mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 1 Jun 2026

631 papers

  1. DS-Lighting: Making Agent Harnesses Explicit for Data-Science AutomationLLM agents and tool use → Web, search, and research agents
  2. Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention MatchingLLM reasoning → Test-time compute and efficient thinking +1
  3. Reliability-Aware Sexism Detection: Combining DPO with Annotator Agreement and Token-Level Confidence ScoringLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  4. AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom MeasurementSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  5. Execution-Grounded Security Testing for Coding Agents in Software Engineering PipelinesLLM agents and tool use → Agent threats, guardrails and governance +1
  6. From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text GenerationMechanistic interpretability → Activation steering methods
  7. Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers OptimizationLLM reasoning → Reasoning for agents, planning and code +3
  8. Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative ProfilesLLM agents and tool use → Agent memory systems
  9. PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  10. The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented AgentsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  11. FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric UncertaintyMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  12. SPACE: Source-free Proxy Anchor Concept Erasure for MLLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  13. Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  14. Alignment Collapse Under KV Cache Quantization: Diagnosis and MitigationEfficient LLM inference and serving → KV cache quantization
  15. From Confident Closing to Silent Failure: Characterizing False Success in LLM AgentsLLM agents and tool use → Software engineering coding agents
  16. AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  17. Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. No Free Lunch for Synthetic Images under Data Scarcity ConditionsDiffusion models → Robustness, privacy and adversarial aspects
  19. Position: Deployed Reinforcement Learning should be ContinualDeep reinforcement learning methods → Deep RL algorithms and representations
  20. MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language ModelsLLM safety and security → Jailbreaking
  21. Designing for Doubt: The Case for Informed Abstention in Autonomous AgentsLLM agents and tool use → Agent threats, guardrails and governance
  22. Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model ServingEfficient LLM inference and serving → KV cache optimization
  23. Gate AI: LLM Security Benchmark Evaluation Methodology and ResultsLLM safety and security → Jailbreaking
  24. The Road Ahead in Autonomous Driving: The KITScenes Multimodal DatasetEnd-to-end autonomous driving → End-to-end system architecture
  25. SCOPE: Real-Time Natural Language Camera Agent at the EdgeLLM agents and tool use → Multimodal and embodied agents
  26. BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  27. Fast Unlearning at Scale via Margin Self-CorrectionLLM safety and security → Machine unlearning
  28. WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing AgentsLLM agents and tool use → Agent skill learning and evolution
  29. Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden StatesLLM reasoning → Reasoning benchmarks and evaluation +1
  30. Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence ReviewDeep reinforcement learning methods → RL for energy, networks and operations
  31. Are we really tilting? The mechanics of reward guidance in flow and diffusion modelsDiffusion models → Diffusion and flow policies for robotics +1
  32. Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted TasksLLM agents and tool use → Software engineering coding agents
  33. Adaptive Latent Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  34. The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based modelsLLM agents and tool use → Social simulation and multi-agent debate
  35. When Helping Hurts and How to Fix It: Multi-Agent Debate for Data CleaningLLM agents and tool use → Social simulation and multi-agent debate
  36. Toward a Modular Architecture for Embedded AI Agent Systems at the EdgeLLM agents and tool use → General LLM agent frameworks and benchmarks
  37. Spectral-Progressive Thought Flow for Lightweight Multimodal ReasoningLLM reasoning → Spatial and embodied reasoning
  38. Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  39. Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM InferenceEfficient LLM inference and serving → KV cache quantization
  40. Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early DetectionLLM agents and tool use → Medical and scientific domain agents +1
  41. Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical ImagingMultimodal LLMs / vision-language models → Medical vision-language models
  42. ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical ReasoningLLM reasoning → Clinical and biomedical applications
  43. Cosmos 3: Omnimodal World Models for Physical AIWorld models → Video-generation world models and simulators
  44. AURA: Action-Gated Memory for Robot Policies at Constant VRAMEfficient LLM inference and serving → Visual token pruning in multimodal models
  45. GeoDrive-Bench: Benchmarking Region-Specific Multimodal Reasoning in Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  46. MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video DataWorld models → Video-generation world models and simulators
  47. SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration VideosVision-language-action models → Human-video and latent-action pretraining
  48. Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  49. See Less, Specify More: Visual Evidence Budgets for Generalizable VLAsVision-language-action models → VLA architectures and generalization
  50. Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  51. Post-Boundary Bridge: Must Local Attention Go Global Between Global Layers?Efficient LLM inference and serving → KV cache optimization
  52. Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security ReasoningLLM agents and tool use → Agent threats, guardrails and governance
  53. Visual Graph Scaffolds for Structural Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  54. Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation NowcastingDiffusion models → Flow matching, time series and science
  55. Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  56. Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward ModelingLLM reasoning → Multimodal reasoning +2
  57. RoboDream: Compositional World Models for Scalable Robot Data SynthesisWorld models → Embodied and robot world models
  58. ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  59. From Zero to Hero: Training-Free Custom Concept Spawning in World ModelsWorld models → Video-generation world models and simulators
  60. ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for AgentsLLM agents and tool use → Medical and scientific domain agents
  61. VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time OptimizationLLM reasoning → Multimodal reasoning
  62. From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM CompressionLLM reasoning → Test-time compute and efficient thinking +1
  63. LongLive-RAG: A General Retrieval-Augmented Framework for Long Video GenerationRetrieval-augmented generation → Multimodal RAG +1
  64. SimSD: Simple Speculative Decoding in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  65. SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated ConstructionLLM agents and tool use → Agent threats, guardrails and governance
  66. LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative ModelsLLM reasoning → Multimodal reasoning
  67. Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion AugmentationDiffusion models → Flow matching, time series and science
  68. SafeSteer: Localized On-Policy Distillation for Efficient Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  69. Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual EventsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  70. Drifting Preference Optimization for One-Step Generative ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  71. CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  72. Bridging the Last Mile of Time Series Forecasting with LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  73. Monitoring Agentic Systems Before They're ReliableLLM agents and tool use → Software engineering coding agents
  74. Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA ManipulationWorld models → Embodied and robot world models +1
  75. Iteris: Agentic Research Loops for Computational MathematicsLLM agents and tool use → Educational agents and math problem solving
  76. Ghost Tool Calls: Issue-Time Privacy for Speculative Agent ToolsLLM agents and tool use → Agent threats, guardrails and governance
  77. MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment SimulationLLM agents and tool use → Tool learning and function calling
  78. Learning When to Translate for Multilingual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  79. Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +2
  80. Beyond One-shot: AI Agents for Learning in Field ExperimentsLLM agents and tool use → Medical and scientific domain agents
  81. Geometry-Aware Implicit Memory for Video World ModelsWorld models → Video-generation world models and simulators
  82. ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  83. NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp GenerationDiffusion models → Diffusion and flow policies for robotics
  84. GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial TranscriptomicsMixture-of-experts → Medical and biomedical MoE
  85. Investigating and Alleviating Harm Amplification in LLM InteractionsLLM safety and security → Safety alignment, refusal and guardrails
  86. K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean ContextsLLM agents and tool use → Web, search, and research agents
  87. A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RLLLM reasoning → Reinforcement learning for reasoning
  88. Policy and World Modeling Co-Training for Language AgentsWorld models → World models for language agents +1
  89. AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence DesignLLM reasoning → Clinical and biomedical applications +1
  90. How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE RepresentationsMechanistic interpretability → Sparse autoencoder training and evaluation
  91. SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action DivergenceLLM agents and tool use → Agent threats, guardrails and governance
  92. When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitecturesMixture-of-experts → MoE large language models +1
  93. Harness-1: Reinforcement Learning for Search Agents with State-Externalizing HarnessesDeep reinforcement learning methods → RL training of language and agent models
  94. CoMAP: Co-Evolving World Models and Agent Policies for LLM AgentsWorld models → World models for language agents +1
  95. MOC: Multi-Order Communication in LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  96. SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent TrainingLLM agents and tool use → Agent skill learning and evolution
  97. Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior UpdatesDiffusion models → Inverse problems and image restoration
  98. Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM ReasoningLLM reasoning → Multimodal reasoning +1
  99. TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report GenerationLLM agents and tool use → Web, search, and research agents
  100. Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPOLLM reasoning → Reinforcement learning for reasoning
All 631
  1. Deep Learning for Remote Sensing to Improve Flood Inundation MappingDiffusion models → Inverse problems and image restoration
  2. FATE-VLA:Failue-aware test generation for vision-language-action modelsVision-language-action models → Failure recovery and robustness
  3. Unified Context Evolution for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial ImageryKnowledge distillation → Detection and dense prediction distillation
  5. SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous AgentsLLM agents and tool use → Agent threats, guardrails and governance
  6. POIROT: Interrogating Agents for Failure Detection in Multi-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
  7. Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy AdaptationDeep reinforcement learning methods → Deep RL algorithms and representations
  8. RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  9. Cross-modal linkage risk in clinical vision-language modelsMultimodal LLMs / vision-language models → Medical vision-language models
  10. Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  11. Vision-language Models for Driver Monitoring Systems: A Driver Activity Description DatasetMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  12. Geometric Latent Reasoning Induces Shorter Generations in LLMsLLM reasoning → Test-time compute and efficient thinking
  13. When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  14. BlockGen: Flexible Blockwise Sequence Modeling with Hybrid SamplersDiffusion models → Discrete and text diffusion
  15. AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS IntegrationsLLM agents and tool use → Agent threats, guardrails and governance +1
  16. Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step DistillationDiffusion models → Diffusion foundations and sampling
  17. Faster Synchronous On-Policy RL via Straggler-Aware Group SizingLLM reasoning → Reinforcement learning for reasoning
  18. Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community NotesLLM agents and tool use → Medical and scientific domain agents +1
  19. Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  20. Coherent Off-Policy Improvement of Large Behavior Models with Learned RewardsOffline RL and imitation learning from data → Real-world robot offline RL +1
  21. On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow MatchingDiffusion models → Flow matching, time series and science
  22. Low-Pass Flow MatchingDiffusion models → Flow matching, time series and science
  23. InfoMerge: Information-aware Token Compression for Efficient Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  24. Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking From Sparse Inertial Sensors and Ranging-Based Between-Sensor DistancesDiffusion models → 3D, point cloud and scene generation
  25. Variational Learning for Insertion-based GenerationDiffusion models → Discrete and text diffusion
  26. Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  27. How Hard Can It Be? Hardness-Aware Multi-Objective UnlearningLLM safety and security → Machine unlearning
  28. Error Bounds for a Diffusion Model-Based Drift EstimatorDiffusion models → Diffusion foundations and sampling
  29. A Primer in Post-Training Reasoning Data: What We Know About How It WorksLLM reasoning → Reinforcement learning for reasoning
  30. Jailbreaking Multimodal Large Language Models using Multi-Clip VideoMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  31. BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  32. Multimodal Action Diffusion for Robust End-to-End Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  33. DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  34. FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image GenerationDiffusion models → Image generation, text-to-image and editing
  35. Agentic-J: An AI Agent for Biological Microscopy Image AnalysisLLM agents and tool use → Medical and scientific domain agents
  36. Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric DesignMechanistic interpretability → Sparse autoencoder training and evaluation
  37. Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent TrajectoriesLLM agents and tool use → Web, search, and research agents
  38. eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory CorrosionLLM reasoning → Prompting and chain-of-thought reasoning
  39. Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in BuildingsDeep reinforcement learning methods → RL for energy, networks and operations
  40. Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA BanksDiffusion models → Flow matching, time series and science
  41. SentGuard: Sentence-Level Streaming Guardrails for Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  42. OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web AgentsLLM agents and tool use → Web, search, and research agents +1
  43. Unveiling the Entropy Dynamics of Chain-of-Thought ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  44. Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted RecoveryLLM reasoning → Test-time compute and efficient thinking
  45. PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph DrawingLLM reasoning → Spatial and embodied reasoning
  46. An Agentic Approach Towards Replication Package Quality EvaluationLLM agents and tool use → Software engineering coding agents
  47. Scaling Agentic Capabilities via Grounded Interaction SynthesisLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh TokenizationDiffusion models → Video generation
  49. CARTE: A Benchmark for Mapping Language Model Knowledge Across FranceLLM reasoning → Reasoning benchmarks and evaluation
  50. MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?LLM agents and tool use → Agent skill learning and evolution +1
  51. SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  52. MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow MatchingDiffusion models → Image generation, text-to-image and editing +1
  53. AutoMedBench: Towards Medical AutoResearch with Agentic AI ModelsLLM agents and tool use → Medical and scientific domain agents
  54. WALL-WM: Carving World Action Modeling at the Event JointsWorld models → Embodied and robot world models
  55. Randomized Least Squares Value Iteration itself is Joint Differentially PrivateDeep reinforcement learning methods → RL for energy, networks and operations
  56. Co-training with Ego-centric Video and Demonstration for Robot Navigation TaskVision-language-action models → Human-video and latent-action pretraining
  57. Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid ObjectsWorld models → Embodied and robot world models
  58. Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and PlanningWorld models → World models for autonomous driving +1
  59. HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought CompressionLLM reasoning → Test-time compute and efficient thinking +1
  60. 3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph RetrievalLLM agents and tool use → Multimodal and embodied agents
  61. QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANsLLM reasoning → Reasoning for agents, planning and code +1
  62. Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +2
  63. SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart HomesLLM reasoning → Spatial and embodied reasoning +1
  64. The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal DialogueMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  65. Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular ObservationsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  66. Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  67. CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  68. Task-Induced Representational Invariances Depend on Learning Objective in Deep RLDeep reinforcement learning methods → Deep RL algorithms and representations
  69. Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through CorrectionsDiffusion models → Diffusion and flow policies for robotics
  70. RadioMaster: Multi-Agent System for Autonomous Radio Signal GenerationLLM agents and tool use → Agentic AI for wireless networks
  71. A Theoretical Framework for Self-Play Theorem Proving AlgorithmsSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  72. The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent SpaceVision-language-action models → 3D and spatial-aware VLA
  73. Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic ServingLLM agents and tool use → Software engineering coding agents
  74. LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  75. Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic RecompositionLLM safety and security → Vision-language and text-to-image safety
  76. CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged FeedbackLLM agents and tool use → Web, search, and research agents
  77. Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent ConsensusLLM agents and tool use → General LLM agent frameworks and benchmarks
  78. Hierarchically Decoupled Mixture-of-Experts for Robust Traffic Sign Recognition in Complex Driving ScenariosMixture-of-experts → MoE in reinforcement learning and robotics
  79. CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User SimulationLLM agents and tool use → Social simulation and multi-agent debate
  80. Cost-Aware Diffusion Draft Trees for Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  81. Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied ReasonersLLM reasoning → Spatial and embodied reasoning
  82. OctoT2I: A Self-Evolving Agentic Text-to-Image RouterLLM agents and tool use → Multimodal and embodied agents
  83. STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  84. PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological MapsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  85. MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI ReconstructionMixture-of-experts → Medical and biomedical MoE
  86. HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent SystemsLLM agents and tool use → Software engineering coding agents
  87. Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task StreamsLLM agents and tool use → Software engineering coding agents +1
  88. EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  89. TriAlign: Towards Universal Truth Consistency in Personalized LLM AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  90. THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language ModelsLLM safety and security → Jailbreaking
  91. TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability DeterminationRetrieval-augmented generation → Legal and financial RAG
  92. Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven SimulationLLM agents and tool use → General LLM agent frameworks and benchmarks
  93. Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  94. Density-Aware Translation of Spurious Correlations in Zero-Shot VLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  95. CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language ModelsMechanistic interpretability → Steering and probing for LLM safety
  96. Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  97. Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim VerificationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  98. RDA: Reward Design Agent for Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  99. When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language ModelsMixture-of-experts → Multimodal MoE models
  100. ATLAS: Agentic Test-time Learning-to-Allocate ScalingLLM reasoning → Reasoning for agents, planning and code +1
  101. DOT-MoE: Differentiable Optimal Transport for MoEficationMixture-of-experts → MoE large language models
  102. Quantifying the Energy Floor: Direct Measurement and Replay Buffer Bias in SAC-Based HVAC Control on sbsimDeep reinforcement learning methods → RL for energy, networks and operations
  103. CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  104. Self-Regulating Annealing in Heavy-Tailed Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  105. MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility GenerationLLM agents and tool use → Multimodal and embodied agents +1
  106. Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity DecompositionLLM reasoning → Reinforcement learning for reasoning
  107. IMWM: Intuition Models Complement World Models for Latent PlanningWorld models → Latent predictive world models
  108. What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  109. Goal2Pixel: Grounding Goals to Pixels for Vision-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  110. Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEsDiffusion models → Audio, speech and music
  111. ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RLLLM agents and tool use → Agent skill learning and evolution
  112. TechRAG: Evidence-Gated Multimodal Agentic RAG for Technical Literature ReasoningLLM reasoning → Multimodal reasoning +2
  113. Self-Improving Small Object Grounding in LVLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  114. Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image CompressionDiffusion models → Diffusion for compression and wireless
  115. FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning EnvironmentKnowledge distillation → Federated, robust and private distillation
  116. RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic ManipulationWorld models → Embodied and robot world models
  117. TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RLLLM reasoning → Multimodal reasoning
  118. TLG: Temporal-Logic Grounding for Video Question Answering via Source-Annotation Reconstruction and Category-Targeted ReasoningLLM reasoning → Multimodal reasoning
  119. Effective Multi-sensor Conditioning for Street-view Novel-view SynthesisDiffusion models → Diffusion and flow policies for robotics
  120. Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring AgentsLLM agents and tool use → Social simulation and multi-agent debate
  121. Agent System Operations: Categorization, Challenges, and Future DirectionsLLM reasoning → Reasoning for agents, planning and code +1
  122. Defenses & Enablers For Skill Injection Attacks on Terminal Based AgentsLLM agents and tool use → Agent threats, guardrails and governance
  123. Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning
  124. MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  125. S-SPPO: Semantic-Calibrated Self-Play Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  126. Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning +1
  127. RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing AgentsLLM agents and tool use → Social simulation and multi-agent debate
  128. ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud SegmentationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  129. Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality AuditRetrieval-augmented generation → Multimodal RAG
  130. MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical DynamicsDiffusion models → Video generation
  131. Multi-Agent Computer UseLLM agents and tool use → GUI and mobile agents
  132. Joint Agent Memory and Exploration Learning via Novelty SignalsLLM agents and tool use → Agent memory systems
  133. Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex LossesLLM safety and security → Machine unlearning
  134. Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute DefenseLLM safety and security → Safety alignment, refusal and guardrails
  135. ProbMoE: Differentiable Probabilistic Routing for Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  136. Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating SystemsLLM agents and tool use → Software engineering coding agents
  137. Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees
  138. PragyaDoc: A Universal Document Intelligence Framework for Multilingual Medical Document Understanding in Low-Resource Settings
  139. "YES! YES! I absolutely love this insight!" Affirmative Narration as Interactional Strategy in Dialogues with LLM Chatbots
  140. Reference Feature Atlases for Mechanistic Auditing of Language Models
  141. Tractable Hierarchical Control of Autoregressive Language Models
  142. LLMs as Teaching Assistants for Mathematics Exam Grading: Reliability, and Practical Usability
  143. Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints
  144. Graph Instance Landscapes: When Structural Similarity Does (Not) Reflect Shortest-Path Performance
  145. Machine Learning-Driven Chemical Reactor Network Modeling of the Sandia-D Flame
  146. FairGen: Preference-Aligned Diffusion for Demographically Equitable Medical Image Synthesis
  147. QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
  148. EstRTL: Functional Estimation Guided RTL Code Generation
  149. LLM-as-a-Discriminator: When Synthetic Tables Still Look Real
  150. Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View
  151. MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
  152. Anchor-Conditioned Compositional Control for Landscape Image Generation
  153. Unpredictable Safety: Domain-Dependent Compliance and the Transparency Gap in Open-Weight LLMs
  154. Gradient-based optimization of nuclear criticality experiments using neural surrogate eigenvalue sensitivities
  155. Do Transformers Need Three Projections? Systematic Study of QKV Variants
  156. Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent
  157. Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning
  158. The Biomimetic Architecture of Software 4.0
  159. CodegenBench: Can LLMs Write Efficient Code Across Architectures?
  160. Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks
  161. SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggability
  162. Gravity-Aware Hierarchical Routing for Lightweight SensorLLM on Human Activity Recognition
  163. KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators
  164. Hand Trajectory Fusion for Egocentric Natural Language Query Grounding
  165. Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries
  166. Fast-dLLM++: Fr'echet Profile Decoding for Faster Diffusion LLM Inference
  167. Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
  168. From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
  169. Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessment
  170. ERP-XTTN: Interpretable Prototype-Guided Cross-Attention for Cross-Subject ERP Classification
  171. BEAST3D: Animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
  172. Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning
  173. CAD-to-CT Registration of Cylindrical Objects via Ellipse-Based Axis Estimation
  174. SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks
  175. ATLAS: A Large-Scale Evaluation Benchmark for Adversarial LiDAR Perception
  176. Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
  177. Any2Poster: Any-Source Poster Generation Across Modalities and Domains
  178. Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models
  179. Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
  180. The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction
  181. Scalable Derivative Gaussian Processes via Exact Gradient Reduction
  182. Depth from Dual Differential Defocus and Stereo Consensus
  183. Tiny Collaborative Inference for Occlusion-Robust Object Detection
  184. Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction
  185. A Nonmonotone Gradient-Based Algorithm for Symmetric Nonnegative Matrix Factorization and Graph Clustering
  186. Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels
  187. LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
  188. Pathway-Structured Privileged Distillation for Deployable Computational Pathology
  189. RRISE: Robust Radius Inference via a Surrogate Estimator
  190. Neural Posterior Estimation for Stochastic Epidemic Models Using Final Outcome Data
  191. Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems
  192. Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys
  193. Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
  194. GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning
  195. RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
  196. A Systematic Evaluation of Current Architectures in Wind Power Forecasting
  197. Learning Coherent Representations: A Topological Approach to Interpretability
  198. Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling
  199. Large Byte Model: Teaching Language Models About Compiled Code
  200. An Exploration of Collision-based Enemy Morphology Generation
  201. Principled Reflection Separation via Nonlinear Superposition and Feature Interaction
  202. Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing
  203. Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing
  204. Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors
  205. Translating Classical Poetry into Modern Prose
  206. BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
  207. Recovering Direct Price Effects of Environmental Amenities in Housing Markets: Regression and Causal Machine Learning Model Assessment with Empirical Monte Carlo Simulation
  208. Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins
  209. Diagnosis of Human Object Interaction Detectors for Real World Educational Applications
  210. Neutrino Fingerprints: Image-Based Encodings of IceCube Events for CNN Direction Reconstruction
  211. QUIVER: Quantum-Informed Views for Enhanced Representations in Large ML Models
  212. CRAM-ER: Error-Resilient Spintronic Computational Random Access Memory for Scalable In-Memory Computation
  213. Do Value Vectors in Deep Layers Need Context from the Residual Stream?
  214. One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL
  215. Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
  216. Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification
  217. Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models
  218. From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry
  219. Binary Road Surface Classification Using Machine Learning on Production Vehicle Signals During Cruising
  220. Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
  221. Acceptance-Test-Driven Evaluation Protocols for Business-Centric LLM Systems
  222. Psi-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues
  223. On the Persistent Effects of Lexicality in Large Language Models
  224. Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records
  225. Greener Than Humans? Environmental Attitudes in Large Language Models
  226. ScoreStop: Gradient-based early stopping using functional score tests
  227. EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
  228. Attention Calibration for Position-Fair Dense Retrieval
  229. AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes
  230. Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
  231. Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis
  232. Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate
  233. State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation
  234. AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
  235. Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
  236. CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning
  237. Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift
  238. Coherent Swap Regret and Channel-Proof Learning
  239. HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
  240. VISReg: Variance-Invariance-Sketching Regularization for JEPA training
  241. AdaCodec: A Predictive Visual Code for Video MLLMs
  242. Policy-based Foveated Imaging and Perception
  243. IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
  244. Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics
  245. HERO'S JOURNEY: Testing Complex Rule Induction with Text Games
  246. Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
  247. AFUN: Towards an Affordance Foundation Model for Functionality Understanding
  248. SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation
  249. Transferable Self-Harm Surveillance from Emergency Department Triage Notes Using an Evidence-Augmented Machine Learning Approach
  250. Tracking the Behavioral Trajectories of Adapting Agents
  251. Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation
  252. Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
  253. FigSIM: A Dataset for Fine-grained Suicide Severity and Figurative Language in Suicide Memes
  254. ToolFG: Towards Well-Grounded Fine-Grained Image Classification
  255. A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
  256. Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis
  257. When Rating Scales Fall Short: LLM-Assisted Discovery of ADHD Signals in Turkish Teacher Narratives
  258. Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
  259. Question-Aware Evidence Ledgers for Video Relational Reasoning
  260. GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
  261. Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims
  262. MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
  263. Expressivity of congruence-based architectures for DNNs on positive-definite matrices
  264. RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering
  265. Towards Multidisciplinary Summarization of Hospital Stays: Efficient Sentence-Level Clinical Provenance Categorization
  266. X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
  267. Places in the Wild: A Large, High-Resolution RAW Photograph Dataset for Ecologically Valid Vision Research
  268. Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
  269. Physics-Informed Residuals for Adaptive Mesh Refinement in Finite-Difference PDE Solvers
  270. MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence
  271. AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
  272. Speculative Sampling For Faster Molecular Dynamics
  273. Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
  274. Reason-Then-Retrieve for CoVR-R with Structured Edit Prompts and Dense-Sparse Fusion
  275. HLL: Can Agents Cross Humanity's Last Line of Verification?
  276. Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback
  277. PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
  278. Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
  279. LLM-Evolved Pattern Generators for Optimal Classical Planning
  280. On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
  281. Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
  282. Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
  283. Spectral Audit of In-Context Operator Networks
  284. Evolutionary Discovery of Bivariate Bicycle Codes with LLM-Guided Search
  285. Edge Prediction for Roof Wireframe Reconstruction with Transformers
  286. AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis
  287. Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
  288. TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
  289. A Mathematical Conflict Framework for Contextual Data Modulation
  290. Honey, I Shrunk the Arc de Triomphe!
  291. WAXAL-NET: Finetuned Edge ASR Across 19 African Languages
  292. Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models
  293. PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation
  294. FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
  295. Minimax-Optimal Policy Regret in Partially Observable Markov Games
  296. Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
  297. Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection
  298. Local Preferential Bayesian Optimization
  299. TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
  300. VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning
  301. Doing well with less! On Sampling Techniques for Empirical Pairwise Loss Estimation/Minimization
  302. Detecting Pen-In-Air States from Video: A Proof-of-Concept Toward Complementary Handwriting Analysis
  303. Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification
  304. Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
  305. Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
  306. Forget Attention: Importance-Aware Attention Is All You Need
  307. Riemannian Gradient Descent for Low-Rank Architectures
  308. Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions
  309. Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
  310. Measurement Geometry and Design for Trustworthy Generative Inverse Problems
  311. Quantitative Movement Testing: Measuring Chronic Pain Patient Movements from a Single Smartphone Video
  312. Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
  313. Regularized Large Neighborhood Search
  314. AI as a Tool for Simulation-Based Experiments in Literary Studies
  315. Neural Acquisition & Representation of Subsurface Scattering
  316. DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations
  317. Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization
  318. CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation
  319. Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
  320. From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
  321. A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
  322. ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems
  323. Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025
  324. CEON: Circular Economy Ontology Network
  325. ResMerge: Residual-based Spectral Merging of Large Language Models
  326. FW-NKF: Frequency-Weighted Neural Kalman Filters
  327. ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
  328. Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification
  329. A Doeblin-Anchored Contrastive Chart for Learning Markov Transition Kernels
  330. Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families
  331. Bayesian meta-learning for modeling Alzheimer's disease progression
  332. Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images
  333. Network Learning with Semi-relaxed Gromov-Wasserstein
  334. CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
  335. Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution
  336. Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark
  337. Consistency Training while Mitigating Obfuscation via Rate Matching
  338. Model Multiplicity and Predictive Arbitrariness in Recidivism Risk Assessment
  339. The Ghost Couple: Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing
  340. Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization
  341. Closing the Alignment-Maturity Gap in Federated Prototype Learning
  342. InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark
  343. CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning
  344. Disentanglement-Based Equivariant Learning for Compositional VQA
  345. From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generation
  346. EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction
  347. An Abstract Worlds Semantic Framework for Belief Change Operators
  348. Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis
  349. On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
  350. Predicting the risk of colorectal anastomotic leak based on preoperative mapping of the blood supply of the bowel
  351. S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty
  352. Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
  353. Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics
  354. TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version
  355. VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
  356. Edge-aware Decoding for Neural Asymmetric Routing
  357. Rethinking Evaluation Paradigms in IBP-based Certified Training
  358. Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization
  359. Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
  360. ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting
  361. Network Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters
  362. When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes
  363. It does what it says on the tin: safe synthetic data from coarsened margins
  364. PortBERT: Navigating the Depths of Portuguese Language Models
  365. WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos
  366. The Role of Ambiguity in Error Prediction via Uncertainty Quantification
  367. LALE: Lightweight-Transformer Architecture for Land-Cover Estimation
  368. Decision-calibrated prediction sets for robust power system operations
  369. FACT: A Simple and Efficient Framework for Active Finetuning
  370. Beyond ℓ2-norm and ℓ_∞-norm: A Curvature-Inspired ℓp-Norm Scheme for Deep Neural Networks
  371. Planar Symmetric Pattern Generation
  372. Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image
  373. TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
  374. Query-Limited Community Recovery in Stochastic Block Models
  375. Topological texture analysis of microscopy images of dynamic casein gelation and its relation to rheological properties
  376. Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
  377. Quantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies
  378. Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning
  379. Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints
  380. RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network
  381. World-Task Factorization for Robot Learning
  382. Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
  383. PerBite: A Curated Diagnostic Workflow for Bite-Aware Food Volume Estimation
  384. PliableBVS: A flexible Bayesian variable selection method for modeling interactions with mandatory modifying variables
  385. Evaluating Real-World Generalizability of Algorithm Selection Models
  386. Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French
  387. Provable Data Scaling Law for Meta Learning via Complexity Minimization
  388. Machine Learning for Coding Retail Product Names to Consumer-Price Categories: A Rule-plus-Bag-of-Words Pipeline with Reliability-Weighted Human-in-the-Loop Labeling
  389. Parameter-Efficient Adaptation of a Multi-Stream Vision-Language Framework for Blind Image Quality Assessment
  390. Why Do Time Series Models Need Long Context Windows?
  391. A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
  392. Graph Edit Distance Formulation for the Vehicle Routing Problem: Theory and Analysis
  393. An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification
  394. Generalization Limits in Vehicle Re-Identification
  395. Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
  396. A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
  397. Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
  398. Eyettention II: A Dual-Sequence Architecture for Modeling Fixation Location, Within-Word Landing Position, and Fixation Duration in Reading
  399. Contrastive Augmented Transformer with Domain-specific Enhancement for Robust Multi-scenario Metal Surface Defect Detection
  400. Flow-Transformed Implicit Processes for Function-Space Variational Inference
  401. Rank-Constrained Deep Matrix Completion for Group Recommendation
  402. Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
  403. Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization
  404. SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation
  405. SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video
  406. What to Format and How: A Benchmark and Workflow Approach for Document Formatting
  407. VET: A Framework for Analyzing AI Discourse
  408. Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
  409. Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
  410. Pool-Select-Refine for Allocation-Aware Generative Dataset Distillation
  411. Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
  412. Single-Line Drawing Generation via Semantics-Driven Optimization
  413. Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space
  414. Private and Stable Test-Time Adaptation with Differential Privacy
  415. Bayesian Spectral Emotion Transition Discovery from Multi-Annotator Disagreement
  416. KliniskVestBERT: BERT Model Specialised to Norwegian Clinical Texts
  417. Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
  418. RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models
  419. Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
  420. Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
  421. Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations
  422. Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
  423. MidSurfNet: Learning Face Pairing for Mid-surface Abstraction of Thin-walled CAD Models
  424. Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
  425. Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
  426. EVA-Net: Subject-Independent EEG Motor Decoding with Video-Derived Motor Priors
  427. Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognition
  428. G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
  429. Deep Learning for Generating Computational PIN-4 Immunohistochemistry Staining from Prostate Biopsy H&E Images
  430. WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis
  431. Continual Learning as a Multiphase Moving-Boundary Problem
  432. Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
  433. Boosting Multimodal Federated Learning via Chained Modality Optimization
  434. Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
  435. ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
  436. RescueBench: Can Embodied Agents Save Lives in the Wild ?
  437. Mos-Gen: A Generative Molecular Framework for Mosquito Insecticide Design
  438. Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
  439. Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
  440. Evaluation of Baseline Methods for IDD-based SSD External Memory Search
  441. Physics-Guided Attention in a Lightweight TCN for Efficient WiFi CSI-Based Human Activity Recognition
  442. Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
  443. Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
  444. ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
  445. TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech
  446. Hist2Style: Histogram-Guided Stylization with Bilateral Grids
  447. Unsupervised Collaborative Domain Adaptation for Driving Scene Parsing
  448. Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
  449. "I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
  450. Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI for Cardiac Digital Twins
  451. ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
  452. MOSS-Audio Technical Report
  453. Multilinguality of Large Language Models From a Structural Perspective
  454. Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
  455. Consistency evaluation of benchmarks used for causal discovery
  456. Stochastic convergence of parallel asynchronous adaptive first-order methods
  457. Breaking the Information Silo: Semantic Personas for Cross-Domain Recommendation
  458. Structure-Guided Adaptive Propagation for Protein-Protein Interaction Site Prediction
  459. FLARE: Diffusion for Hybrid Language Model
  460. EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks
  461. An Algebraic View of the Expressivity of Recurrent Language Models
  462. Accelerating Min-Max Optimization via Power-Law Stepsizes
  463. PillarDETR: YOLO-Backbone and RT-DETR Head for Real-Time 3D Object Detection
  464. Quality-Guided Semi-Supervised Learning for Medical Image Segmentation
  465. Construction of Historical Knowledge Graphs Based on BERT and Graph Neural Networks
  466. Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness
  467. SECUREVENT: Hybrid AI/ML Security Monitoring for Distributed Event-Based Systems
  468. Argument Collapse: LLMs Flatten Long-Form Public Debate
  469. FlatVPR: Plug-and-play Geo-linear Residual Adapter for Geometric Rectification of Foundation Model Feature Manifolds
  470. Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization
  471. Shortcut to Nowhere: Demystifying Deep Spurious Regression
  472. Post-Deterministic Distributed Systems: A New Foundation for Trustworthy Autonomous Infrastructure
  473. A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling
  474. Fair Finetuning Mitigates Distribution Inference Attacks
  475. Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
  476. Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
  477. JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions
  478. KDH-CAD: Knowledge-data hybrid CAD learning under data scarcity
  479. Spatio-Temporal Correlation Guided Geometric Partitioning for Versatile Video Coding
  480. MixerSENet: A Lightweight Framework for Efficient Hyperspectral Image Classification
  481. Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model
  482. RCEM: Robust Conversational Search EMbedder in Distributional Shift
  483. Understanding Identity Continuity in Thermal Video through Scene-Level Consistency
  484. IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems
  485. RPCASSM: Robust PCA State Space Model For Infrared Small Target Detection
  486. HAIM: Human-AI Music Datasets for AI Music Production Tracking Benchmark
  487. Don't Let a Few Network Failures Slow the Entire AllReduce
  488. Why Do Self-Harm Prediction Models Struggle to Generalise? Lexical and Semantic Variations in Emergency Department Triage Notes
  489. Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
  490. Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
  491. Data-Automated Policy Learning for Nonlinear Welfare
  492. MINTS: Minimalist Thompson Sampling
  493. Physics-Aware Linearized ADMM and Its Unrolling
  494. Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
  495. PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
  496. Conditional Collapse in Sign Language Production: A Diagnostic and a Scaling Argument
  497. Edge-directed geometric partitioning for versatile video coding
  498. CanonCGT: Reference-Based Color Grading via Canonical Pivot Representation
  499. Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
  500. AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
  501. E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
  502. A Framework for Graph-Conditioned Hierarchical Shapley Attribution in Patent Valuation
  503. Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
  504. Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
  505. EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
  506. Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval
  507. Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
  508. Paving the Way for Point Cloud Video Representation Learning Using A PDE Model
  509. Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks
  510. EIVE: End-to-End Instance-Specific Visual Explanations for Detection Transformers
  511. Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
  512. Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation
  513. Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises
  514. FLAME: Physics-Guided Neural Operators for Onboard Satellite Methane Detection in Hyperspectral Imagery
  515. Deformable Wiener Filter for Future Video Coding
  516. VG2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
  517. PINNOCHIO: Physics-Informed Neural Network for Coupled Hyperelastic Interface-Volume Simulation in Orthognathic Surgery
  518. RobustModelMaker: Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning
  519. GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
  520. Everywhere Learning: Artificial Intelligence with Pointwise Constraints
  521. Flexible Online Representation Learning Based on Similarity Matching
  522. CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search
  523. PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images
  524. TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
  525. Scalable Counterfactual Risk Estimation for Rare Events in Longitudinal Data
  526. PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
  527. Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
  528. Semi-Supervised Hyperbolic Hierarchical Clustering with Set-Level Structural Priors
  529. Fast Generalization after Interpolation via Critically Damped Momentum Optimization
  530. TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications
  531. SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes