Data Augmentation for DNN Retraining with Binomial Outcomes in Vision-Based UAV Landing
  568. How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation
  569. Bellman-Centric Learning: Near-Optimal Regret for Linear Bandits with Memory
  570. Graph Data Augmentation via Contrastive Generator Inversion (textttDCBA)
  571. Training and Scaling Compute-Optimal Physiological Waveform Foundation Models
  572. Transformer-Based Time-Series Inference of Lindblad Dynamics in Open Quantum Systems
  573. When Does a Diffusion Model Decide What to Draw ?