mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 27 May 2026

686 papers

  1. Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong ModelsLLM reasoning → Test-time compute and efficient thinking
  2. DocArena: Turning Raw Documents into Controllable Training Environments for Document Search AgentsLLM agents and tool use → Web, search, and research agents
  3. Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLMEfficient LLM inference and serving → Diffusion LLM and MoE inference
  4. LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein AlignmentVision-language-action models → 3D and spatial-aware VLA
  5. From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUsLLM agents and tool use → General LLM agent frameworks and benchmarks
  6. Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory ConditionsWorld models → Latent predictive world models
  7. World Models for Robotic Manipulation: A SurveyWorld models → Embodied and robot world models
  8. Evolving to the Aesthetics of a Vision-Language ModelMultimodal LLMs / vision-language models → Image editing and quality assessment
  9. Lightweight SAR Ship Detection via Contrastive DistillationKnowledge distillation → Detection and dense prediction distillation
  10. The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  11. UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  12. Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction CorrectionLLM reasoning → Knowledge- and tool-augmented reasoning +1
  13. RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable DomainsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  14. CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  15. SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication RecommendationLLM agents and tool use → Medical and scientific domain agents
  16. Toward User Preference Alignment in LLM Recommendation via Explicit Context FeedbackLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  17. Multi-Resolution End-to-End Deep Neural Network for Optimizing Latency-Accuracy Tradeoff in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  18. Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU MemoryMixture-of-experts → Efficient MoE training and inference systems
  19. Governing Technical Debt in Agentic AI SystemsLLM agents and tool use → Software engineering coding agents
  20. When and How Long? The Readout-Mediator Angle in Temporal ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  21. The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  22. A Minimal Bifurcation Model of Load Imbalance in a Softmax Mixture-of-Experts RouterMixture-of-experts → Expert routing strategies
  23. PRO-CUA: Process-Reward Optimization for Computer Use AgentsLLM agents and tool use → GUI and mobile agents +2
  24. Beyond Consensus: Trace-Level Synthesis in Mixture of AgentsLLM agents and tool use → Social simulation and multi-agent debate
  25. ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
  26. OISD: On-Policy Internal Self-Distillation of Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  27. The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial PressureLLM reasoning → Prompting and chain-of-thought reasoning
  28. Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAGRetrieval-augmented generation → Medical and biomedical RAG
  29. The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data PlaneLLM agents and tool use → Agent threats, guardrails and governance
  30. Bridging the Sim-to-Real Gap in Reinforcement Learning-Based Industrial Dispatching through Execution SemanticsDeep reinforcement learning methods → RL for energy, networks and operations
  31. Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex TextDeep reinforcement learning methods → RL training of language and agent models
  32. Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  33. Diffusion Model-Based Data Assimilation for Real-World Energy Consumption ForecastingDiffusion models → Flow matching, time series and science
  34. Robust and Efficient Guardrails with Latent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  35. Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive VariationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  36. Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational EquivalenceLLM agents and tool use → Software engineering coding agents
  37. Moment Matching Q-LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  38. Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator LearningWorld models → Latent dynamics models and model-based RL +1
  39. When Models Disagree: Rethinking LLM Evaluation for Public Comment AnalysisLLM reasoning → Reasoning benchmarks and evaluation
  40. Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone EmulationDiffusion models → Inverse problems and image restoration
  41. Label-Free Reinforcement Learning via Cross-Model EntropyDeep reinforcement learning methods → RL training of language and agent models
  42. Taxonomy-Targeted Error Generation for Quantitative ReasoningLLM reasoning → Mathematical reasoning
  43. FedQHD: Closed-Form Function-Space Federated Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  44. FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning BenchmarksLLM reasoning → Mathematical reasoning
  45. Measuring Real-World Prompt Injection Attacks in LLM-based Resume ScreeningLLM safety and security → Prompt injection and agent security
  46. GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  47. VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element AnalysisLLM agents and tool use → Multimodal and embodied agents
  48. Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypesLLM agents and tool use → Web, search, and research agents
  49. CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language ModelsLLM reasoning → Test-time compute and efficient thinking
  50. Agentic AI for Gravitational Wave Data Analysis: A Head-to-Head Comparison of Coding Agents Executing a Matched Filter Pipeline on Einstein Telescope Simulated DataLLM agents and tool use → Web, search, and research agents
  51. AIRGuard: Guarding Agent Actions with Runtime Authority ControlLLM agents and tool use → Agent threats, guardrails and governance
  52. Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  53. Hallucination Detection-Guided Preference Optimization for Clinical SummarizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  54. Orthogonal Concept Erasure for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  55. Spectral Guidance for Flexible and Efficient Control of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  56. Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language ModelsMechanistic interpretability → SAE features and their applications
  57. Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  58. Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in AmapLLM reasoning → Spatial and embodied reasoning
  59. From Pixels to Words -- Towards Native One-Vision Models at ScaleMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. Do VLMs Align Better with Humans than LLMs during Natural Reading?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  61. Gamma-World: Generative Multi-Agent World Modeling Beyond Two PlayersWorld models → Video-generation world models and simulators
  62. Self-Improving Language Models with Bidirectional Evolutionary SearchLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  63. Calibrating Conservatism for Scalable OversightLLM agents and tool use → Agent threats, guardrails and governance
  64. OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured RecalibrationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  65. HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  66. Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  67. Skill-Conditioned Gated Self-Distillation for LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  68. Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data RetrievalLLM agents and tool use → Web, search, and research agents
  69. The Abstraction Gap in Vision-Language Causal ReasoningLLM reasoning → Multimodal reasoning +1
  70. Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use AgentsLLM agents and tool use → Software engineering coding agents
  71. Agent Explorative Policy Optimization for Multimodal Agentic ReasoningLLM reasoning → Multimodal reasoning +2
  72. Rethinking Memory as Continuously Evolving ConnectivityLLM reasoning → Reasoning for agents, planning and code +1
  73. CORE: Contrastive Reflection Enables Rapid Improvements in ReasoningLLM reasoning → Test-time compute and efficient thinking
  74. Self-Prophetic Decoding to Unlock Visual Search in LVLMsLLM reasoning → Multimodal reasoning +1
  75. Imitation Learning for Robot Assistance in Open Surgery: A Multi-Policy Evaluation on Suture FollowingOffline RL and imitation learning from data → Safe offline RL
  76. Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code RequestsLLM safety and security → Safety alignment, refusal and guardrails
  77. MemTrace: Tracing and Attributing Errors in Large Language Model Memory SystemsLLM reasoning → Test-time compute and efficient thinking
  78. Execution and assessment of agentic influence operations in simulated social networksLLM agents and tool use → Social simulation and multi-agent debate
  79. Multi-Adapter Representation Interventions via Energy CalibrationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  80. LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?LLM agents and tool use → Web, search, and research agents
  81. Thinking as Compression: Your Reasoning Model is Secretly a Context CompressorLLM reasoning → Test-time compute and efficient thinking +1
  82. Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion ModelsDiffusion models → Inverse problems and image restoration
  83. The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-SymbolicLLM reasoning → Mathematical reasoning
  84. TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
  85. OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement LearningDiffusion models → Video generation +1
  86. VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web CorporaLLM agents and tool use → Multimodal and embodied agents
  87. DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel ExecutionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  88. Optimal Data Acquisition for Reinforcement Learning: A Large Deviations PerspectiveDeep reinforcement learning methods → RL theory and sample complexity
  89. Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety DetectionMechanistic interpretability → Activation steering methods
  90. Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model EditingMechanistic interpretability → Sparse autoencoder training and evaluation
  91. The Ethics of LLM Sandbox and Persona DynamicsLLM safety and security → Safety alignment, refusal and guardrails
  92. MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill EvolutionLLM agents and tool use → Agent threats, guardrails and governance
  93. GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal ReconstructionRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  94. Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV SparsityEfficient LLM inference and serving → KV cache optimization
  95. PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
  96. Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM WatermarkingLLM safety and security → Watermarking generated content and models
  97. Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using AgentsLLM agents and tool use → GUI and mobile agents
  98. Random Process Flow Matching: Generative Implicit Representations of Multivariate Random FieldsDiffusion models → Flow matching, time series and science
  99. LACUNA: Safe Agents as Recursive Program HolesLLM agents and tool use → Agent threats, guardrails and governance
  100. Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
All 686
  1. JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  2. Adaptive Multimodal Agents-Based Framework for Automatic Workflow ExecutionLLM agents and tool use → Software engineering coding agents
  3. Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning CapabilityLLM reasoning → Reasoning benchmarks and evaluation
  4. Transformers Provably Learn to Internalize Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  5. Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online NewsLLM agents and tool use → Social simulation and multi-agent debate
  6. Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic EvaluationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  7. Technical Report: Exploring the Emerging Threats of the Agent Skill EcosystemLLM safety and security → Prompt injection and agent security
  8. SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving
  9. Continual Model Routing in Evolving Model HubsMixture-of-experts → Expert routing strategies
  10. Actor-Identifier-Critic Reinforcement Learning for Adaptive Model-Free Optimal Control of Nonlinear Systems with Stochastic Packet DropoutsDeep reinforcement learning methods → RL theory and sample complexity
  11. Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit CompressionMechanistic interpretability → SAE features and their applications
  12. Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design PatternsLLM reasoning → Test-time compute and efficient thinking
  13. Soft-SVeRL: Self-Verified Reinforcement Learning with Soft RewardsDeep reinforcement learning methods → RL training of language and agent models
  14. A Matter of TASTE: Improving Coverage and Difficulty of Agent BenchmarksLLM agents and tool use → Tool learning and function calling
  15. Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM ActivationsMechanistic interpretability → Steering and probing for LLM safety
  16. Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  17. GEM: Generative Supervision Helps Embodied IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  18. DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous DrivingWorld models → World models for autonomous driving +2
  19. GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar ReselectionLLM agents and tool use → GUI and mobile agents
  20. Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using AgentsLLM reasoning → Reasoning for agents, planning and code
  21. Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question AnswerabilityRetrieval-augmented generation → RAG pipeline design and evaluation
  22. Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code GenerationLLM agents and tool use → Software engineering coding agents
  23. SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMsLLM reasoning → Spatial and embodied reasoning
  24. ProvMind: Provenance-grounded reasoning for materials synthesisLLM reasoning → Clinical and biomedical applications
  25. Mag-VLA: Vision-Language-Action Model for Bimanual Magnetically Actuated Microrobot ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA
  26. Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency TrainingLLM reasoning → Reasoning for agents, planning and code +1
  27. Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
  28. REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation DetectionMixture-of-experts → Multimodal MoE models
  29. AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient UpdatesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  30. Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  31. Latent Diffusion for Missing DataDiffusion models → Flow matching, time series and science
  32. Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution
  33. VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMsLLM reasoning → Clinical and biomedical applications
  34. DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy PrefixesLLM reasoning → Reinforcement learning for reasoning +1
  35. Efficient Post-training of LLMs for Code Generation With Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  36. HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMsLLM reasoning → Test-time compute and efficient thinking
  37. ADWIN: Adaptive Windows for Horizon-Aware On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  38. You Live More Than Once: Towards Hierarchical Skill Meta-EvolvingLLM agents and tool use → Agent skill learning and evolution
  39. FABSVer: Faster Training and Better Self-Verification for LLM Mathematical ReasoningLLM reasoning → Mathematical reasoning
  40. Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMsLLM reasoning → Reinforcement learning for reasoning +1
  41. Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation LearningOffline RL and imitation learning from data → Imitation learning methods +1
  42. From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligenceLLM agents and tool use → Web, search, and research agents
  43. CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes VerdictLLM agents and tool use → Social simulation and multi-agent debate
  44. LEIA: Learned Environment for Interactive Architected MaterialsWorld models → Latent predictive world models
  45. Risk-Controlled Lean-as-Judge for Natural-Language Mathematical ReasoningLLM reasoning → Mathematical reasoning
  46. Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function ApproximationDeep reinforcement learning methods → RL theory and sample complexity
  47. Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction RefinementLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock MarketsLLM agents and tool use → Financial trading and forecasting agents
  49. Plan Before Search: Search Agents Need PlanLLM reasoning → Knowledge- and tool-augmented reasoning +2
  50. FedMPT: Federated Multi-label Prompt Tuning of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  51. When Discourse Pressures Conflict: Information Structure in Vision-Language Model OutputsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  52. Inpainting-Style Conditional Diffusion for Multivariable Time Series ForecastingDiffusion models → Flow matching, time series and science
  53. Multi-Agent LLM-based Metamorphic Testing for REST APIsLLM agents and tool use → Software engineering coding agents
  54. Hybrid Neural World ModelsWorld models → Latent predictive world models
  55. Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry ApproachLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  56. Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts ModelsMixture-of-experts → Expert routing strategies
  57. Revisiting Anthropomorphic Reflection Markers in Large Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  58. From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  59. How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM ServingMixture-of-experts → Efficient MoE training and inference systems +1
  60. Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought DistillationLLM reasoning → Clinical and biomedical applications +1
  61. Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVRLLM reasoning → Reinforcement learning for reasoning
  62. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient EstimationDeep reinforcement learning methods → RL training of language and agent models
  63. CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  64. AtomComposer: Discovering Chemical Space from First Principles with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  65. Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial ReasoningWorld models → World models for language agents +1
  66. Commit to the Bit: Reactive Reinforcement Learning Done RightDeep reinforcement learning methods → RL theory and sample complexity
  67. Global Policy-Space Response Oracles for Two-Player Zero-Sum GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  68. GUI Agents for Continual Game GenerationLLM agents and tool use → Software engineering coding agents
  69. IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder CoverageLLM reasoning → Reinforcement learning for reasoning +1
  70. Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression SegmentationSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  71. PIRS: Physics-Informed Reward Shaping for SAC-Based Building Energy ManagementDeep reinforcement learning methods → RL for energy, networks and operations
  72. ProgVLA: Progress-Aware Robot Manipulation Skill LearningVision-language-action models → Reinforcement learning and post-training +1
  73. VidPrism: Heterogeneous Mixture of Experts for Image-to-Video TransferMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  74. PhAME: Phenotype-Aware Molecular Editing via Latent DiffusionDiffusion models → Flow matching, time series and science
  75. When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?LLM reasoning → Reasoning for agents, planning and code +1
  76. Analyzing Quality-Latency-Resource Trade-offs in a Technical Documentation RAG Assistant Using LoRA AdaptationRetrieval-augmented generation → RAG pipeline design and evaluation
  77. Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual ClassifiersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  78. Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel LineagesLLM agents and tool use → Software engineering coding agents
  79. Pruning and Distilling Mixture-of-Experts into Dense Language ModelsMixture-of-experts → MoE large language models
  80. Refining Multidimensional Video Reward Models via Disentangled Influence FunctionsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  81. Plant, Persist, Trigger: Sleeper Attack on Large Language Model AgentsLLM agents and tool use → Agent threats, guardrails and governance
  82. Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual ReasoningLLM reasoning → Audio-language model reasoning +1
  83. Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature ExtensionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  84. Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient CalibrationLLM reasoning → Reinforcement learning for reasoning +1
  85. BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German LawLLM reasoning → Reasoning for agents, planning and code
  86. When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  87. Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based RecommendationRetrieval-augmented generation → RAG for recommendation +2
  88. MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga GenerationLLM agents and tool use → Multimodal and embodied agents
  89. DebFilter: Eradicating Biases Stashed in ValueMultimodal LLMs / vision-language models → Social bias and fairness in VLMs +1
  90. Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal ReasoningLLM reasoning → Multimodal reasoning
  91. OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  92. Off-Policy Learning to Reason Works Because It Is More Pessimistic Than You ThinkLLM reasoning → Reinforcement learning for reasoning
  93. Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU ActivationsMechanistic interpretability → SAE features and their applications
  94. Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  95. Self-Consistency via Marginal SharpeningLLM reasoning → Test-time compute and efficient thinking
  96. Data-Efficient On-Policy Distillation for Automatic Speech RecognitionKnowledge distillation → Speech and audio distillation
  97. Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  98. Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  99. SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding AgentsLLM agents and tool use → Software engineering coding agents +1
  100. LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  101. MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated ContentLLM agents and tool use → Agent threats, guardrails and governance +1
  102. CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  103. Language model agents show in-group trust bias invisible to standard behavioural auditsLLM agents and tool use → Social simulation and multi-agent debate
  104. Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation PredictionWorld models → Medical and surgical world models
  105. Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  106. Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level RectificationLLM agents and tool use → Agent threats, guardrails and governance
  107. Training Stratigraphy: Persistent Behavioral Artifacts in Large Language Models Observed Through Longitudinal AI-Human InteractionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  108. Examining Agents' Bias Amplification versus Suppression in Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  109. ICAN-Deploy: Identity-Stable Canary Deployment for Safety-Critical Embodied AgentsLLM agents and tool use → Agent threats, guardrails and governance
  110. ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  111. SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about LaughterLLM reasoning → Multimodal reasoning
  112. VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception HijackingVision-language-action models → Safety and adversarial attacks
  113. MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram ParsingLLM reasoning → Clinical and biomedical applications +1
  114. SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data PoisoningRetrieval-augmented generation → Privacy and security of RAG +1
  115. StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative EnrichmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  116. AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based AgentLLM agents and tool use → Agent threats, guardrails and governance
  117. Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient InformationLLM reasoning → Test-time compute and efficient thinking
  118. ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response ReplayEfficient LLM inference and serving → Efficient reasoning and agent inference
  119. BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  120. CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent PlanningLLM agents and tool use → Multimodal and embodied agents
  121. Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  122. Extracting Small Translation Specialists from LLMs by Aggressively Pruning ExpertsMixture-of-experts → MoE large language models
  123. Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance ScalesDiffusion models → Image generation, text-to-image and editing
  124. SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data SelectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  125. BPPO: Binary Prefix Policy Optimization for Efficient GRPO-Style Reasoning RL with Concise ResponsesLLM reasoning → Reinforcement learning for reasoning
  126. The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter UpdatesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  127. ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across DomainsLLM reasoning → Prompting and chain-of-thought reasoning +1
  128. KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural RisksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  129. MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  130. Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-TrainingLLM reasoning → Test-time compute and efficient thinking
  131. Integrated and Cross-Architecture Interpretation of LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  132. Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  133. ResearchMath-14K: Scaling Research-Level Mathematics via AgentsLLM agents and tool use → Educational agents and math problem solving
  134. Tool Forge: A Validation-Carrying Toolchain for Governed Agentic ExecutionLLM agents and tool use → Tool learning and function calling
  135. Learning to Assign Prediction Tasks to Agents with Capacity ConstraintsLLM agents and tool use → Agent skill learning and evolution
  136. Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  137. Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization PressureLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  138. AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task ScenariosLLM agents and tool use → Tool learning and function calling
  139. Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination MitigationLLM reasoning → Hallucination detection and mitigation +1
  140. Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned DampingDiffusion models → Inverse problems and image restoration
  141. KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  142. ABot-OCR Technical ReportMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  143. Continual Learning in Modern Hopfield Networks with an Application to Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  144. Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent ResponsesDiffusion models → Discrete and text diffusion
  145. Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture PriorsKnowledge distillation → General knowledge distillation methods
  146. The Shape of Overthinking: Backtracking Bursts in Long Reasoning TracesLLM reasoning → Test-time compute and efficient thinking
  147. Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene ReasoningLLM reasoning → Multimodal reasoning +2
  148. ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image ReasoningLLM reasoning → Multimodal reasoning +1
  149. Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive RepresentationsMechanistic interpretability → Probing deception, bias and beliefs
  150. Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  151. Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  152. Beyond Similarity: Task-Aligned Retrieval for Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  153. SANTS: A State-Adaptive Scheduler for World Action ModelsWorld models → Embodied and robot world models
  154. Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential PlanningLLM reasoning → Reasoning for agents, planning and code +1
  155. GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned OptimizationLLM reasoning → Reinforcement learning for reasoning
  156. When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?LLM reasoning → Reasoning for agents, planning and code +2
  157. Structure-Guided Visual Perturbation Neutralization for LVLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  158. Harness-Bench: Measuring Harness Effects across Models in Realistic Agent WorkflowsLLM agents and tool use → Software engineering coding agents
  159. Rethinking Video-Language Model from the Language Input PerspectiveLLM reasoning → Multimodal reasoning
  160. OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  161. Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation ParadigmSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  162. Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference OptimizationLLM reasoning → Multimodal reasoning +1
  163. AI Research Agents Narrow Scientific ExplorationLLM agents and tool use → Web, search, and research agents
  164. The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse LanguagesLLM reasoning → Prompting and chain-of-thought reasoning
  165. Decoupled Training with Local Reinforcement Fine-Tuning in Federated LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  166. SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit AssignmentLLM agents and tool use → Agent skill learning and evolution
  167. UniACE: A Unified Framework for Evaluating LLM Agentic CapabilitiesLLM agents and tool use → General LLM agent frameworks and benchmarks
  168. FinBoardBench: Benchmarking Dynamic Wealth Management and Strategic Financial Reasoning of LLMs via Board Game SimulationsLLM reasoning → Reasoning for agents, planning and code
  169. Towards Unified Vision-Language Models with Incomplete Multi-Modal InputsLLM reasoning → Multimodal reasoning +1
  170. Reflective Dialogue between Teacher and Solver Agents for Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  171. VibeSearchBench: Benchmarking Long-horizon Proactive Search in the WildLLM agents and tool use → Web, search, and research agents
  172. Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?LLM agents and tool use → Web, search, and research agents
  173. Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model FaithfulnessLLM agents and tool use → General LLM agent frameworks and benchmarks
  174. AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI ModelsLLM agents and tool use → Web, search, and research agents
  175. GRADE: Generalizable Reasoning-Aware Dialogue Evaluation for AI TutorsLLM reasoning → Mathematical reasoning
  176. FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment ResearchLLM agents and tool use → Financial trading and forecasting agents
  177. C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis ReasoningLLM reasoning → Clinical and biomedical applications +1
  178. MolLingo: Molecule-Native Representations for LLM-Powered Scientific AgentsLLM reasoning → Clinical and biomedical applications +1
  179. When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  180. FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code GenerationMixture-of-experts → MoE large language models
  181. EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QALLM reasoning → Reinforcement learning for reasoning
  182. Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax ApproachOffline RL and imitation learning from data → Inverse reinforcement learning +1
  183. MRMMIA: Membership Inference Attacks on Memory in Chat AgentsLLM safety and security → Membership inference attacks
  184. Revealing Algorithmic Deductive Circuits for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  185. Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM SecurityLLM safety and security → Jailbreaking
  186. EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using AgentsLLM reasoning → Spatial and embodied reasoning +1
  187. ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer InterventionsMechanistic interpretability → Sparse autoencoder training and evaluation
  188. Turning Video Models into Generalist Robot PoliciesVision-language-action models → Human-video and latent-action pretraining
  189. Residualized Temporal Sparse Autoencoders for Interpreting Diffusion ModelsDiffusion models → Diffusion foundations and sampling +1
  190. Density-aware Sample-specific AttackLLM safety and security → Backdoor and data poisoning attacks
  191. SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic DenoisingLLM reasoning → Multimodal reasoning
  192. A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress TestRetrieval-augmented generation → RAG pipeline design and evaluation
  193. A Query Engine for the AgentsLLM reasoning → Reasoning for agents, planning and code +1
  194. WIRE: Profiling Witnessed Within-Policy Instruction Collisions in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  195. Large Models for Battery Prognostics and Health Management: A Review and Future Roadmap
  196. DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph
  197. ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control
  198. CNM-BERT: A Drop-In Structural Embedding for Chinese Characters via Ideographic Description Sequences
  199. To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussions
  200. Semi-Supervised Text-Attributed Graph Distillation
  201. Dot-Flik: A Scalable Edge AI Architecture for Distributed Insect Monitoring
  202. Human Decision-Making with AI Assistance under Correlated Features
  203. A Geometric Profile of Semantic Information in Text: Frame-Conditional Uniqueness and a Trade-Off Triangle for Scalar Summaries
  204. Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows
  205. Information-Geometric Optimization on Spheres
  206. The Routing Plateau: Understanding the Accuracy Limits of LLM Routers
  207. Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach
  208. Closed-Loop Molecular Design with Calibrated Deference
  209. Enhancing BiGRU with a KAN Block for Legal Document Classification and Summarization
  210. Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
  211. ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression
  212. General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
  213. VDSB-GWSyn: Diffusion Schr"odinger Bridge for Controllable and Anatomically Feasible Guidewire Synthesis in Coronary Angiography
  214. Project SPARROW and the Future of Conservation Technology
  215. Bayesian Multiplicity Correction in the Probabilistic Forward Stepwise Framework
  216. Slogans or Stance? A Label-Light Diagnostic for Entrepreneurial-Discourse Measurement on Chinese SOE Speeches
  217. Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
  218. TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
  219. Sustainable Metal-Organic Framework Water Harvesters in the Artificial Intelligence Era
  220. Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents
  221. Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictions
  222. Domain-Informed Representation for Evolutionary Sieving in Integral and Module Lattices
  223. Evolutionary Refinement of Generative Graph Topologies: A Hybrid WGAN-GA Approach
  224. PROTOCOL: Late Interaction Retrieval for Protein Homolog Search
  225. Parallax: Parameterized Local Linear Attention for Language Modeling
  226. Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
  227. Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
  228. Real-rootedness of the Poincar'e polynomials of overlinemathcal M0,n: an AI-assisted proof
  229. Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning
  230. Certified Adaptive Refresh: Anytime-Valid Monitoring for Federated Conformal RAG
  231. Eulerian Gaussian Splatting using Hashed Probability Pyramids
  232. Apertus LLM Family Expansion via Distillation and Quantization
  233. Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
  234. unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
  235. Bridging Chemists and AI: An Expert-Augmented Framework for Interpretable Route Evaluation
  236. GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
  237. Model Merging by Output-Space Projection
  238. Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
  239. GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals
  240. Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration
  241. Lightweight Complementary-Cue Fusion for Robust Video Face Forgery Detection
  242. A Deep Learning Iterative Framework for Sentinel-1 Stripmap Enhancement Based on Azimuth Doppler Decomposition
  243. Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules
  244. Accelerating HEVC Intra Partitioning via a CNN-Hierarchical Attention Transformer Hybrid
  245. Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies
  246. SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers
  247. Parallel Adaptive Multi-Objective Evolutionary Learning of Discretized Bayesian Network Classifiers for Clinical Data
  248. Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching
  249. LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English
  250. Differentiable Belief-based Opponent Shaping
  251. Practitioner Beliefs and Behaviors in AI-Enhanced Education: DOT Framework Survey Evidence
  252. Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
  253. Mind Your Tone: Does Tone Alter LLM Performance?
  254. Designing Active Tether-Net Systems for Space Debris Capture with Graph-Learning-Aided Mixed-Combinatorial Optimization
  255. Adopt neq Adapt: Longitudinal Analyses of LLM Conversations in the Wild
  256. Trajectory Constraints for Imaging Inverse Problems
  257. Causal Intelligence for Constraint-Aware Intervention Design to Induce State Transitions
  258. LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers
  259. Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Moments
  260. Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
  261. BEAMS: Benchmarking and Evaluating AI for Modeling and Simulation
  262. Learning Robust and Task-Invariant Functional Representation from fMRI through Siamese Self-Supervised Learning
  263. The Hamilton-Jacobi Theory of Deep Learning
  264. Manifold-based Algorithms for the Hadamard Decomposition
  265. Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
  266. A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio
  267. Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
  268. The Trust Paradox: How CS Researchers Engage LLM Leaderboards
  269. Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment
  270. Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions
  271. Optimal Rates for Differentially Private Hypothesis Testing with E-values
  272. Neural Scaling Laws for Jet Generation
  273. Conf-Gen: Conformal Uncertainty Quantification for Generative Models
  274. When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
  275. Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems
  276. Sequential Physics-Constrained Neural Operator Forward Modeling for the textitNorne Reservoir System
  277. Quantum-Enhanced Adversarial Robustness in Artificial Intelligence
  278. Review Arcade: On the Human Alignment and Gameability of LLM Reviews
  279. Saddle Networks: Structure-Preserving Architectures for Convex-Concave Functions
  280. Context Distillation as Latent Memory Management
  281. Computational Modeling of Antibody-Antigen Complexes: PLM-Based and MSA-Based Approaches
  282. PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
  283. Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation
  284. HarmoVid: Relightful Video Portrait Harmonization
  285. Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization
  286. AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
  287. Personal Visual Memory from Explicit and Implicit Evidence
  288. CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
  289. Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay
  290. Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions
  291. Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
  292. Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
  293. Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
  294. SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks
  295. CubePart: An Open-Vocabulary Part-Controllable 3D Generator
  296. Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples
  297. Inference-Native Zeroth-Order Optimization for LLMs
  298. Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
  299. Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity
  300. Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context
  301. Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text
  302. BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
  303. SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping
  304. Utility-Aware Multimodal Contrastive Learning for Product Image Generation
  305. AlphaTransit: Learning to Design City-scale Transit Routes
  306. Beyond Lipschitz: Data-Driven Robustness via Discrete Modulus of Continuity
  307. How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures
  308. OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol
  309. IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents
  310. Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study
  311. Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI
  312. Understanding Generalization and Forgetting in In-Context Continual Learning
  313. Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
  314. A Fresh Look at Lamarckian Evolution and the Baldwin Effect
  315. Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?
  316. Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
  317. Latent-Conditioned Parameterized Quantum Circuits as Universal Approximators for Distributions over Quantum States
  318. History-aware adaptive reduced-order models via incremental singular value decomposition
  319. AI in the Workplace: The Impact of AI on Perceived Job Decency and Meaningfulness
  320. Optimal ridge regularization revisited
  321. Sense Representations Are Inducible Interfaces
  322. An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning
  323. Applications of temporal graph learning for predicting the dynamics of biological systems
  324. AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
  325. GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
  326. Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translation
  327. The Attentional White Bear Effect in Transformer Language Models
  328. Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
  329. EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
  330. When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models
  331. A Multiscale Kinetic Framework for Image Segmentation: From Particle Systems to Continuum Models
  332. Measuring Form and Function in Language Models
  333. Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization
  334. Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
  335. Internally Referenced Low-Light Enhancement
  336. Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification
  337. Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration
  338. Dark Quest II: A Wide-Coverage Neural Network Emulator of the Nonlinear Matter Power Spectrum Across Extended Cosmologies
  339. Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method
  340. PLS in the Mirror of Self-Attention
  341. Models That Know How Evaluations Are Designed Score Safer
  342. Thinned Mean Field Langevin Dynamics
  343. Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation
  344. Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization
  345. MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation
  346. A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
  347. A Conflict-Aware Penalty and Statistical Loss Framework for Balancing Modalities and Enhancing Stability in Multimodal Sentiment Analysis
  348. Efficient Pre-Training of LLMs through Truncated SVD Representations
  349. Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs
  350. A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models
  351. Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration
  352. High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models
  353. Resolution-free neural surrogates for geometric parameterization and mapping with spatially varying fields
  354. SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints
  355. Cultural Binding Heads in Language Models
  356. Semi-Supervised Hypothesis Testing by Betting on Predictions
  357. Stabilizing distribution-free probabilistic forecasts
  358. Entropy-aware Masking for Masked Language Modeling
  359. Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection
  360. ClinicalEncoder26AM: A Multlilingual Diagnosable ColBERT Model; Evidences from the MultiClinNER Shared Task
  361. GS-FUSE: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial Forecasting
  362. Stochastic Gradient Descent with Momentum is Algorithmically Stable
  363. Conservative neural posterior estimation via distributionally robust training
  364. Learning Theory of the SVRG: Generalization and Convergence Analysis
  365. On Compositional Learning Behaviours in Formal Mathematics
  366. Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
  367. Benchmarking AI for low-resource contexts: Thinking beyond leaderboards
  368. Universal Time Series Generation with Neural Controlled Differential Equations
  369. Fitting Unknown Number of Hyperplanes with Manifold Optimization
  370. Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
  371. The Decision to Verify: How Warmth and User Characteristics Shape Reliance on Conversational Agents for Information Search
  372. Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
  373. A new semantically annotated corpus with syntactic-semantic and cross-lingual senses
  374. DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing
  375. Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models
  376. Comonadic Morphophonology: A Compositional Framework for Context-Dependent Morphological Rules in Finnish
  377. From Learning Resources to Competencies: LLM-Based Tagging with Evidence and Graph Constraints
  378. SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation
  379. The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment
  380. Diffusion Large Language Models for Visual Speech Recognition
  381. GONDOR to the Rescue: Satisficing Planning with Low Memory
  382. BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
  383. Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer
  384. Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
  385. Bayesian Gated Non-Negative Contrastive Learning
  386. Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts
  387. Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
  388. Conveyance: A Versatile Framework for Learning in Structured Class Spaces
  389. Explaining Tabular Foundation Model Differences Through Meta-Features
  390. Tactile-Proprioceptive Sensor Fusion for Contact Wrench Estimation in Whole-Body Physical Human-Robot Interaction
  391. Measuring Progress Toward AGI: A Cognitive Framework
  392. EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering
  393. A Two-Scan Deep Learning Model for Predicting Dementia in Mild Cognitive Impairment
  394. Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization
  395. Bound-Constrained Sparse Representation for Electrical Impedance Tomography
  396. CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras
  397. Meta-Attention: Bayesian Per-Token Routing for Efficient Transformer Inference
  398. PrionNER: A Named Entity Recognition Dataset for Prion Disease Biomedical Literature
  399. PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text
  400. Score Based Error Correcting Code Decoder
  401. Detecting Diffusion-Generated Time Series Under Generator Shift
  402. Improving Evaluation of Recombination-based Cartesian Genetic Programming
  403. Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
  404. Picid: A Modular Evaluation Infrastructure for Reproducible PHM Across Tasks and Domains
  405. Decision-focused learning for optimal PV-Battery scheduling
  406. SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models
  407. An Enhanced Large Neighborhood Search Approach for the Capacitated Facility Location Problem with Incompatible Customers
  408. Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guarantee
  409. Transfer learning RGB models to hyperspectral images with trainable tensor decompositions
  410. Learning the Error Patterns of Language Models
  411. Insurance Pricing Optimization via Off-Policy Evaluation
  412. Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-series: Application to manipulator robots
  413. HardMTBench: Stress-Testing Chinese-English Translation on Knowledge-Intensive Domains
  414. EventShiftFlow: Towards Hardware-efficient FPGA-based Flow Estimation
  415. Learning to Assess the Reliability of Number-of-Runs Estimation in Stochastic Optimization
  416. HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
  417. Compositional Generalization in Autoregressive Models via Logit Composition
  418. T-GINEE: A Tensor-Based Multilayer Graph Representation Learning
  419. REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis
  420. Machine Learning methods for event classification and vertex reconstruction of the 12C + 12C reaction with the MATE-TPC
  421. Adaptive Bandit Algorithms for Contextual Matching Markets
  422. PrunePath: Towards Highly Structured Sparse Language Models
  423. ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
  424. EchoAvatar: Real-time Generative Avatar Animation from Audio Streams
  425. LV-OSD: Language-Vision-Complementary Open-Set Object Detection
  426. Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
  427. Dynamic Topic Modeling with a Higher-Order Hypergraphical Representation
  428. Parameter-Efficient Generative Modeling with Controlled Vector Fields
  429. Entropy Distribution as a Fingerprint for Hallucinations in Generative Models
  430. MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations
  431. Category-Level 3D Correspondence in Camera Space via Morphable Object Priors
  432. AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?
  433. Building Community-Centred NLP Resources for Puno Quechua
  434. Counterfactually Fair Regression via Optimal Transport
  435. PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment
  436. POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation
  437. Bridging the Sampling Distribution Shift in Radio Map Estimation: A Trajectory-Aware Paradigm
  438. Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
  439. Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation
  440. When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions
  441. Why We Need Speech to Evaluate Speech Translation
  442. Supervised Semantic Differential for Cross-Cultural Concept Analysis: A Case Study of Human Affect
  443. SmartIterator: Visual Analytics Workflows for Supervising Unsupervised Data Grouping
  444. IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following
  445. A Patient-Specific Pulmonary Arterial Tree Digital Twin to Extract Pulmonary Embolism Biomarkers
  446. Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems
  447. When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR
  448. The Illusion of Opting in AI-Mediated Consequential Decisions
  449. Robust Contrastive Graph Clustering with Adaptive Local-Global Integration
  450. Geometry-First Generative Spatial Single-Cell Reconstruction
  451. Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework
  452. The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness
  453. Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
  454. Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
  455. SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling
  456. From Kellgren-Lawrence to Calcium Pyrophosphate Crystal Deposition: A Soft-Labelling Framework for Knee Osteoarthritis Assessmen
  457. FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
  458. Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values
  459. OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
  460. QuITE: Query-Based Irregular Time Series Embedding
  461. Unification and Optimization of Robust Supervised Learning
  462. Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization
  463. DEPART: DEcomposing PARiTy across Multilingual LLMs
  464. Learning Logical Operations for Arbitrary Quantum Error Correction Codes
  465. MeniOmni: A Structured Multimodal Benchmark for Holistic Meniscus Injury Assessment
  466. Intra-YOLO: A Small Object Detection Model for Caries and Molar-Incisor Hypomineralization in Intraoral Photography Based on Transfer Learning with Reinforcement Learning
  467. Temporal Hyperbolic Graph Representation Learning for Scale-Free Internet Routing and Delay Prediction
  468. Skillful high-resolution weather forecasting independent of physical models
  469. A novel ordinal multi-view aggregation scheme for oak defoliation
  470. DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers
  471. Adaptive Reservoir Computing for Multi-Scenario Chaotic System Forecasting
  472. Sequential Neural Probabilistic Amplitude Shaping: Learning the Channel's Language
  473. No Safe Dose: How Training Data Drives Unsafe Image Generation
  474. SAM-Enhanced Segmentation on Road Datasets: Balancing Critical Classes in Autonomous Driving
  475. Convergence of empirical subgradients for optimal transport-based objectives
  476. Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
  477. Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
  478. Better heads do not guarantee better binarized constituency parsing
  479. Do Clinical Models Change Treatment Decisions?
  480. Chinese Word Boundary Recovery through Character Alignment Projection
  481. CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes
  482. Gradient Step Plug-and-Play Model for Dental Cone-Beam CT Reconstruction
  483. ST-ColoNet: Spatio-Temporal Colon Segment Recognition via Hybrid Attention and Edge-Guided Feature Learning
  484. A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG
  485. Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
  486. Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
  487. Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector
  488. EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction
  489. Revisiting Change Detection Methods for their Application to Serac Fall Time-Lapse Monitoring
  490. Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
  491. BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization
  492. ATLAS: All-round Testing of Long-context Abilities across Scales
  493. Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
  494. Diagnosing the conditional-mean barrier in scientific machine-learning surrogates
  495. Measure-to-measure Regression with Transformers
  496. PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
  497. PromptEmbedder: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
  498. Verifiable Benchmarking of Long-Horizon Spatial Biology
  499. I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
  500. Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
  501. ConvMemory: A Lightweight Learned Memory Reranker, a Negative Attribution Result, and a Research-Preview Conflict Editor
  502. Challenges in Explaining Pretrained Clinical Text Classifiers
  503. Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis
  504. On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
  505. RW-TTT: Batched Serving for Request-Owned Test-Time Training State
  506. Knowledge Dependency Estimation for Reliable Question Answering
  507. MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
  508. Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
  509. Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis
  510. MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
  511. Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings
  512. PetroBench: A Benchmark for Large Language Models in Petroleum Engineering
  513. MIRA: A Bilingual Benchmark for Medical Information Response Audit
  514. VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
  515. Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation
  516. AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels
  517. Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking
  518. Enhancing Ultra-low-field MRI with Segmentation-guided Adversarial Learning
  519. Automated Estimation of Impact Time, Impact Location, and Shuttlecock Speed in Badminton Smashes Using Event Cameras
  520. Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback
  521. Learning Compositional Latent Structure with Vector Networks
  522. An Empirical Audit of k-NAF Budget Accounting for Anchored Decoding
  523. Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection
  524. Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning
  525. The Model Shape Behind Scaling Laws: A Gradient Superposition Perspective
  526. Auditing Stance Asymmetry in Generative Explanations
  527. An Evolutionary Approach for Designing Stable and Highly Expressible Low-Immunogenicity Therapeutic mRNA Sequences
  528. STAB: Specification-driven Testing for Algorithmic Bottlenecks
  529. Periodic RoPE for Infinite Context LLMs
  530. Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
  531. Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost
  532. Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning
  533. Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective
  534. DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints
  535. Con-DSO: Learning Short-Horizon Consistency Priors for RGB-D Direct Sparse Odometry
  536. Evaluating the Feasibility of Inferring Dietary Behavior Change Receptivity from Egocentric Images of Eating Environment
  537. Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
  538. From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
  539. Quantum principal component analysis without eigenvector recovery
  540. SEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images
  541. Machine learning enables experimental access to photon-by-photon arrival times in scintillation detectors
  542. DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation
  543. Exploratory Experience Shapes the Geometry of Predictive Representations
  544. SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
  545. Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study
  546. Show, Don't TELL: Explainable AI-Generated Text Detection
  547. Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
  548. Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs
  549. Privately Estimating Monotone Statistics in Polynomial Time
  550. SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats
  551. ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
  552. Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting
  553. SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation
  554. FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation
  555. SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
  556. PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management
  557. A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning
  558. Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM Fiction
  559. SPAR: Support-Preserving Action Rectification
  560. Beyond Phones: Structured Phonemic Modeling for Vietnamese Automatic Speech Recognition
  561. MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment
  562. From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Interaction Type Prediction An Ablation Study with Acetylsalicylic Acid Validation
  563. DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
  564. Fine-Tuned LLM as a Complementary Predictor Improving Ads System
  565. ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
  566. TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems
  567. Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China
  568. A self-supervised learning approach to deep filter banks for texture recognition
  569. LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation
  570. Symmetry Defeats Auditing
  571. CAREF: Calibration-Aware Regularization for Explanation Faithfulness Without Rationale Supervision
  572. Playing with Words, Improving with Rewards: Training Language Models for Creative Association
  573. Decentralized Parameter-Free Online Learning with Compressed Gossip
  574. Operational AI Deployment Assurance: Governance-State Orchestration Under Threshold-Sensitive Deployment Conditions -- A Governance Framework for High-Stakes AI Systems
  575. Pattern Recognition Tasks with Personalized Federated Learning
  576. Constrained Auto-Bidding via Generative Response Modeling
  577. TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
  578. ChildEval: When large language models meet children's personalities
  579. CuriosAI Submission to the CASTLE Challenge at EgoVis 2026
  580. GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection of Inflammatory Bowel Disease
  581. Benchmarking Ultrasound Foundation Models for Fetal Plane Classification
  582. Learning to target with network interference
  583. Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
  584. Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
  585. Locality-Aware Redundancy Pruning for LLM Depth Compression
  586. Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms