mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 8 Jun 2026

549 papers

  1. Active Inference as Context Acquisition for AI AgentsLLM agents and tool use → Agent memory systems
  2. MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned EvaluatorsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  3. Backdoor Learning in Language Models and Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  4. How to Dogfood Your AI Chat Agent: A Three-Layer Evaluation Framework with Goal-Directed NPC SimulationLLM agents and tool use → Social simulation and multi-agent debate
  5. The Effect of Text Chunk Size on Retrieval-Augmented Generation PerformanceRetrieval-augmented generation → Multimodal RAG
  6. The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent EvaluationLLM agents and tool use → Software engineering coding agents
  7. Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior ApproachRetrieval-augmented generation → RAG robustness and adaptive retrieval
  8. ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified RecommendationLLM agents and tool use → Agentic recommender systems
  9. XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical SystemsLLM reasoning → Clinical and biomedical applications
  10. Disentangling Hallucinations: Orthogonal Semantic Projection for Robust InterpretabilityMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  12. My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model AgentsLLM agents and tool use → Medical and scientific domain agents
  13. RealMath-Eval: Why SOTA Judges Struggle with Real Human ReasoningLLM reasoning → Mathematical reasoning
  14. SHAPO: Sharpness-Aware Policy Optimization for Safe ExplorationDeep reinforcement learning methods → Safe and constrained RL
  15. Alignment Defends LLMs from Property Inference AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  16. Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  17. A Continuous-Time Markov Chain Framework for Insertion Language ModelsDiffusion models → Discrete and text diffusion
  18. Density Ridge Selective Prediction for LLM and VLM Hallucination Detection under Calibration Label ScarcityMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  19. Dropout-GRPO: Variational Stochasticity for Continuous Latent ReasoningLLM reasoning → Reinforcement learning for reasoning
  20. Making Time Editable in Video Diffusion TransformersDiffusion models → Video generation
  21. Flow Control: Steering Vision-Language-Action Models with Simple Real-Time InputsVision-language-action models → Generalist VLA models and benchmarks
  22. VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food ScienceRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  23. τ-Rec: A Verifiable Benchmark for Agentic Recommender SystemsLLM agents and tool use → Agentic recommender systems
  24. From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  25. BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional AutoregressionWorld models → Video-generation world models and simulators
  26. Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  27. Pareto-Guided Teacher Alignment for Fair Personalized Text GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  28. What makes a harness a harness: necessary and sufficient conditions for an agent harnessLLM agents and tool use → Software engineering coding agents
  29. A Theory on Flow Matching with Neural NetworksDiffusion models → Flow matching, time series and science
  30. VFUSE: Virulent Feature Understanding with Sparse autoEncodersMechanistic interpretability → Interpreting biomedical and science models
  31. A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language BenchmarksMultimodal LLMs / vision-language models → Medical vision-language models
  32. Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet TracesLLM reasoning → Reasoning for agents, planning and code +1
  33. Deployment-Time Memorization in Foundation-Model AgentsLLM agents and tool use → Agent memory systems
  34. Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation ModelsDiffusion models → Audio, speech and music
  35. Business World ModelWorld models → World models for language agents
  36. Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future ImaginationWorld models → Embodied and robot world models
  37. Interpreting and Steering a Text-to-Speech Language Model with Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  38. Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-SpeechDiffusion models → Discrete and text diffusion
  39. 3SPO: State-Score-Supervised Policy Optimization for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  40. Uncertainty-Aware Motion Planning for Autonomous Driving in Mixed Traffic EnvironmentEnd-to-end autonomous driving → Reinforcement learning for driving
  41. Interactions Between Crosscoder Features: A Compact Proofs PerspectiveMechanistic interpretability → Sparse autoencoder training and evaluation
  42. Latent Spatial Memory for Video World ModelsWorld models → Video-generation world models and simulators
  43. MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  44. OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement DynamicsLLM agents and tool use → Reinforcement learning for LLM agents
  45. An Agency-Transferring Model-Free Policy Enhancement TechniqueDeep reinforcement learning methods → Deep RL algorithms and representations
  46. Rethinking the Divergence Regularization in LLM RLLLM reasoning → Reinforcement learning for reasoning
  47. PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal LawsDiffusion models → Diffusion foundations and sampling
  48. iMaC: Translating Actions into Motion and Contact Images for Embodied World ModelsWorld models → Embodied and robot world models
  49. AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context RoutingWorld models → Embodied and robot world models
  50. Echo-Memory: A Controlled Study of Memory in Action World ModelsWorld models → Video-generation world models and simulators
  51. Difference-Aware Retrieval Policies for Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  52. Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action ModelsVision-language-action models → Safety and adversarial attacks
  53. Multi-Turn Evaluation of Deep Research Agents Under Process-Level FeedbackLLM agents and tool use → Web, search, and research agents
  54. ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  55. HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM AgentsLLM agents and tool use → Multimodal and embodied agents
  56. The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language ModelLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  57. SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep ResearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal DomainRetrieval-augmented generation → Legal and financial RAG
  59. Evaluating the Representation Space of Diffusion Models via Self-Supervised PrinciplesDiffusion models → Diffusion foundations and sampling
  60. Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its GeneralizationLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  61. IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural ThinkingLLM reasoning → Prompting and chain-of-thought reasoning
  62. Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPOLLM reasoning → Reinforcement learning for reasoning +1
  63. Cranio-Diff: Diffusion-based Cross-domain Craniofacial Reconstruction with 2D X-ray Skull Guidance and Structural Identity ConstraintsDiffusion models → 3D, point cloud and scene generation
  64. Observability for Delegated Execution in Agentic AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  65. (Auto)formalization is supposed to be easy: Trellis process semantics for spelling out rigorous proofsLLM agents and tool use → Educational agents and math problem solving
  66. SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World TasksLLM reasoning → Spatial and embodied reasoning +2
  67. When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction FollowingLLM reasoning → Mathematical reasoning
  68. End-to-End Context Compression at ScaleEfficient LLM inference and serving → Prompt and context compression
  69. Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous DrivingLLM reasoning → Multimodal reasoning +2
  70. Agentic Persona Generation with Critique-Refinement: An Industrial EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  71. Gradient-Guided Reward Optimization for Inference-time AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  72. ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action PoliciesVision-language-action models → Failure recovery and robustness
  73. DexPIE: Stable Dexterous Policy Improvement from Real-World ExperienceOffline RL and imitation learning from data → Robot manipulation imitation learning
  74. AgentServeSim: Serving-System Simulation and Policy Search for LLM Agent ProgramsLLM agents and tool use → Software engineering coding agents
  75. TUDSR: Twice Upsampling-Diffusion for Higher Super-ResolutionDiffusion models → Inverse problems and image restoration
  76. Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation DisposesMechanistic interpretability → Circuits and mechanistic analysis
  77. Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond TextLLM reasoning → Multimodal reasoning +1
  78. TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  79. CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor ControlVision-language-action models → Efficient VLA inference and adaptation
  80. Safe-RULE: Safe Reinforcement UnLEarningLLM safety and security → Machine unlearning +1
  81. AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset ValuationLLM reasoning → Knowledge- and tool-augmented reasoning
  82. SecureClaw: Clawing Back Control of LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  83. Model Poisoning Against Federated Model Adaptation with Chain of Bit-FlipsLLM safety and security → Federated unlearning and poisoning
  84. From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMsEfficient LLM inference and serving → KV cache optimization
  85. Prisma-World: Camera-Controllable Multi-Agent Video World ModelWorld models → Video-generation world models and simulators
  86. Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Auditable Biomedical Informatics ArchitectureLLM agents and tool use → Web, search, and research agents
  87. Targeting World Models to Compromise Robot Learning PipelinesWorld models → World model security and GUI agents +1
  88. Self-Harness: Harnesses That Improve ThemselvesLLM agents and tool use → Software engineering coding agents
  89. Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM AgentsLLM agents and tool use → Agent memory systems +1
  90. Escaping the KL Agreement Trap in On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  91. H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human InteractionsLLM agents and tool use → Agent memory systems
  92. AbstRAG: Learning to Abstract for Retrieval ProblemsRetrieval-augmented generation → RAG pipeline design and evaluation
  93. ω-EVA: Envision, Verify, and Act with Latent Interactive World ModelsWorld models → Embodied and robot world models
  94. Breaking the Tokenizer Barrier: On-Policy Distillation across Model FamiliesKnowledge distillation → On-policy and self-distillation for LLMs
  95. AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
  96. SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention InvarianceRetrieval-augmented generation → Generation and context integration
  97. MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  98. Graph Mamba Operator: A Latent Simulator for Interacting Particle SystemsState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  99. WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid InterfacesLLM agents and tool use → GUI and mobile agents
  100. What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model AgentsLLM agents and tool use → Agent skill learning and evolution
All 549
  1. RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing BehaviourLLM agents and tool use → Web, search, and research agents
  2. PriFT: Prior-Support Guided Supervised Fine-TuningDeep reinforcement learning methods → RL training of language and agent models
  3. CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  4. Distilling Safe LLM Systems via Soft Prompts for On Device SettingsLLM safety and security → Safety alignment, refusal and guardrails
  5. ReGIL: Retrieval-Guided Imitation Learning from a Single DemonstrationOffline RL and imitation learning from data → Robot manipulation imitation learning
  6. Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall ShortLLM reasoning → Reinforcement learning for reasoning
  7. Echo-DM: Ultrasound Marker Removal via Conditional Latent Diffusion and Region-Aware FusionDiffusion models → Medical imaging and segmentation
  8. Capability-Aligned Hierarchical Learning for Tool-Augmented LLMsLLM agents and tool use → Tool learning and function calling
  9. PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics ExperimentsLLM reasoning → Spatial and embodied reasoning
  10. Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMsLLM reasoning → Audio-language model reasoning
  11. Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline StudyEnd-to-end autonomous driving → VLMs for autonomous driving
  12. PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit AssignmentLLM reasoning → Reinforcement learning for reasoning +3
  13. Leveraging Structural Constraints for Diffusion-based Neural TSP SolversDiffusion models → Diffusion foundations and sampling
  14. Multi-Hop Knowledge Composition is Bound by Pretraining ExposureLLM reasoning → Knowledge- and tool-augmented reasoning
  15. TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA
  16. Anything2Skill: Compiling External Knowledge into Reusable Skills for AgentsRetrieval-augmented generation → Agentic RAG, agents and memory
  17. Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  18. KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp GenerationDiffusion models → Diffusion and flow policies for robotics
  19. Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program SearchWorld models → World models for language agents
  20. FF-JEPA: Long-Horizon Planning in World Models with Latent PlannersWorld models → Latent predictive world models
  21. SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher SamplingKnowledge distillation → On-policy and self-distillation for LLMs +1
  22. Reason Twice: Segmentation via Candidate Discovery and Comparative ReasoningLLM reasoning → Multimodal reasoning
  23. Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual ReasoningLLM reasoning → Multimodal reasoning +1
  24. Trajectory Geometry of Transformer Representations Across LayersMechanistic interpretability → Circuits and mechanistic analysis
  25. EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  26. Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone SelectionVision-language-action models → Failure recovery and robustness
  27. BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data GenerationDiffusion models → Flow matching, time series and science
  28. TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective ReasoningLLM reasoning → Reasoning for agents, planning and code
  29. LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  30. Temporal-Aware Reasoning Optimization for Video Temporal GroundingLLM reasoning → Multimodal reasoning +1
  31. Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in SimulationDeep reinforcement learning methods → RL for autonomous driving and traffic
  32. End-to-End Training for Discrete Token LLM based TTS SystemDiffusion models → Audio, speech and music
  33. MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-ManipulationWorld models → Humanoid and legged locomotion world models
  34. The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context InjectionLLM safety and security → Safety alignment, refusal and guardrails
  35. MASS: Deep Research for Social Sciences with Memory-Augmented Social SimulationLLM agents and tool use → Social simulation and multi-agent debate
  36. Symbolic and Abstractive Reasoning with Complex Visual QueriesLLM reasoning → Multimodal reasoning +1
  37. Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation ModelsLLM safety and security → Machine unlearning
  38. Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software EngineeringLLM agents and tool use → Tool learning and function calling
  39. Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative AnalysisLLM safety and security → Safety alignment, refusal and guardrails
  40. Unified Energy for Invariant and Independent Decoding in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  41. Ultra Flash: Scaling Real-Time Streaming Video Generation to High ResolutionsDiffusion models → Video generation
  42. Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  43. FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow DistillationDiffusion models → Audio, speech and music
  44. Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  45. Vision Language Model Helps Private Information De-Identification in Vision DataMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  46. Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual SaturationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  47. Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation ChallengesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  48. A Regret Minimization Framework on Preference Learning in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  49. Autonomous Incident Resolution at Hyperscale: An Agentic AI Architecture for Network OperationsLLM agents and tool use → Agent threats, guardrails and governance
  50. ComplexConstraints and Beyond: Expert Rubrics for RLVRLLM agents and tool use → Reinforcement learning for LLM agents
  51. Counterfactual Transport Flows for Offline Conservative Trajectory RefinementOffline RL and imitation learning from data → Offline RL algorithms +1
  52. HDRAgent: An Agentic Framework for Multi-Exposure HDR ImagingLLM agents and tool use → Multimodal and embodied agents
  53. Driving Video Retrieval for Complex Queries with Structured GroundingEnd-to-end autonomous driving → VLMs for autonomous driving
  54. Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured ContextsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  55. Addressing Market Regime Changes and Heavy-Tailed Returns in Portfolio Optimization via Bayesian VAR and Elliptical Black-LittermanDeep reinforcement learning methods → Adversarial robustness and RL in finance
  56. HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio SynthesisDiffusion models → Audio, speech and music
  57. Stabilizing On-Policy Distillation for MLLM Reasoning with Global NormalizationLLM reasoning → Reinforcement learning for reasoning +1
  58. Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance GapsLLM agents and tool use → Agent threats, guardrails and governance +1
  59. Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric TaxonomyEfficient LLM inference and serving → Early exit and edge inference
  60. FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse AttentionEfficient LLM inference and serving → KV cache optimization
  61. The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  62. Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score DistributionsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  63. A Unifying Lens on Reward Uncertainty in RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  64. REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent TracesLLM agents and tool use → Software engineering coding agents
  65. See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video UnderstandingLLM reasoning → Multimodal reasoning
  66. Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  67. Stage-1 Controls the Entropy Regime, Not the OutcomeMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  68. INFUSER: Influence-Guided Self-Evolution Improves ReasoningLLM reasoning → Reasoning for agents, planning and code
  69. BareWave: Waveform-Native Flow-Matching Text-to-SpeechDiffusion models → Audio, speech and music
  70. DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual SensitivityLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  71. Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMsMixture-of-experts → Expert routing strategies
  72. A Multi-Agent System for Motor Design Optimization via an FEA-AI Hybrid ApproachLLM agents and tool use → Multimodal and embodied agents
  73. CRANE: Knowledge Editing for Reasoning MLLMsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  74. Bridging the Agent-World Gap: Text World Models for LLM-based AgentsWorld models → World models for language agents +1
  75. TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMsLLM reasoning → Clinical and biomedical applications
  76. ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World ModelsWorld models → Latent predictive world models
  77. TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-SpeechEfficient LLM inference and serving → Audio and omni-modal token compression
  78. Scaling by Diversified Experience for Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  79. Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety BoundariesRetrieval-augmented generation → Privacy and security of RAG
  80. The Token Not Taken: Sampling, State, and the Stochasticity of AI AgentsLLM agents and tool use → Agent memory systems
  81. SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and ReasoningLLM agents and tool use → Multimodal and embodied agents
  82. Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural NetworksKnowledge distillation → Graph neural network distillation
  83. RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  84. Diverse Thinking Schemata Elicit Better Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  85. An Effective Router for Vision-Language Model SelectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  86. C3ache: Accelerating World Action Models with Cross Inference Chunk CacheWorld models → Embodied and robot world models +1
  87. Hardening Agent Benchmarks with Adversarial Hacker-Fixer LoopsLLM agents and tool use → Software engineering coding agents +1
  88. ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in ChinaLLM reasoning → Multimodal reasoning +1
  89. Rethinking 3D Shape Generation: Diffusion over SuperquadricsDiffusion models → 3D, point cloud and scene generation
  90. Self-Consistent Generative Paths via Admissible Random Variational TransportDiffusion models → Flow matching, time series and science
  91. AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation ModelsLLM reasoning → Spatial and embodied reasoning +1
  92. NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient AnalysisMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  93. Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency MaintenanceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  94. Generalized Rank-based Evaluation for Knowledge Graph Completion: Perspectives, Framework, and AnalysesRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  95. Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing HumanLLM agents and tool use → Agent threats, guardrails and governance
  96. Failure-Aware Refinement of Vision-Language Model for Lithography Defect DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  97. FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series ForecastingMixture-of-experts → MoE for time series and graphs
  98. Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?LLM reasoning → Multimodal reasoning +1
  99. Cheap Reward Hacking DetectionLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  100. Diffuse AI Control on Fuzzy TasksLLM safety and security → Prompt injection and agent security
  101. EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
  102. A collective capability boundary in frontier large language models on guideline-conformant and case-specific oncology decision-making
  103. FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification
  104. Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and Analysis
  105. Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
  106. CRAWO: Custom Resources for Adaptive Workload Orchestration
  107. Logic-Guided Data Extraction with Answer Set Programming and Large Language Models
  108. CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries
  109. The Jagged Global Economy: Frontier AI Unevenly Exposes National Economies
  110. AI tools in Arab University English classrooms: Looking back and forward
  111. SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents
  112. DBpedia-Enriched Company Representation for B2B Lead Recommendation
  113. Generating in the Limit with Infinitely Many Hallucinations
  114. Invisible to humans, visible to machines: a preregistered audit of Unicode fidelity across four biomedical bibliographic APIs
  115. Heterogeneous 2D/1D Signal Representation Fusion for Underwater Acoustic Modulation Recognition Under Distribution Shift
  116. Input-schema identifiability limits in physics-informed surrogates for mechanics-governed flow
  117. Distributed Model Predictive Control with Adaptive Safety Zones for Multi-Fleet Drone Operations
  118. EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis
  119. Computational Identifiability
  120. A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings
  121. Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning
  122. Avoiding Exponential Blow-Up in Distributive Lattice Submodular Minimization
  123. Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation
  124. Scribby: A Multi-Level LLM Framework for Semantic Video Analysis
  125. GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models
  126. Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling
  127. Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers
  128. History of the Muddy Children Puzzle
  129. Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization
  130. AugRelNet: Relation-Augmented Dynamics for Structure Discovery and Forecasting from Limited Data
  131. MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics
  132. Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction
  133. POPSICLE: Benchmark Datasets for Segmentation and Localization in CryoET
  134. Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning
  135. When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice
  136. Linguistically Augmented Audio Speech Data (LinguAS)
  137. YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale
  138. DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction
  139. Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph
  140. Hyperbolic Neural Population Geometry Benefits Computation
  141. Minimalist Genetic Programming
  142. ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling
  143. What Demonstration Curation Metrics Do to Your Policy
  144. Spatiotemporal Graph Transformer for 3D Neighborhood Interaction and Quality Prediction in Metal Additive Manufacturing
  145. Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing
  146. Fast Exact Nearest-Neighbor Learning for High-Frequency Financial Time Series
  147. A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport
  148. Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning
  149. Intrinsic Riemannian Cross-covariance for Manifold-valued Random Objects
  150. Exploration of Foundation Model-Based Robots in Patient and Elderly Care
  151. An Improved Generative Adversarial Network for Micro-Resistivity Imaging Logging Restoration
  152. Integral Field Unit Spectroscopy with One Fiber
  153. Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning
  154. MMClima: A Framework for Multimodal Climate Science Data and Evaluation
  155. Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising
  156. Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
  157. A Large Scale Open-Source Image and Video Dataset for Robust Wildfire Detection and Classification
  158. Beyond Locality: Feature-Boundary Auditing for OS-Integrated AI
  159. Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction
  160. FlexPath: Adapting Learned Connectivity Guidance to Path Preferences
  161. Fusing Satellite Imagery and Planimetric Maps for Cross-View Localization
  162. Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community
  163. Quality Is Not a Safety Proxy Under Quantization
  164. Compositional Generative Modeling from Decentralized Data
  165. DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation
  166. Ambiguous Strategic Classification
  167. iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision
  168. Effective Training Principles of Physical Reservoirs
  169. Robust Active Learning for Few-Shot Example Selection in Text-to-SQL
  170. FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching
  171. MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention
  172. Convergence Rates for Neural-Network Estimation with Current-Status Data
  173. Improving PET/CT-Based Whole-Body Lesion Segmentation Using Prediction Uncertainty-Augmented Models
  174. Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
  175. Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning
  176. Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
  177. Maximum Matching Accuracy: An Instance Segmentation Evaluation Metric Utilizing Globally Optimal Matching
  178. Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
  179. Predictive Assistance and the Temporal Dynamics of Exploratory Compression
  180. Decision-Making under Combinatorial Risk
  181. SoK: Colluding Adversaries in Machine Learning Pipelines
  182. Interpretable Temporal Facial-Region Motion Analysis for In-the-Wild Parkinson's Disease Video Classification
  183. CodeAlchemy: Synthetic Code Rewriting at Scale
  184. Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization
  185. Structured Adaptive Tensor Prediction for Streaming Data
  186. Divide-and-Conquer Modeling for the CTF-4-Science Lorenz Benchmark
  187. Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport
  188. Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability
  189. Importance-Aware Scheduling for High-Dimensional Hyperparameter Optimization
  190. BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts
  191. Compiling Rewrite Rules to Finite-State Transducers with the Worsening Trick
  192. Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair
  193. GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation
  194. Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
  195. SpineReport: Automated 3D Quantification and Reporting of Lumbar Spine Degeneration on MRI
  196. Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization
  197. DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment
  198. Spiking Neural Network inference on FPGAs with hls4ml
  199. ABot-Earth 0.5: Generative 3D Earth Model
  200. JGRA: Jacobian Geometry Robustness Assessment in NISQ Noise-Aware Quantum Neural Networks
  201. Geometry-Aware Anisotropic Boundary Correction for Aerodynamic Simulation
  202. HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers
  203. Temporal Context Conditioning for Seasonality-Aware Precipitation Nowcasting of High-Intensity Rainfall
  204. Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics
  205. Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads
  206. Does Normalization Choice Matter for Causal Large Time-Series Models?
  207. Deep Slice Interpolation for Reducing Through-Plane Anisotropy and Noise in Head CT
  208. Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks
  209. Integrating Out, Twice:The Open-System Case That Neural-Network Ensemble Theory Is Missing
  210. Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
  211. SPARX: Secure and Privacy-Aware Approximate CNN Acceleration with Edge RISC-V SoC
  212. GAGI: A Gini-Adjusted GDP-per-Capita Index for Distribution-Aware Macroeconomic Welfare Monitoring
  213. Anomaly Detection and Root Cause Analysis for Microservice Systems
  214. Stochastic weather generators for high-frequency wind vector time series
  215. Causally Evaluating the Learnability of Formal Language Tasks
  216. Weighted universal approximation of differentiable maps on infinite-dimensional manifolds
  217. Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
  218. Topological Neural Operators
  219. Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
  220. FASE: Fast Adaptive Semantic Entropy for Code Quality
  221. Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
  222. End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout
  223. POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction
  224. Zero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge Continuum
  225. Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution
  226. Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters
  227. SemDINO: Foundation Prior-Guided Cross-Temporal Semantic Alignment Network for Remote Sensing Change Detection
  228. Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model
  229. Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan
  230. iOSWorld: A Benchmark for Personally Intelligent Phone Agents
  231. Preserving Plasticity in Continual Learning via Dynamical Isometry
  232. Perturbative Contrastive Physical Learning
  233. Collaborative Human-Agent Protocol (CHAP)
  234. Hybrid Robustness Verification for Spatio-Temporal Neural Networks
  235. Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics
  236. Adaptive directional gradients for parameterised quantum circuits
  237. Tight Sample Complexity of Transformers
  238. Disentanglement with Holographic Reduced Representations
  239. BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling
  240. When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark
  241. What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
  242. PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
  243. Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
  244. AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis
  245. GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development
  246. SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines
  247. MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
  248. Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery
  249. Transition-Based Digital Twin Modelling for Alzheimer's Disease under Sparse Longitudinal Data
  250. Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision
  251. Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
  252. Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading
  253. Frequency-based Constrained Sampling for Interval Patterns
  254. In-Context Learning for Latent Space Bayesian Optimization
  255. From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design
  256. Muon Learns More Robust and Transferable Features than Adam
  257. Beyond Accuracy: Community Perspectives on Machine Translation
  258. A Unifying Framework for Concept-Based Representational Similarity
  259. ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset
  260. How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms
  261. FMplex: Model Virtualization for Serving Extensible Foundation Models
  262. MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding
  263. CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
  264. Data-driven discovery of governing differential equations across physical systems
  265. ATN3D: Density-Aware LiDAR-Radar Early 3D Object Detection Under Extreme Sparsity
  266. Civil Court Simulation with Large Language Models
  267. Constrained user-item allocation for e-commerce marketing campaigns
  268. Powering the Future of AI: Navigating the Trade-offs for Europe's Energy Transition and Net-Zero Goals
  269. Shape Formation for the Cooperative Transportation of Arbitrary Objects Using Multi-Agent Reinforcement Learning
  270. Next-Token Prediction Learns Generalisable Representations of Sleep Physiology
  271. Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion
  272. Assessing Sample Quality in Conditional Generation under Compositional Shift
  273. Clinically Grounded Privacy Evaluation of Medical LMs
  274. I Was Scrolling and Then I Saw a Pregnant Strawberry
  275. Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization
  276. On Choosing the μ Parameter in Gaussian Differential Privacy
  277. Code Is More Than Text: Uncertainty Estimation for Code Generation
  278. UXBench: Benchmarking User Experience in AI Assistants
  279. Efficient Minimal Solvers for Relative Pose Estimation in Autonomous Driving Applications
  280. Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions
  281. PRISM: Recovering Instruction Sets from Language Model Activations
  282. Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis
  283. OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages
  284. FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
  285. Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?
  286. From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis
  287. A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation
  288. Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy
  289. Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth
  290. Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
  291. Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages
  292. Interpretable Crisis Behavior Analysis Using Mobility and Social Media Data
  293. Emergence of Context Characteristics Sensitivity in Large Language Models
  294. Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration
  295. Investigating Calibration Challenges in Probabilistic Electricity Price Forecasting
  296. SwiftVR: Real-Time One-Step Generative Video Restoration
  297. BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference
  298. Securing Self-supervised Data Curation for Foundation Models Robustness
  299. ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
  300. LLM-Orchestrated Conformance Checking in Stroke Care Without Computer-Interpretable Guidelines
  301. Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism
  302. Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction
  303. Optical Music Recognition for Real-World Manuscripts with Synthetic Data
  304. Efficient Minimal Solvers for Visual-Inertial Relative Pose Estimation in Multi-Camera Systems
  305. Emergent alignment and the projectability of ethical personas
  306. Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitration
  307. Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting
  308. A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales
  309. DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
  310. GD-MIL: Grade-Disentangled Multiple Instance Learning for Multimodal Biochemical Recurrence Prediction in Prostate Cancer
  311. Dense Force Estimation with an Event-based Optical Tactile Sensor
  312. TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics
  313. Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization
  314. Leveraging Morphology for Historical Script Metrological Analysis
  315. A transition-density-based operator learning method for Fokker-Planck equations with various initial conditions
  316. Bayesian Selective Latent Inference for Wastewater-First Influenza Monitoring
  317. LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models
  318. Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios
  319. Toward Signing Activity Projection in Sign Language Interaction
  320. Context-Aware Deep Learning for Defect Classification in Atomic-Resolution STEM
  321. Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer
  322. AI Assurance in UK Defence: Challenges in Operationalising JSP 936
  323. Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
  324. Capacity, Not Format: Rethinking Structured Reasoning Failures
  325. Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
  326. Can Data Work be Reparative?
  327. SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths
  328. Introducing multiplex semantic networks as multifaceted representations of creative associative knowledge across multilingual samples
  329. Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
  330. vesselFM-CT: Segmenting All Blood Vessels in CT Images for System-Level Cardiovascular Analysis
  331. From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
  332. Real-time body pose non-verbal communication with a consistency-based reliability measure
  333. LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks
  334. An Opticalmechanics Framework for Dynamic Estimation of Multibody Systems
  335. Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
  336. Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle
  337. RT-SDGOD: Real-Time Single-Domain Generalized Object Detection
  338. Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
  339. ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
  340. Beyond Humans: Multispecies Animal Face Recognition Using Transfer Learning
  341. In-Context Learning for the Imputation of Public Opinion Data with Large Language Models
  342. Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classification
  343. IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal
  344. Thresholded Local Hyper-Flow Diffusion
  345. How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?
  346. Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding
  347. A Universal Dense Football Event Representation Based on TabTransformer
  348. TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
  349. Machine-Learning Emulation of Satellite Greenhouse Gas Retrievals: Stability over Time
  350. PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
  351. N"ushuVoice: Reviving the Voice of Endangered N"ushu with Pitch-Aware Text-to-Speech
  352. Virtual-point-based Solutions to Handle Generalized Absolute Pose Problem
  353. One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems
  354. Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
  355. Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation
  356. ERBench: A Benchmark and Testsuite for Equation Discovery Algorithms
  357. Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention
  358. Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design
  359. See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning
  360. Self-supervised Learning Matters: A Simple Ensemble Solution for Micro-Gesture Recognition
  361. A practical probabilistic framework for deformable image registration uncertainty in radiotherapy dose propagation
  362. DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
  363. SOMA: From Surface Observations to Muscle Anatomy
  364. Proposal Refinement for Few-Shot Object Detection
  365. EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
  366. Orange Lab: Lowering Barriers to Data Mining through Embedded Interactive Workflows
  367. Trustworthy Smart Fabs via Professional Proxies: Scaling Safe and Sustainable by Design (SSbD) through Industrial Data Spaces
  368. Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline
  369. Minimal Solvers for Full-DoF Motion Estimation from Asynchronous Differential SfM
  370. SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C
  371. Event-driven dynamic trajectories reconstruction and measurement of mechanical parameters for fragments
  372. Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads
  373. Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards
  374. Trajectory Optimization in Single and Dual-UAV Bearing-Only Target Localization
  375. CP4D: Compositional Physics-aware 4D Scene Generation
  376. Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA
  377. Claude Code-Driving Scenario Mining for the Argoverse 2 Challenge
  378. CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon
  379. IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation
  380. Vision-Language Guided Hyperspectral Object Tracking via Semantics Fusion and Contextual Template Updating
  381. Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
  382. Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation
  383. Crop Recommendation and Agricultural Query Answering System Using Spatio-Temporal Graph Neural Networks and Hybrid Retrieval Augmentation
  384. SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance
  385. OmniGen-AR: AutoRegressive Any-to-Image Generation
  386. Improved Convergence Analysis of Topology Dependence in Decentralized SGD
  387. Explicit Representation Alignment for Multimodal Sentiment Analysis
  388. CAMF-Det: Closure-Aware Multimodal Fusion for LiDAR-Camera 3D Object Detection on UAV Platforms
  389. DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction
  390. A Geometric Framework for Absolute Pose and Velocity Estimation with Event Cameras
  391. Steganography Without Modification: Hidden Communication via LLM Seeds
  392. From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
  393. An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification
  394. Optimizing Energy-based Neural Network Training with Coherent Ising Machine
  395. MAAM: Anchor-Preserving Compression and Contextual Calibration for Chinese Discriminatory Language Detection
  396. Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning
  397. Illumination-Invariant Anomaly Detection for Sub-Canopy UAV Multispectral Point Clouds
  398. RAM: Reachability Across Morphologies
  399. Alcmean's: Unsupervised community detection using local Laplacian, automatic detection of the number of centers
  400. From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
  401. Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts
  402. DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling
  403. Edge-Constrained UAV Small-Object Detection with P2 Enhancement and Quantum-Inspired Lightweight Structure Search
  404. Neural Legendre-Fenchel transform with Hessian Preconditioning
  405. REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance
  406. Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
  407. OnlyDense: Reduced-Order Modeling for Lagrangian simulation
  408. MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
  409. Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
  410. Data augmented bootstrap: Unifying confidence interval construction by approximate invariance
  411. Families of Control-Cost-Parametrized Inverse-Optimal Universal Stabilizers
  412. Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models
  413. Culturally-Aware AI for Cross-Boundary Community Learning: Undergraduate Innovation at the Intersection of Computation and Design
  414. Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents
  415. Leveraging NeRF-Rendered Images for 3D Gaussian Splatting
  416. Frequency Decoupled Framework for Screen Content Image Super-Resolution
  417. SafeRun: Enabling Determinism in LLM Planning for Running
  418. Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI
  419. Personal Salience: Highlighting Is Social, but Individuality Lives in Selection
  420. Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level
  421. Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin
  422. Sustainability and Artificial Intelligence: Necessary, Challenging, and Promising Intersections
  423. LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)
  424. Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees
  425. Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning
  426. LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization
  427. Structure-Aware Modeling of Multiple-Choice Questions Improves Automatic Difficulty Estimation
  428. Beyond Neural Collapse: Task-Intrinsic Geometry Governs Neural Representations in Modular Arithmetic
  429. Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
  430. EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
  431. Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
  432. A systematic investigation of molecular encoding methods for drug property predictions across neural network and Transformer encoder-based model
  433. CARE: A Conformal Safety Layer for Medical Summarization
  434. From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models
  435. From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model
  436. Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls
  437. PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
  438. Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)
  439. PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection
  440. Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory
  441. From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
  442. PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models
  443. PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images
  444. GeoMetric: Injecting Metric Geographic Structure into Worldwide Image Geo-Localization
  445. DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance
  446. Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
  447. Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structured Electronic Medical Records
  448. Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
  449. A multi-agent system for spine MRI report generation from multi-sequence imaging