mlsanityData to 13 Oct 2026

Papers

New on arXiv

Wed 13 May 2026

656 papers

  1. GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM AgentsLLM agents and tool use → Medical and scientific domain agents
  2. Domyn-Small: A European 10B Reasoning Language ModelLLM reasoning → Reasoning benchmarks and evaluation
  3. OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System AttacksLLM agents and tool use → Agent threats, guardrails and governance
  4. Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  5. Why We Need World Models for AGI: Where LLMs Fail and How World Models May OutperformWorld models → World models for language agents +1
  6. Knowledge Distillation for Low-Resource Open-source Text-to-SQL ModelKnowledge distillation → Knowledge distillation for LLMs
  7. SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context InferenceEfficient LLM inference and serving → KV cache optimization
  8. Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  9. INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  10. Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware RankingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  11. STRIDE: Learnable Stepwise Language Feedback for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  12. KadiAssistant: A conversational AI Agent for information retrieval in Kadi4MatLLM agents and tool use → Medical and scientific domain agents
  13. Exact Linear AttentionMixture-of-experts → Expert routing strategies +1
  14. Transformers Linearly Represent Highly Structured World ModelsWorld models → World models for language agents +1
  15. TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM BacktestingLLM reasoning → Test-time compute and efficient thinking
  16. Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety ConstraintsDeep reinforcement learning methods → Safe and constrained RL
  17. From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  18. CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence ReasoningLLM reasoning → Multimodal reasoning +1
  19. Diffusion Models, Denoiser Architecture and CreativityDiffusion models → Diffusion foundations and sampling
  20. SCAR: Self-Supervised Continuous Action Representation LearningWorld models → Embodied and robot world models
  21. Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  22. Test-Time Hinting for Black-Box Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  23. Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  24. WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop EnvironmentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. Learning Selective Merge Policies for Deadline-Constrained Coded Caching via Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  26. PBT-Bench: Benchmarking AI Agents on Property-Based TestingLLM agents and tool use → Software engineering coding agents
  27. Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  28. NIMO Controller: a self-driving laboratory orchestrator based on the Model Context ProtocolLLM agents and tool use → Web, search, and research agents
  29. Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-benchLLM agents and tool use → Software engineering coding agents
  30. ICRL: Learning to Internalize Self-Critique with Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution +1
  31. Effective Harness Engineering for Algorithm Discovery with Coding AgentsLLM agents and tool use → Software engineering coding agents
  32. MAPLE: Latent Multi-Agent Play for End-to-End Autonomous DrivingVision-language-action models → VLA for autonomous driving +2
  33. How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable ParameterizationMixture-of-experts → MoE large language models
  34. Why Retrieval-Augmented Generation Fails: A Graph PerspectiveRetrieval-augmented generation → RAG robustness and adaptive retrieval
  35. CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion TransformersDiffusion models → Diffusion foundations and sampling +1
  36. LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time ScalingLLM reasoning → Test-time compute and efficient thinking
  37. Thinking Ahead: Prospection-Guided Retrieval of Memory with Language ModelsLLM reasoning → Reasoning for agents, planning and code
  38. Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot NavigationDeep reinforcement learning methods → Safe and constrained RL
  39. Agentic Systems as Boosting Weak Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code +1
  40. ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity AgentsLLM agents and tool use → Agent threats, guardrails and governance
  41. ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public SafetyLLM safety and security → Safety alignment, refusal and guardrails
  42. Distribution-Aware Algorithm Design with LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  43. TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video DiffusionDiffusion models → Video generation
  44. PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  45. Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)LLM agents and tool use → Medical and scientific domain agents +1
  46. When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
  47. ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic WorkflowsLLM agents and tool use → Medical and scientific domain agents
  48. ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent EvaluationLLM agents and tool use → Tool learning and function calling
  49. Pause and Reflect: Conformal Aggregation for Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  50. SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic OrchestrationLLM agents and tool use → Agent skill learning and evolution
  51. Rethinking Layer Relevance in Large Language Models Beyond Cosine SimilarityLLM reasoning → Reasoning benchmarks and evaluation
  52. Distribution Corrected Offline Data Distillation for Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  53. CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan CurvesLLM reasoning → Multimodal reasoning
  54. Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight RejectionSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  55. Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  56. Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  57. SPIN: Structural LLM Planning via Iterative Navigation for Industrial TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  59. PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified FlowDiffusion models → Inverse problems and image restoration
  60. Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool UseLLM agents and tool use → Tool learning and function calling
  61. Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future UtilityLLM reasoning → Test-time compute and efficient thinking +2
  62. Enhanced and Efficient Reasoning in Large Learning ModelsLLM reasoning → Reasoning benchmarks and evaluation
  63. From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based AgentsLLM agents and tool use → Social simulation and multi-agent debate
  64. R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  65. Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  66. PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political FactsLLM reasoning → Reasoning for agents, planning and code +1
  67. Support Before Frequency in Discrete DiffusionDiffusion models → Discrete and text diffusion
  68. HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  69. Ergodic Imitation for Adaptive Exploration around DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  70. VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool UseLLM agents and tool use → Agent threats, guardrails and governance
  71. Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  72. WarmPrior: Straightening Flow-Matching Policies with Temporal PriorsDiffusion models → Diffusion and flow policies for robotics
  73. Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis ReproductionLLM agents and tool use → Web, search, and research agents
  74. EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM AgentsLLM agents and tool use → Agent memory systems +1
  75. AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  76. Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  77. Mechanistic Interpretability of EEG Foundation Models via Sparse AutoencodersMechanistic interpretability → Interpreting biomedical and science models
  78. Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM InferenceEfficient LLM inference and serving → KV cache quantization
  79. Covariance-aware sampling for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  80. TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal RateLLM agents and tool use → Social simulation and multi-agent debate
  81. Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your WeightsLLM agents and tool use → General LLM agent frameworks and benchmarks
  82. R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh FlowDiffusion models → Video generation
  83. Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K ContextMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  84. Harnessing Agentic EvolutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR GenerationWorld models → World modeling from LiDAR generation
  86. Provable Quantization with Randomized Hadamard TransformEfficient LLM inference and serving → KV cache quantization
  87. Attention Once Is All You Need: Efficient Streaming Inference with Stateful TransformersEfficient LLM inference and serving → KV cache optimization
  88. MinT: Managed Infrastructure for Training and Serving Millions of LLMsMixture-of-experts → Mixture of LoRA experts
  89. Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAsVision-language-action models → Efficient VLA inference and adaptation +1
  90. Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport GeometryLLM reasoning → Hallucination detection and mitigation
  91. Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter MatchingMixture-of-experts → Expert routing strategies
  92. VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance DefenseRetrieval-augmented generation → Privacy and security of RAG
  93. EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic EnvironmentsLLM agents and tool use → Social simulation and multi-agent debate
  94. FrameSkip: Learning from Fewer but More Informative Frames in VLA TrainingVision-language-action models → Human-video and latent-action pretraining
  95. Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous VehiclesEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  96. Learning POMDP World Models from Observations with Language-Model PriorsWorld models → World models for language agents
  97. KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM ServingEfficient LLM inference and serving → KV cache optimization
  98. ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic ProfilesLLM agents and tool use → Social simulation and multi-agent debate
  99. AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map DistillationDiffusion models → Video generation
  100. Tight Sample Complexity Bounds for Entropic Best Policy IdentificationDeep reinforcement learning methods → RL theory and sample complexity
All 656
  1. SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software EcosystemsLLM agents and tool use → Agent skill learning and evolution
  2. Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based OptimizationDiffusion models → Medical imaging and segmentation
  3. Cross Modality Image Translation In Medical Imaging Using Generative FrameworksDiffusion models → Medical imaging and segmentation
  4. Sampling from Flow Language Models via Marginal-Conditioned BridgesDiffusion models → Discrete and text diffusion
  5. SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow TunnelsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  7. Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene ModelingEnd-to-end autonomous driving → End-to-end system architecture
  8. Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  9. Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  10. Achieving ε-2 Sample Complexity for Single-Loop Actor-Critic under Minimal AssumptionsDeep reinforcement learning methods → RL theory and sample complexity
  11. CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation ProblemDeep reinforcement learning methods → Quantum reinforcement learning
  12. Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  13. OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics ResearchLLM agents and tool use → Medical and scientific domain agents
  14. Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving ScenesEnd-to-end autonomous driving → Generative simulation for driving
  15. Position: Assistive Agents Need Accessibility AlignmentLLM agents and tool use → GUI and mobile agents
  16. Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy OptimisationDeep reinforcement learning methods → Deep RL algorithms and representations
  17. CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  18. RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior ImitationLLM agents and tool use → Medical and scientific domain agents
  19. Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  20. HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  21. Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit MergingLLM reasoning → Knowledge- and tool-augmented reasoning +1
  22. Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMsLLM reasoning → Clinical and biomedical applications
  23. Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA GenerationKnowledge distillation → On-policy and self-distillation for LLMs
  24. MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud DatacentersLLM agents and tool use → Reinforcement learning for LLM agents
  25. Path-independent Flow Matching for Multi-parameter Generative DynamicsDiffusion models → Flow matching, time series and science
  26. PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM AgentsLLM agents and tool use → Web, search, and research agents
  27. Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI AgentsLLM safety and security → Prompt injection and agent security
  28. On the Limits of Latent Reuse in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  29. Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based PolicyDeep reinforcement learning methods → RL with diffusion and flow models
  30. Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-EvolutionLLM safety and security → Prompt injection and agent security
  31. Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum RenderingDiffusion models → Audio, speech and music
  32. RotVLA: Rotational Latent Action for Vision-Language-Action ModelVision-language-action models → Human-video and latent-action pretraining +1
  33. Trajectory-Level Data Augmentation for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  34. The Diffusion EncoderDiffusion models → Diffusion foundations and sampling
  35. RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  36. Support-Conditioned Flow Matching Is Kernel SmoothingDiffusion models → Flow matching, time series and science
  37. BlockVLA: Accelerating Autoregressive VLA via Block Diffusion FinetuningLLM reasoning → Spatial and embodied reasoning +2
  38. GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  39. Query-Conditioned Test-Time Self-Training for Large Language ModelsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  40. Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool CallingLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. AI Harness Engineering: A Runtime Substrate for Foundation-Model Software AgentsLLM agents and tool use → Software engineering coding agents
  42. GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language EmbeddingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  43. Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  44. LLM-Based Persuasion Enables Guardrail Override in Frontier LLMsLLM safety and security → Safety alignment, refusal and guardrails
  45. Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank AdaptationDiffusion models → Image generation, text-to-image and editing
  46. KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  47. HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language NavigationLLM reasoning → Spatial and embodied reasoning
  48. PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative DecodingEfficient LLM inference and serving → Early exit and edge inference
  49. Test-time Sparsity for Extreme Fast Action DiffusionDiffusion models → Diffusion foundations and sampling
  50. IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim GenerationLLM agents and tool use → Web, search, and research agents
  51. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified ScalingLLM reasoning → Mathematical reasoning
  52. Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social AttentionDiffusion models → Diffusion and flow policies for robotics
  53. CANTANTE: Optimizing Agentic Systems via Contrastive Credit AttributionRetrieval-augmented generation → Agentic RAG, agents and memory +1
  54. What properties of reasoning supervision are associated with improved downstream model quality?LLM reasoning → Reasoning benchmarks and evaluation
  55. Proximal-Based Generative Modeling for Bayesian Inverse ProblemsDiffusion models → Diffusion foundations and sampling
  56. Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  57. D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  58. Physics Guided Generative Optimization for Trotter Suzuki DecompositionDiffusion models → Diffusion foundations and sampling
  59. Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  60. EMO: Frustratingly Easy Progressive Training of Extendable MoEMixture-of-experts → Efficient MoE training and inference systems
  61. Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy DivergenceLLM reasoning → Prompting and chain-of-thought reasoning +1
  62. Improving Code Translation with Syntax-Guided and Semantic-aware Preference OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  63. ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool GroundingLLM reasoning → Multimodal reasoning
  64. GAGPO: Generalized Advantage Grouped Policy OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  65. Switching Successor Measures for Hierarchical Zero-shot Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  66. STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action RecognitionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  67. DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  68. CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  69. STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data RegimesLLM reasoning → Test-time compute and efficient thinking
  70. A3B2: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  71. Dual-Pathway Circuits of Object Hallucination in Vision-Language ModelsLLM reasoning → Hallucination detection and mitigation +2
  72. Pareto-Guided Optimal Transport for Multi-Reward AlignmentLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  73. On the Generalization of Knowledge Distillation: An Information-Theoretic ViewKnowledge distillation → General knowledge distillation methods
  74. SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution CycleLLM agents and tool use → Software engineering coding agents
  75. GateKD: Confidence-Gated Closed-Loop Distillation for Robust ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  76. ERPPO: Entropy Regularization-based Proximal Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  77. GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-trainingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  78. Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks +1
  79. DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number DefenseDiffusion models → Robustness, privacy and adversarial aspects +1
  80. Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
  81. A Multi-Agent Orchestration Framework for Venture Capital Due DiligenceLLM agents and tool use → Financial trading and forecasting agents
  82. Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack DetectionKnowledge distillation → Federated, robust and private distillation
  83. What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA ModelsVision-language-action models → Reinforcement learning and post-training
  84. Learning to See What You Need: Gaze Attention for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  85. Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  86. Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  87. Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  88. Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic SaliencyMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  89. An Agentic LLM-Based Framework for Population-Scale Mental Health ScreeningLLM agents and tool use → Medical and scientific domain agents
  90. No Attack Required: Semantic Fuzzing for Specification Violations in Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance +1
  91. Adaptive Steering and Remasking for Safe Generation in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  92. MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  93. PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  94. Understanding and Accelerating the Training of Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  95. JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement LearningWorld models → Latent dynamics models and model-based RL +2
  96. Amortized Guidance for Image Inpainting with Pretrained Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  97. Implicit Behavioral Decoding from Next-Step Spike Forecasts at Population ScaleState-space sequence models (S4, Mamba) → Core SSM architectures for language
  98. F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and RankingLLM reasoning → Reinforcement learning for reasoning
  99. Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent SycophancyLLM agents and tool use → Social simulation and multi-agent debate +1
  100. Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI EducationRetrieval-augmented generation → Agentic RAG, agents and memory
  101. Leveraging Multimodal Self-Consistency Reasoning in Coding Motivational Interviewing for Alcohol Use ReductionLLM reasoning → Clinical and biomedical applications
  102. Useful Memories Become Faulty When Continuously Updated by LLMsLLM agents and tool use → Agent memory systems
  103. Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  104. Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive PerspectiveLLM reasoning → Reinforcement learning for reasoning
  105. Position: Agentic AI System Is a Foreseeable Pathway to AGILLM agents and tool use → General LLM agent frameworks and benchmarks
  106. GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video DiffusionDiffusion models → 3D, point cloud and scene generation
  107. Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided SegmentationLLM reasoning → Multimodal reasoning +1
  108. Coreset-Induced Conditional Velocity Flow MatchingDiffusion models → Flow matching, time series and science
  109. Reinforced Collaboration in Multi-Agent Flow NetworksLLM agents and tool use → General LLM agent frameworks and benchmarks
  110. The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language ModelsMechanistic interpretability → Circuits and mechanistic analysis
  111. CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video GenerationWorld models → Video-generation world models and simulators
  112. Embodied Multi-Agent Coordination by Aligning World Models Through DialogueWorld models → World models for language agents +2
  113. GuardMarkGS: Unified Ownership Tracing and Edit Deterrence for 3D Gaussian SplattingLLM safety and security → Watermarking generated content and models
  114. CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  115. Revisiting DAgger in the Era of LLM-AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  116. Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  117. Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated TextsMechanistic interpretability → Activation steering methods
  118. EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search AgentsLLM agents and tool use → Web, search, and research agents
  119. Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many FeaturesMechanistic interpretability → SAE features and their applications
  120. Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival AnalysisLLM safety and security → Jailbreaking
  121. Language-Based Agent ControlLLM agents and tool use → Agent threats, guardrails and governance
  122. ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL GenerationLLM agents and tool use → Software engineering coding agents
  123. Persona-Model Collapse in Emergent MisalignmentSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  124. Discrete Stochastic Localization for Non-autoregressive GenerationDiffusion models → Diffusion foundations and sampling
  125. PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and ModelsWorld models → World models for language agents
  126. Learning to Optimize at Scale: A Benders Decomposition-TransfORmers Framework for Stochastic Combinatorial Optimization
  127. The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs
  128. thaulab@EEUCA 2026: Who Said What to Whom? A Targeting-Aware Neural-Symbolic Pipeline for Gaming Toxicity Detection
  129. Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content
  130. SCoPE: Shift-Aware Speaker-Conditioned Priors for Emotion Recognition in Conversations
  131. Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools
  132. Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
  133. Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure
  134. Incentives Of EdTech: A Systematic Review Of EduNLP Research
  135. Indirect Computing Model with Indirect Formal Method
  136. Product-Aware Deep Autoencoders for Robust Process Monitoring in Multi-Product Cyber-Physical Systems
  137. WASHH: An Anchor-Aware Whale-Guided Selection Hyper-Heuristic for Continuous Optimization and SVC Configuration
  138. Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets
  139. Metacognition Should Be the Scientific Framework for Bounded and Effective Self-Governance in Generative AI
  140. Algometrics: Forecasting Under Algorithmic Feedback
  141. A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks
  142. AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
  143. Physics-Guided Concentration Inference from Resistance Transients in a Mixed-Phase SnO-SnO2 Carbon Monoxide Sensor with p-n Switching
  144. Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
  145. SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
  146. Sensing Intelligence as a Trainable Metamaterial Property
  147. Community-Aware Vertex Ordering for Reference-Based Graph Compression: A Cross-Encoder Empirical Study
  148. Why Latent Actions Fail, and How to Prevent It
  149. Quantum End-to-End Learning for Contextual Combinatorial Optimization
  150. Delta Attention Residuals
  151. INSIGHTS: Demonstration-Based Summaries of Time Series Predictors
  152. Lost and Found in Translation: Variational Diagnostics for Neural Codebook Channels
  153. First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
  154. Graph-Driven Cross-Industry Real-Time Monitoring Framework for Anti-Money Laundering Detection in Converged Mobility-Energy Supply Chain Networks
  155. The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next
  156. An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making
  157. Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
  158. VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals
  159. Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
  160. StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping
  161. SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing
  162. NERVE: A Neuromorphic Vision and Radar Ensemble for Multi-Sensor Fusion Research
  163. Visual Search Patterns in 3D Pancreatic Imaging: An Eye Tracking Study
  164. Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture
  165. Mitigating Illumination-Induced Domain Shift in Night-Time Pedestrian Detection for Intelligent Vehicles using Annotation-Preserving Diffusion Augmentation
  166. Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
  167. Hybrid Quantum-MambaVision: A Quantum-enhanced State Space Model for Calibrated Mixed-type Wafer Defect Detection
  168. When Vision Speaks for Sound
  169. FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization
  170. MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
  171. Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation
  172. Do Biological Structural Guarantees Earn Their Complexity?
  173. GenAI-Driven Approach to RISC-V Supply Chain Exploration
  174. PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization
  175. Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
  176. LLM-Based Robustness Testing of Microservice Applications: An Empirical Study
  177. Stochastic Matching via Local Sparsification
  178. GradShield: Alignment Preserving Finetuning
  179. QOuLiPo: What a quantum computer sees when it reads a book
  180. Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
  181. CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision
  182. BOOKMARKS: Efficient Active Storyline Memory for Role-playing
  183. Finite Sample Bounds for Learning with Score Matching
  184. The Evaluation Trap: Benchmark Design as Theoretical Commitment
  185. You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps
  186. Unsteady Metrics and Benchmarking Cultures of AI Model Builders
  187. Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings
  188. Stochastic global optimization of continuous functions via random walks on Grassmannians
  189. A Systematic Evaluation of Imbalance Handling Methods in Biomedical Binary Classification
  190. bde: A Python Package for Bayesian Deep Ensembles via MILE
  191. Rethinking the Good Enough Embedding for Easy Few-Shot Learning
  192. To discretize continually: Mean shift interacting particle systems for Bayesian inference
  193. ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
  194. Polar probe linearly decodes semantic structures from LLMs
  195. Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis
  196. Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence
  197. Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
  198. Modeling Bounded Rationality in Drug Shortage Pharmacists Using Attention-Guided Dynamic Decomposition
  199. SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
  200. A Cascaded Edge-Cloud Architecture for Automated Diabetic Retinopathy Screening
  201. DUET: Dual-Paradigm Adaptive Expert Triage with Single-cell Inductive Prior for Spatial Transcriptomics Prediction
  202. Venus-DeFakerOne: Unified Fake Image Detection & Localization
  203. Synthetic Sociality: How Generative Models Privatize the Social Fabric
  204. Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study
  205. CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
  206. Fair and Calibrated Toxicity Detection with Robust Training and Abstention
  207. AttnGen: Attention-Guided Saliency Learning for Interpretable Genomic Sequence Classification
  208. SurF: A Generative Model for Multivariate Irregular Time Series Forecasting
  209. Comparative Evaluation of Machine Learning Approaches for Minority-Class Financial Distress Prediction Under Class Imbalance Constraints
  210. A Benchmark for Early-stage Parkinson's Disease Detection from Speech
  211. Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
  212. MathAtlas: A Benchmark for Autoformalization in the Wild
  213. Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systems
  214. Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
  215. PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
  216. Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
  217. Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation
  218. Wahkon: A Statistically Principled Deep RKHS Superposition Network
  219. Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning
  220. Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents
  221. Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
  222. Unified Pix Token And Word Token Generative Language Model
  223. Do Language Models Align with Brains? Prediction Scores Are Not Enough
  224. Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impact
  225. Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization
  226. Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
  227. Conditional Attribute Estimation with Autoregressive Sequence Models
  228. Synthetic American Option Pricing via Jump-HMM-Driven Heston Implied Volatility
  229. CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI
  230. Neural Fields for NV-Center Inverse Sensing
  231. TabPFN-3: Technical Report
  232. Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines
  233. Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
  234. A Unified Geometric Framework for Weighted Contrastive Learning
  235. EMA: Efficient Model Adaptation for Learning-based Systems
  236. Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
  237. Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling
  238. Learning to Select Source Domains: Proxy-Rewarded Policy Optimization for Molecular OOD Generalization
  239. Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations
  240. XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
  241. Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey
  242. CA2: Code-Aware Agent for Automated Game Testing
  243. A Regret Perspective on Online Multiple Testing
  244. A Survey on Data-Dependent Worst-Case Generalization Bounds
  245. AIS: Adaptive Importance Sampling for Quantized RL
  246. A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study
  247. Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2
  248. WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
  249. Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
  250. EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
  251. What is Learnable in Valiant's Theory of the Learnable?
  252. Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
  253. Topology-Preserving Neural Operator Learning via Hodge Decomposition
  254. QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
  255. Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach
  256. Negation Neglect: When models fail to learn negations in training
  257. Reducing cross-sample prediction churn in scientific machine learning
  258. History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions
  259. Neurosymbolic Auditing of Natural-Language Software Requirements
  260. Uncertainty-Driven Anomaly Detection for Psychotic Relapse Using Smartwatches: Forecasting and Multi-Task Learning Fusion
  261. JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift
  262. Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo
  263. Min-Max Optimization Requires Exponentially Many Queries
  264. EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
  265. Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling
  266. VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence
  267. BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
  268. An LLM-Based System for Argument Mining
  269. Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
  270. ENSEMBITS: an alphabet of protein conformational ensembles
  271. Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
  272. Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data
  273. Amplification to Synthesis: A Comparative Analysis of Cognitive Operations Before and After Generative AI
  274. LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration
  275. RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data
  276. (How) Do Large Language Models Understand High-Level Message Sequence Charts?
  277. High-Rate Quantized Matrix Multiplication II
  278. Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
  279. Fast and effective algorithms for fair clustering at scale
  280. Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception
  281. Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein
  282. Weakly-Supervised Spatiotemporal Anomaly Detection
  283. Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration
  284. GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction
  285. LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction
  286. Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
  287. Distinguishing performance gains from learning when using generative AI
  288. Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography
  289. Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation
  290. Humanwashing -- It Should Leave You Feeling Dirty
  291. MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling
  292. Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
  293. DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
  294. Identifying AI Web Scrapers Using Canary Tokens
  295. Adaptive mine planning under geological uncertainty: A POMDP framework for sequential decision-making
  296. RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning
  297. Polyhedral Instability Governs Regret in Online Learning
  298. The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
  299. MedCore: Boundary-Preserving Medical Core Pruning for MedSAM
  300. A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
  301. Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale
  302. Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting
  303. Characterizing Universal Object Representations Across Vision Models
  304. Weakly Supervised Segmentation as Semantic-Based Regularization
  305. Graph Neural Networks with Triangle-Based Messages for the Multicut Problem
  306. SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
  307. Pattern-Enhanced RT-DETR for Multi-Class Battery Detection
  308. HADAR-Based Thermal Infrared Hyperspectral Image Restoration
  309. Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas
  310. Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
  311. NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
  312. FlowCompile: An Optimizing Compiler for Structured LLM Workflows
  313. Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with nonconform
  314. How to Interpret Agent Behavior
  315. Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction
  316. Multimodal Graph-based Classification of Esophageal Motility Disorders
  317. WD-FQDet: Multispectral Detection Transformer via Wavelet Decomposition and Frequency-aware Query Learning
  318. DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy
  319. Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
  320. Rethinking Graph Convolution for 2D-to-3D Hand Pose Lifting
  321. Unweighted ranking for value-based decision making with uncertainty
  322. Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting
  323. Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective
  324. Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations
  325. Inducing Artificial Uncertainty in Language Models
  326. Causal Learning with the Invariance Principle
  327. Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models
  328. HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation
  329. Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging
  330. HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation
  331. Beyond Anthropomorphism: Exploring the Roles of Perceived Non-humanity and Structural Similarity in Deep Self-Disclosure Toward Generative AI
  332. Learning Local Constraints for Reinforcement-Learned Content Generators
  333. Dynamical Predictive Modelling of Cardiovascular Disease Progression Post-Myocardial Infarction via ECG-Trained Artificial Intelligence Model
  334. Spatiotemporal downscaling and nowcasting of urban land surface temperatures with deep neural networks
  335. Qwen-Image-VAE-2.0 Technical Report
  336. Uncertainty-Aware Prediction of Lung Tumor Growth from Sparse Longitudinal CT Data via Bayesian Physics-Informed Neural Networks
  337. Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report
  338. Mixed neural posterior estimation for simulators with discrete and continuous parameters
  339. AttenA+: Rectifying Action Inequality in Robotic Foundation Models
  340. Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models
  341. Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
  342. AI-Generated Slides: Are They Good? Can Students Tell?
  343. MMSkills: Towards Multimodal Skills for General Visual Agents
  344. Beyond Explained Variance: A Cautionary Tale of PCA
  345. ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
  346. Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
  347. Limits of Personalizing Differential Privacy Budgets
  348. PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors
  349. R^2-Mem: Reflective Experience for Memory Search
  350. Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
  351. Discovery of Hidden Miscalibration Regimes
  352. Neural Video Compression with Domain Transfer
  353. FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
  354. OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
  355. Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems
  356. PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
  357. Z-Order Transformer for Feed-Forward Gaussian Splatting
  358. A Unified Three-Stage Machine Learning Framework for Diabetes Detection, Subtype Discrimination, and Cognitive-Metabolic Hypothesis Testing
  359. Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices
  360. OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression
  361. Bayesian In Vivo Tracking of Synapses using Joint Poisson Deconvolution and Diffeomorphic Registration
  362. CUBic: Coordinated Unified Bimanual Perception and Control Framework
  363. LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking
  364. Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers
  365. CogniFold: Always-On Proactive Memory via Cognitive Folding
  366. Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP
  367. Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
  368. TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation
  369. Towards a holistic understanding of Selection Bias for Causal Effect Identification
  370. TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
  371. Strategic PAC Learnability via Geometric Definability
  372. LIFT: Last-Mile Fine-Tuning for Table Explicitation
  373. DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning
  374. KIT-TIP-NLP at MultiPride: Continual Learning with Multilingual Foundation Model
  375. TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
  376. LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics
  377. From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks
  378. Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction
  379. When is Warmstarting Effective for Scaling Language Models?
  380. Fast and Compact Graph Cuts for the Boykov-Kolmogorov Algorithm
  381. PreFIQs: Face Image Quality Is What Survives Pruning
  382. Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
  383. Teaching and Learning under Deductive Errors
  384. Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
  385. Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics
  386. Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing
  387. Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory
  388. What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
  389. A Horn extension of DL-Lite with NL data complexity
  390. Neural Surrogate Forward Modelling For Electrocardiology Without Explicit Intracellular Conductivity Tensor
  391. Constitutional Governance in Metric Spaces
  392. Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints
  393. Contextual Bandits for Resource-Constrained Devices using Probabilistic Learning
  394. Multi-Agent Systems in Emergency Departments: Validation Study on a ED Digital Twin
  395. A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves
  396. Shortcut Mitigation via Spurious-Positive Samples
  397. Probing Persona-Dependent Preferences in Language Models
  398. Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling
  399. Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
  400. Diversity of Extensions in Abstract Argumentation
  401. FIND: Toward Multimodal Financial Reasoning and Question Answering for Indic Languages
  402. Tracing Persona Vectors Through LLM Pretraining
  403. What Limits Vision-and-Language Navigation ?
  404. VERA-MH: Validation of Ethical and Responsible AI in Mental Health
  405. Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation
  406. Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis
  407. PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
  408. Color Constancy in Hyperspectral Imaging via Reduced Spectral Spaces
  409. MPINeuralODE: Multiple-Initial-Condition Physics-Informed Neural ODEs for Globally Consistent Dynamical System Learning
  410. Safe Bayesian Optimization for Uncertain Correlation Matrices in Linear Models of Co-Regionalization
  411. PaMM: Periodic Motif Memory for Atomistic Models with an Explicit Local-Structure Interface
  412. Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion
  413. IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages
  414. Delightful Exploration
  415. Learning Perturbations to Extrapolate Your LLM
  416. Byzantine-Robust Distributed Sparse Learning Revisited
  417. Differentiable Learning of Lifted Action Schemas for Classical Planning
  418. Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code
  419. LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections
  420. Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
  421. "It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps
  422. Unified generalization analysis for physics informed neural networks
  423. X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge
  424. The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
  425. Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis
  426. It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows
  427. When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
  428. IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations
  429. Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
  430. Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation
  431. An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing
  432. Machine Learning-Driven Multimodal Spectroscopic Liquid Biopsy for Early Multicancer Detection
  433. Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks
  434. Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
  435. A Hybrid Tucker-LSTM Tensor Network Model for SOC Prediction in Electric Vehicles
  436. McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting
  437. ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification
  438. FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition
  439. N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
  440. LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information
  441. Stable Attention Response for Reliable Precipitation Nowcasting
  442. Does Engram Do Memory Retrieval in Autoregressive Image Generation?
  443. Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training
  444. Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems
  445. When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling
  446. Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
  447. Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications
  448. PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World
  449. GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language
  450. LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
  451. Continual Fine-Tuning of Large Language Models via Program Memory
  452. Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
  453. Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
  454. Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning
  455. EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
  456. GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation
  457. Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process
  458. AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
  459. Understanding Generalization through Decision Pattern Shift
  460. On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods
  461. Collaborating in Multi-Armed Bandits with Strategic Agents
  462. A Constraint Programming Approach for n-Day Lookahead Playoff Clinching in the NHL
  463. Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
  464. A Comprehensive Evaluation of Code Language Models for Security Patch Detection
  465. LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
  466. KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation
  467. Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
  468. Amortized Neural Clustering of Time Series based on Statistical Features
  469. State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
  470. MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing
  471. Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
  472. SECOND-Grasp: Semantic Contact-guided Dexterous Grasping
  473. Context Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles
  474. Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning
  475. Watermarking Should Be Treated as a Monitoring Primitive
  476. RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
  477. Adaptive Kernel Density Estimation with Pre-training
  478. Bayesian Nonparametric Mixed-Effect ODEs with Gaussian Processes
  479. Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
  480. Does language matter for spoken word classification? A multilingual generative meta-learning approach
  481. PRA-PoE: Robust Multimodal Alzheimer's Diagnosis with Arbitrary Missing Modalities
  482. Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
  483. Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
  484. TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints
  485. Scaling few-shot spoken word classification with generative meta-continual learning
  486. HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
  487. Neural QAOA2: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
  488. Local Inverse Geometry Can Be Amortized
  489. When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation
  490. BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability
  491. The Cost of Perfect English: Pragmatic Flattening and the Erasure of Authorial Voice in L2 Writing Supported by GenAI
  492. RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
  493. Context Training with Active Information Seeking
  494. Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images
  495. Large Language Models Lack Temporal Awareness of Medical Knowledge
  496. EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing
  497. CoGE: Sim-to-Real Online Geometric Estimation for Monocular Colonoscopy
  498. ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence
  499. What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
  500. FeatCal: Feature Calibration for Post-Merging Models
  501. Offline Two-Player Zero-Sum Markov Games with KL Regularization
  502. Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle
  503. OCH3R: Object-Centric Holistic 3D Reconstruction
  504. A General B'ezier Tree Encoding Counterfactual Framework for Retinal-Vessel-Mediated Disease Analysis
  505. DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
  506. Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
  507. DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
  508. SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting
  509. Decision Tree Learning on Product Spaces
  510. Protocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence
  511. CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions
  512. Enhancing a Risk Model by Adding Transient Statistical Factors
  513. Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving
  514. Controlling Logical Collapse in LLMs via Algebraic Ontology Projection over F2
  515. ImageAttributionBench: How Far Are We from Generalizable Attribution?
  516. U-HNO: A U-shaped Hybrid Neural Operator with Sparse-Point Adaptive Routing for Non-stationary PDE Dynamics
  517. Asymmetric Flow Models
  518. Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements
  519. Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
  520. DiMtextsuperscript3: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
  521. AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding
  522. Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
  523. When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
  524. Separating Shortcut Transition from Cross-Family OOD Failure in a Minimal Model
  525. From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning
  526. DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
  527. AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters
  528. ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset
  529. Anatomy-Slot: Unsupervised Anatomical Factorization for Homologous Bilateral Reasoning in Retinal Diagnosis
  530. The Efficiency Gap in Byte Modeling
  531. ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels
  532. AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
  533. IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning
  534. When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
  535. Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classification
  536. SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring
  537. The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
  538. Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
  539. VIP-COP: Context Optimization for Tabular Foundation Models
  540. Robust Sequential Experimental Design for A/B Testing
  541. When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method
  542. RISED: A Pre-Deployment Evaluation Framework for High-Stakes AI Decision-Support Systems, with Application to Healthcare
  543. CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
  544. ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection
  545. Adam-SHANG: A Convergent Adam-Type Method for Stochastic Smooth Convex Optimization
  546. Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
  547. SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
  548. NeuroRisk: Physics-Informed Neural Optimization for Risk-Aware Traffic Engineering
  549. Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue
  550. Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy
  551. Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response
  552. PRISM: Perinuclear Ring-based Image Segmentation Method for Acute Lymphoblastic Leukemia Classification
  553. AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects
  554. ReForge: Refining Merged Models with Anchor-Regularized Regression
  555. Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness
  556. Multimodal Hidden Markov Models for Persistent Emotional State Tracking