mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 31 Aug 2026

616 papers

  1. PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable SlidesLLM agents and tool use → Multimodal and embodied agents
  2. Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual LearningKnowledge distillation → Distillation for continual learning
  3. Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated MarketsLLM reasoning → Reasoning for agents, planning and code +1
  4. Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent PlanningLLM agents and tool use → Agent threats, guardrails and governance
  5. EvLink: Source-Grounded Evidence Linking for Graph RAGLLM reasoning → Knowledge- and tool-augmented reasoning +1
  6. Fair Like Us? Auditing LLM Alignment in Resource AllocationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  7. PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM ConversationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Improving Parameter Utilization by Sharing Neural Experts Across Layers in TransformersMixture-of-experts → Expert routing strategies
  9. Seeing What the Vehicle Sees: Video-Augmented Virtual Reality for Physical Autonomous VehiclesEnd-to-end autonomous driving → Generative simulation for driving
  10. AgenticGen: Reward-Guided Agentic Video Generation for AdvertisingLLM agents and tool use → Multimodal and embodied agents +1
  11. CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  12. Emergent Goal-Directed Attention in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  13. The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent SocietiesLLM agents and tool use → Social simulation and multi-agent debate
  14. When and What to Teach: Budget-Aware Online Adaptation for Web AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM DeploymentLLM reasoning → Test-time compute and efficient thinking +1
  16. SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill AbstractionLLM agents and tool use → Web, search, and research agents
  17. Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted DevelopmentLLM agents and tool use → Agent memory systems
  18. Context Inference Attacks Without JailbreaksLLM agents and tool use → Agent threats, guardrails and governance +1
  19. How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-MakingLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving
  21. PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +2
  22. NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and InferenceMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  23. Validity-Aware Jailbreak Evaluation for Large Language ModelsLLM safety and security → Jailbreaking
  24. Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  25. EvoFlint: An Evolutionary Atlas of Multi-Turn LLM VulnerabilitiesLLM safety and security → Prompt injection and agent security
  26. EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language ModelsRetrieval-augmented generation → Medical and biomedical RAG
  27. Exploring Collaboration between a language and a non-language agentLLM agents and tool use → Reinforcement learning for LLM agents
  28. TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge PoisoningRetrieval-augmented generation → Privacy and security of RAG
  29. Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic PerspectiveLLM reasoning → Reasoning for agents, planning and code +1
  30. Can LLMs Use Relational Transformer Embeddings?LLM reasoning → Test-time compute and efficient thinking
  31. Towards a Belief-Based World Model for LLM AgentsWorld models → World models for language agents +1
  32. HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM InferenceEfficient LLM inference and serving → KV cache quantization
  33. Capability-Gated Language Models: Security Composes, Utility Does NotLLM safety and security → Safety alignment, refusal and guardrails
  34. SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  35. SpecMind: Enabling Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
  36. DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  37. RestoreBench: Can AI Agents Restore Power Flow Convergence?LLM agents and tool use → Financial trading and forecasting agents
  38. FoldingAgent: Inferring Parametric Origami Procedures from Demonstration VideosLLM agents and tool use → Multimodal and embodied agents
  39. Dr. Claw: An AI Scientist Workspace for Vibe ResearchLLM agents and tool use → Software engineering coding agents
  40. Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  41. Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex DomainsDiffusion models → Flow matching, time series and science
  42. Toward Workflow-Aware Benchmarking for Healthcare NLP AgentsLLM agents and tool use → Medical and scientific domain agents
  43. Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory ConflictsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  44. WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network OptimizationMixture-of-experts → Expert routing strategies +1
  45. Exact Global MCMC with Denoising DiffusionDiffusion models → Diffusion foundations and sampling
  46. The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating SystemsLLM agents and tool use → Software engineering coding agents
  47. Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  48. The Answer Is Not the ArgumentLLM reasoning → Prompting and chain-of-thought reasoning
  49. Spec-Driven Development for Agentic Software Engineering: Harnessing Human-Agent TeamworkLLM agents and tool use → Software engineering coding agents
  50. Hypotheses-Guided Self Distillation for Continual PersonalizationKnowledge distillation → On-policy and self-distillation for LLMs
  51. Invalidation Contracts for Cross-Episode Agent MemoryLLM agents and tool use → Agent memory systems
  52. CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance PredictionEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  53. Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Beyond Blind Compliance: Benchmarking Task Verification in OCR ReasoningLLM reasoning → Multimodal reasoning +2
  55. Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLMMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  56. Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  57. Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video ModerationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  58. A Lagrangian View of Flow MatchingDiffusion models → Flow matching, time series and science
  59. Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication CostDeep reinforcement learning methods → RL for energy, networks and operations
  60. LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New BenchmarkEnd-to-end autonomous driving → VLMs for autonomous driving
  61. ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-trainingWorld models → Embodied and robot world models
  62. Do General NLP Embeddings Capture Ontological Reasoning?LLM reasoning → Knowledge- and tool-augmented reasoning
  63. IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model TrainingWorld models → Embodied and robot world models
  64. Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMsLLM reasoning → Reasoning benchmarks and evaluation
  65. Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  66. Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm OperationsLLM agents and tool use → Multimodal and embodied agents
  67. Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond AccuracyMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  68. Generative artificial intelligence for reliable mechanistic reasoning for corrosionLLM reasoning → Clinical and biomedical applications
  69. Assessing Alignment and Stability of Feature Importance Explanations via Weight of EvidenceLLM reasoning → Reasoning benchmarks and evaluation
  70. Framework and Benchmark for Code-Driven Agentic Testing in Web DevelopmentLLM agents and tool use → Software engineering coding agents
  71. Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  72. DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk ScreeningLLM agents and tool use → Medical and scientific domain agents
  73. When Does Bigger Help? A Controlled Study of LLM Scale for Ontology LearningMixture-of-experts → MoE large language models
  74. Aspire: Can Models Self-Evolve from Vague Goals?Synthetic data and self-improvement for LLMs → Self-evolving LLM agents
  75. S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?Synthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  76. Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured DataLLM reasoning → Knowledge- and tool-augmented reasoning +1
  77. Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  78. Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  79. Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research AgentsLLM agents and tool use → Web, search, and research agents
  80. Scaling Large Reasoning Models beyond Human Supervision: A Path toward SuperintelligenceLLM reasoning → Reinforcement learning for reasoning
  81. A Model with No Head and Many ThoughtsLLM reasoning → Test-time compute and efficient thinking
  82. Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence ScoresLLM reasoning → Test-time compute and efficient thinking
  83. Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought CompressionLLM reasoning → Test-time compute and efficient thinking
  84. Measure Before You Manage: Evaluating Agent Working Memory in Coding AgentsLLM agents and tool use → Agent memory systems
  85. Identity-Conditioned Latent Consistency Distillation for Face SynthesisDiffusion models → Image generation, text-to-image and editing
  86. Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-ImprovementKnowledge distillation → On-policy and self-distillation for LLMs
  87. Driving on MemoryEnd-to-end autonomous driving → End-to-end system architecture
  88. Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech ProtocolsLLM reasoning → Clinical and biomedical applications
  89. Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular GenerationDiffusion models → Flow matching, time series and science
  90. Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration +1
  91. Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation SteeringMechanistic interpretability → Steering and probing for LLM safety
  92. A Human-in-the-Loop Autonomous Agent for Industry Time Series ForecastingLLM agents and tool use → Financial trading and forecasting agents
  93. LOCI: A Locator-Critic with Refinement LoopMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  94. One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool LearningLLM agents and tool use → Medical and scientific domain agents +1
  95. Detecting AI Impostors: How Do Middle Schoolers Identify LLM Agents in a Live Collaborative Setting?LLM agents and tool use → Social simulation and multi-agent debate
  96. Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical ReferralLLM reasoning → Clinical and biomedical applications +1
  97. Stride-k Subsampling: Train-Free Audio Token Reduction for WhisperEfficient LLM inference and serving → Audio and omni-modal token compression
  98. TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  99. CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  100. Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment SeparationDiffusion models → Audio, speech and music
All 616
  1. S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure ElucidationLLM agents and tool use → Medical and scientific domain agents
  2. MMDS-Bench: Benchmarking Multimodal Large Language Models on Dynamic Stance in Social Media InteractionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. Low-Resource Preference Adaptation of LLMs via Activation-Based Label PropagationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  4. CAER: Causal Action Effect Reweighting for World Model TrainingWorld models → Embodied and robot world models
  5. Playability-Aware Audio-to-Tablature Guitar Transcription via Diffusion ModelsDiffusion models → Audio, speech and music
  6. Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  7. HSRM: Hidden-State Reward Models for Test-Time VerificationLLM reasoning → Test-time compute and efficient thinking +1
  8. What Emerges and What Breaks in Self-Play DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  9. TopoCompress: Long Context Compression via Graph-Wired Semantic TrajectoriesEfficient LLM inference and serving → Prompt and context compression
  10. Schwarz: Solver-Aware Agentic Program VerificationLLM agents and tool use → Educational agents and math problem solving
  11. PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-ResolutionDiffusion models → Inverse problems and image restoration
  12. T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and SchedulerDeep reinforcement learning methods → Deep RL algorithms and representations
  13. PRACTICE: From Experience to Expertise in Self-Evolving Embodied AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  14. CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray InterpretationLLM reasoning → Clinical and biomedical applications +1
  15. Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language ModelsLLM reasoning → Spatial and embodied reasoning
  16. Do VLMs Share Safety Neurons Across Modalities?Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  17. The Fragility of Jailbreak Robustness Across Operational StatesLLM safety and security → Jailbreaking
  18. E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business OperationLLM agents and tool use → Social simulation and multi-agent debate
  19. Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment AnalysisMixture-of-experts → Multimodal MoE models
  20. BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML TasksLLM agents and tool use → Software engineering coding agents +1
  21. Mind the Gap: Theory-of-Mind-Grounded Friction for Epistemic AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  22. GUIDE: Guiding Internal Evidence with Language InstructionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  23. VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  24. SingProbe Technical ReportLLM safety and security → Safety alignment, refusal and guardrails
  25. An Agentic Retrobiosynthesis Framework with Learned Frontier SelectionLLM agents and tool use → Medical and scientific domain agents
  26. A Phased Workflow for Operating LLM-Based Coding AgentsLLM agents and tool use → Software engineering coding agents
  27. Can Video World Models Track Unobserved World States?World models → Video-generation world models and simulators
  28. Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository PoisoningLLM agents and tool use → Agent threats, guardrails and governance
  29. ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use AgentsLLM agents and tool use → Tool learning and function calling
  30. LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  31. OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image UnderstandingLLM reasoning → Multimodal reasoning +1
  32. CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain EnvironmentsDeep reinforcement learning methods → RL theory and sample complexity
  33. HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task SolvingLLM agents and tool use → Multimodal and embodied agents
  34. MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable PipelinesMechanistic interpretability → Knowledge and representations inside LLMs
  35. SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?LLM agents and tool use → General LLM agent frameworks and benchmarks
  36. LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent WorkflowLLM agents and tool use → Software engineering coding agents
  37. Fine-Grained Multi Image Object Hallucination BenchmarkMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  38. Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  39. Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  40. What It Costs to Compose, Rebuild, and Correct Precomputed MemoryEfficient LLM inference and serving → KV cache optimization
  41. BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  42. Temporal Forcing: 4D Representation Alignment for Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
  43. Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RLDeep reinforcement learning methods → Deep RL algorithms and representations
  44. Test-time Reinforcement Learning in Imperfect Information GamesDeep reinforcement learning methods → RL training of language and agent models
  45. GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  46. Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign TextSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  47. DiffSAC: Diffusion-guided Sampling for Consensus-based Robust EstimationDiffusion models → Inverse problems and image restoration
  48. PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  49. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and RefusalLLM safety and security → Safety alignment, refusal and guardrails
  50. TuringLLM: Efficiently Scaling Foundation Models Toward Physical AIMixture-of-experts → MoE large language models
  51. Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMsMixture-of-experts → MoE large language models
  52. AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQALLM reasoning → Clinical and biomedical applications
  53. Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon TasksVision-language-action models → Failure recovery and robustness
  54. DiffPDE: Masked Diffusion Language Models as PDE SolverDiffusion models → Discrete and text diffusion
  55. WebWorld: The Browser as a World Model for Self-Improving Web CodeWorld models → World models for language agents +1
  56. PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMsLLM reasoning → Reinforcement learning for reasoning
  57. Local-to-Global Sentence-Level Graph Reranking for Scientific SynthesisRetrieval-augmented generation → Agentic RAG, agents and memory
  58. Authority-Inference Separation in Agentic Finance: First-Line Control, Blockchain Enforcement, and Replayable AssuranceLLM agents and tool use → Financial trading and forecasting agents
  59. ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad CompetitionsLLM reasoning → Mathematical reasoning
  60. CHIPSMORE: Compute-in-Interconnect and -Memory Chiplets for Multi-Mode Multi-Request LLM Inference AccelerationEfficient LLM inference and serving → Serving systems and request scheduling
  61. CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent FrameworkLLM reasoning → Multimodal reasoning +2
  62. VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  63. Agents in the Large: Perception-Centered Architecture for Persistent AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  64. More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMsLLM reasoning → Mathematical reasoning
  65. Enhancing Low-Resource Language Reasoning via High-Resource Language Feature TransferLLM reasoning → Reasoning benchmarks and evaluation
  66. From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal GeometryLLM reasoning → Spatial and embodied reasoning
  68. PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of ExpertMixture-of-experts → Expert routing strategies
  69. Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient RegistryOffline RL and imitation learning from data → Safe offline RL
  70. ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  71. Event-Driven Language Models with Sparse Neural Activity for Neuromorphic HardwareEfficient LLM inference and serving → Early exit and edge inference
  72. EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  73. Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social InteractionsLLM agents and tool use → Social simulation and multi-agent debate
  74. Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  75. Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog SystemsLLM reasoning → Reasoning benchmarks and evaluation +1
  76. DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative BenchmarkLLM reasoning → Reasoning benchmarks and evaluation
  77. Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware CriticDeep reinforcement learning methods → Deep RL algorithms and representations
  78. Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse AutoencodersLLM safety and security → Backdoor and data poisoning attacks
  79. SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential GenerationLLM reasoning → LLM reasoning for recommendation
  80. Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise RerankingLLM reasoning → Knowledge- and tool-augmented reasoning
  81. Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon NavigationLLM agents and tool use → Multimodal and embodied agents
  82. When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  83. Using Grounded Theory for Agent Behavior Analysis at ScaleLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. Attesting Outputs and Delegation Ancestry in Multi-Agent AI SystemsLLM agents and tool use → Agent threats, guardrails and governance
  85. PAVE: Predictive Alignment and Value-Guided Evolution for World-Action PoliciesVision-language-action models → World model-based VLA
  86. Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  87. Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI EvidenceLLM agents and tool use → Medical and scientific domain agents
  88. Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive ModelsDiffusion models → Diffusion foundations and sampling
  89. Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM AgentsLLM safety and security → Prompt injection and agent security
  90. Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio TriggersLLM safety and security → Audio jailbreaks and speech backdoors
  91. Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  92. On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training StabilityMixture-of-experts → MoE large language models
  93. Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation SteeringMechanistic interpretability → Activation steering methods
  94. Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation GuidanceDeep reinforcement learning methods → RL for autonomous driving and traffic
  95. Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMsEfficient LLM inference and serving → KV cache optimization
  96. ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  97. Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?LLM agents and tool use → Software engineering coding agents
  98. CateKV: On Sequential Consistency for Long-Context LLM Inference AccelerationEfficient LLM inference and serving → KV cache optimization
  99. CometVLA: Co-Training on an Embodied Data Pyramid towards Physical UnderstandingVision-language-action models → Human-video and latent-action pretraining
  100. Extracting Knowledge from Tools in LLM AgentsLLM agents and tool use → Tool learning and function calling
  101. BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  102. SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-TuningLLM agents and tool use → Multimodal and embodied agents
  103. Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  104. Stratified Consistency Distillation for Natural Language FormalizationLLM reasoning → Reasoning benchmarks and evaluation
  105. Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMsLLM reasoning → Reasoning benchmarks and evaluation
  106. Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV CacheEfficient LLM inference and serving → Speculative decoding
  107. Generating Workflow DAGs from Natural Language with Non-Reasoning LLMsLLM reasoning → Reasoning for agents, planning and code
  108. Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning ApproachDeep reinforcement learning methods → RL for games and combinatorial optimization
  109. CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual NavigationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  110. Motus2: A Self-Evolving General World Model for Dexterous ManipulationWorld models → Embodied and robot world models
  111. The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerceLLM reasoning → Reasoning for agents, planning and code
  112. SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific LiteratureLLM reasoning → Knowledge- and tool-augmented reasoning
  113. Towards a Joint Khmer Text Recognition and Word SegmentationRetrieval-augmented generation → Multimodal RAG
  114. Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibrationMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  115. DICS: Exploring Data Intrinsic Consistency for Visual Instruction SelectionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  116. SIR: Self-improving Red-teaming for Compute Use AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  117. ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive AlternativesLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  118. NoisEasier: Test-Time Noise Optimization for Text-to-Video GenerationDiffusion models → Video generation
  119. FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical ValidationLLM agents and tool use → Financial trading and forecasting agents
  120. GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action SpaceLLM agents and tool use → Medical and scientific domain agents
  121. A.X K2 Technical ReportLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  122. Open-Source Autonomous Driving System Analysis and Multi-Disciplinary Hardware-in-the-Loop Research Paradigm with Reinforcement-Learning Testing and Large Language ModelsEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  123. Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent MemoryLLM agents and tool use → Agent threats, guardrails and governance
  124. Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  125. Reinforcement Learning for Symbolic Equation SolvingDeep reinforcement learning methods → Interpretable and logic-guided RL
  126. Reactivating Test-Time Scaling for Plane Geometry Problem SolvingLLM reasoning → Spatial and embodied reasoning
  127. CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  128. Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  129. Balancing Privacy, Utility, and Safety in LLM Alignment through Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  130. Verification-Aware Training for Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  131. E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint RetrievalRetrieval-augmented generation → Generation and context integration
  132. VIBE: Video Instruction-aligned Background music gEnerationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  133. Aligning Multi-Trajectory Supervision with Policy Optimization for VLA DrivingLLM reasoning → Chain-of-thought reasoning for driving +3
  134. TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation
  135. Revalidation Beats Stateful Routing for Scientific Surrogates Under Distribution Shift
  136. RAPTOR: RAndom-projection Physics-informed Transient sOlveR
  137. Three Ways Classical Test Theory Can Mislead About LLM Judges
  138. Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context
  139. An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension
  140. Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon
  141. Predicting Symptoms of Amotivation and Anhedonia among University Students with a Novel Oversampling Method
  142. DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts
  143. Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy
  144. Reconstruction of 4D Mitral Regurgitation Hemodynamics from Sparse Planar Data using Deep Operator Networks with Test-Time Adaptation
  145. ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication
  146. Lensless Gaze Is Not Private by Default: Auditing Identity Leakage Across Disclosure Surfaces
  147. M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
  148. Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification
  149. Robots Influencing Humans to Reveal their Goals during Collaboration and Competition
  150. An Exploratory Study of Frequency-Aware Task Weighting for YOLOv8-Based Unified Driving Perception
  151. AVENUE: Audio-Video EditiNg Understanding and Evaluation
  152. Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation
  153. SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training
  154. Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
  155. Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration
  156. From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models
  157. Human-Anchored Factuality Evaluation with Strategic Annotation
  158. The Privacy-Hallucination Tradeoff in Differentially Private Language Models
  159. MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation
  160. A hybrid quantum-classical neural network for learning to route
  161. AdaptNTK: Adaptive Uncertainty Quantification and Active Learning for Neural Network Potentials
  162. Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?
  163. Less Is More: Balancing Positive and Negative Space in Visual Concept Blending
  164. Fractal dimension predicts quantum kernel collapse in angle-encoded data
  165. Expert-like Bone Ultrasound Segmentation through Expert-in-the-loop Mask-conditioned Progressive Learning
  166. Higher Structures in Deep Learning
  167. Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy
  168. SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation
  169. Toppling the Hierarchy in Byte-level Language Modeling
  170. Context Window Failures in Relational Foundation Models
  171. Location-Aware Language Models via Secondary Embeddings
  172. mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers
  173. Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
  174. Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT
  175. CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning
  176. Group Adaptive Clipping Policy Optimization
  177. (V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement
  178. Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations
  179. Physiological Information Reliability: Cross-Layer Adaptive Resource Allocation for Cardiovascular Sensing
  180. Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks
  181. How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks
  182. Late Transformer Layers Recode Syntax Canonically: Evidence from Greek Scrambling and Cross-Layer Generalisation
  183. Unmasking Face Embeddings: Reading, Rendering and Naming with Foundation Models
  184. A Multi-Branch Feature Fusion Approach for Health Misinformation Detection and Propagation
  185. A convolutional framework for detecting event-driven dynamics in energy price series
  186. SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling
  187. NeuroPriv: Adversarial Representation Learning for Privacy in Wearable EEG Systems
  188. Hidden relationships in a document-derived property graph: top-k chunk embeddings and inverse-distance weighting over a dynamically evolving ontology
  189. Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You
  190. Towards unsupervised representation learning for quantum data: quantum models with inference and generation
  191. Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation
  192. Detoxifying Toxic Communication: A Design Science Approach to Responsible AI
  193. Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers
  194. Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment
  195. From Tool Use to Technological Agency: LoopCAT as a Local-First, Open-Source Tool for Translation Technology Education
  196. SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
  197. Two tests of phase-structure features for transition prediction
  198. Latent-Space No-Arbitrage Geometry of Generative Models for Implied Volatility Surfaces
  199. Latent Mechanisms of Language Control in Multilingual Language Models
  200. A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension
  201. Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries
  202. Emotional Labor Strategy Preferences in LLM Personas
  203. Workload Identification with Physical Side Channels for AI Governance
  204. The Assistant's Ideal Self
  205. TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening
  206. StreamScout: Learning When to Look Deeper for Streaming Video Understanding
  207. Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness
  208. Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection
  209. Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
  210. CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space
  211. NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings
  212. CompanionSim: Synthetic Data for Evaluating Anthropomorphism in Human-AI Relationships
  213. Authority Bias in Conversational Search Engines for Academic Paper Recommendation
  214. LOOMSUM: Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization
  215. Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking
  216. Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field Changes
  217. ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback
  218. QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
  219. LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts
  220. AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning
  221. Rock, Paper, Scissors, ... Dynamite - A Model of Disruption from New Technologies
  222. WHALE: A Simple Recipe for Joint Harness-Weight Optimization
  223. ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation
  224. Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models
  225. Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization
  226. Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs
  227. Intelligent Edge Computing
  228. Asymmetries in Spontaneous and Instructed Deception
  229. Recursive Criticality of AI Self-Improvement
  230. Flawed in Nature, Perfect through Evolution
  231. Different representation learning objectives recover distinct latent structures from the same psychometric data
  232. Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
  233. Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification
  234. Safin-1: Safety from Within through Memory-Native State Evolution
  235. Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?
  236. Commit-first LLM judging inherits the judge's own errors
  237. Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation
  238. Stochastic complexity of vectors containing cluster structure
  239. KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
  240. RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
  241. Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
  242. AI Morbidity and Mortality: A Framework for Clinical AI Failure Review
  243. MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts
  244. Context-Aware Interleaved Batching for WhisperX
  245. SUN: Agentic Robot Policy Learning with Persistent Task Programs
  246. Constant Individual Regret in General Games
  247. BRF-GS: Hyperspectral Bidirectional Reflectance Factor Modeling and Image Generation Based on 3D Gaussian Splatting
  248. Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations
  249. Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
  250. OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
  251. Implementing neural network mixed-effects models in Template Model Builder (TMB)
  252. On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
  253. PaperGym: Rubric-Centered Evolution for Research-Plan Generation
  254. "Train classical, deploy quantum" requires rethinking generalization
  255. Overcoming critical slowing down in frustrated spin systems by learned multiscale sampling
  256. BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
  257. Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions
  258. VeriCam: A Verification Baseline for the Classification of Unknown Data
  259. DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
  260. BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
  261. LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
  262. Cross-Regional Grapevine Cold Hardiness Prediction via Learned Multimodal Latent Representations
  263. One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning
  264. Robust retinal biometrics for patient identity verification and retrieval across age and imaging devices
  265. Minimax bounds for watermarked and masked recursive discrete distribution estimation
  266. Verbalizing Multi-Token Concepts in LLMs
  267. Real-Time Video Anomaly Detection Using YOLO Pose Estimation and CLIP-Based Semantic Scoring
  268. LISynSeg: Data-Centric Label-to-Image Synthesis for Cross-Modality Whole-Heart Segmentation
  269. Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers
  270. Multimodal Shared Latent Representation of Narration, Microscope and iOCT Images for Phase Recognition in Vitreoretinal Surgery
  271. When Can We Work in Embedding Space? What Text Embeddings Preserve
  272. Improving Information Extraction with Learned Queries
  273. Segmentation of Bovid Dentition Under Imperfect Annotations: A Comparative Study of Convolutional and Attention Models
  274. Rotational Equivariance in Machine Learning: A Comprehensive Tutorial
  275. Type-Balanced Contextual Learning for Incremental Named Entity Recognition
  276. Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions
  277. Normalized Low-Rank Adaptation
  278. When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models
  279. FaceSnap: Real-Time Personalized Lightstage Facial Performance Capture
  280. Learning the Geometry of Admissible Hypotheses through Inductive Bias in Training Distributions
  281. Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos
  282. SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting
  283. MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
  284. One note in three: a verified census of three deployed AI scribes, and the instrument that counted it
  285. LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It
  286. TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification
  287. Augmenting Interviewer Judgments of Patient Experience with Automatic Language Analysis
  288. From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
  289. DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception
  290. Multi-View Reflective Surface Inspection via Semantic-Saliency Cross-Verification
  291. Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
  292. Evaluating and Improving LLM Self-Modeling
  293. Sparse Competition during Training For the Emergence of Specialized Modules
  294. MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI
  295. CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations
  296. The Hermon Moment: AI Self-Transcendence and Its Human Narration
  297. CogEvol: Towards Efficient and Reliable Learning Environment Generation
  298. Vision Models Predict Urban Scene Appraisal with Limited Neural Alignment
  299. A Universal Context-Reuse Layer for Cross-Model KV Sharing
  300. Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training
  301. Taking the Whys Seriously: Limitations of Counterfactual Explanations in Justification and Recourse
  302. Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration
  303. Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation
  304. Reproducible macroscopic dynamics in a closed-loop human-AI learning system
  305. Nonparametric Contextual Pricing and Inventory Learning under Censored Demand
  306. MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI
  307. LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
  308. Annotated Surrogate Retrieval for Polish Statutory Law
  309. Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods
  310. Selection-Aware Stress Testing for Interactive Agents
  311. Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation
  312. Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space
  313. Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking
  314. Rad-R: A Raw-ADC Radar Dataset and Capture-Invariant SSM for Hardware-Fault Diagnosis
  315. A Controlled Evaluation of Model Rankings and Input Reliance in Surface Water Segmentation
  316. ECGQuest: Benchmarking and Fine-Tuning Language Models for Electrocardiography
  317. Safety Screening for Voltage Control in Active Distribution Grids via Distributionally Robust Conformal Screening
  318. Evaluating and Mitigating Anti-LGBTQ Biases in German and Multilingual Language Models
  319. Deploying DeepSeek 175B Locally on a Single Consumer-Grade RTX 4060 Laptop with 32GB RAM for 200k-Scale Protein-Ligand Virtual Screening
  320. Personas Differ from Native-Language Generation: Language Pathways Shape LLM Interpersonal Advice
  321. SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessment
  322. VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
  323. Exponential random graph models with soft clique constraints
  324. Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?
  325. Predicting Residential Rents in Dakar Using Machine Learning
  326. GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures
  327. TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment
  328. You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals
  329. Linguistic Distance Segregates Latent Representations in Automatic Speech Recognition Systems
  330. VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction
  331. Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V
  332. Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling
  333. Reliable Benchmarking of Artifact Detection in Computational Pathology: A Reproducibility and Uncertainty Analysis
  334. Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments
  335. Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels
  336. Whole-Body MRI Classification via Prompt-Based Clinical Conditioning
  337. Vocal Music under Phoneme-Conditional Analysis
  338. Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
  339. RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark
  340. A Composition-Aware Pretraining Framework for Geospatial Foundation Models
  341. Aggregate Disambiguation Systems
  342. Geometric Attractor Monitoring: A Robust and Frugal Framework for Multi-modal Industrial Robotic Cycles
  343. Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
  344. Conjoint Audio-to-Spikes Encoding and Processing for Efficient Neuromorphic Speech Recognition
  345. Camera trap classification with deep learning under ground truth uncertainty
  346. SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents
  347. Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning
  348. TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training
  349. CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
  350. ChessQueries: Toward Better Chess Board Recognition
  351. Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts
  352. On the Prospects of Dynamic LLM Conversations in Software Development
  353. CLIN: an Objective Framework for Evaluating Creativity in Short Persian Literary Text
  354. Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval
  355. TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
  356. Functional Degeneracy in Neural Networks: Measurement and Pruning
  357. Not All Fallbacks Are Failures: Understanding and Recovering from Fallbacks in Mobile Voice Assistants
  358. Calibrating Small Language Models for Claim Check-Worthiness Detection
  359. RailGen: Improving Railway Intrusion Detection via Agent-Guided Small-Scale Foreign Object Generation
  360. Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?
  361. Tracing distinguishability through transformer processing with stochastic LayerNorm
  362. SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos
  363. SegWave: Wavelet-Driven Segmentation of Tampered Regions
  364. Kolmogorov--Arnold against bounded translations
  365. RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection
  366. TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos
  367. Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
  368. Liquid Gated Attention
  369. Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions
  370. CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation
  371. UFPR-PEs: A Brazilian Face Recognition Benchmark with Self-Declared Race/Color Labels
  372. WildSEEK: Evaluating Language Models for Information-Seeking
  373. Learning Materials Properties from Scarce Labels and Unlabeled Crystals
  374. MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
  375. CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy
  376. InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning
  377. APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images
  378. Seasonality-Aware Hybrid Convolutional Transformer for Antarctic Sea Ice Concentration Forecasting
  379. PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN
  380. Marginal Coordinate Test for Fr'echet Regression with Random Objects
  381. MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions
  382. Quantum-Grassmann-Plucker Token Mixing for Deep Learning-Based Post-Disaster Damage Assessment
  383. REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation
  384. Cost-efficient Active Learning for Referring Image Segmentation and Grounding
  385. AQ3D: Adaptive Query Transformer for 3D Instance Segmentation
  386. RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias
  387. OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Dataset
  388. TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale
  389. Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training
  390. Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster
  391. State of Health Estimation using Convolutional and Bidirectional LSTM Neural Networks tuned by Bayesian Optimization
  392. Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum
  393. Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading
  394. Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle
  395. Collapsibility of Performance Metrics in Clinical Predictive AI
  396. Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
  397. Informative Label Missingness in Multiclass Classification Information Geometry and Excess Risk
  398. Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
  399. GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
  400. Designing an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis
  401. Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation
  402. Minerals in the Wild: A Hyperspectral-XRF Dataset for Elemental Composition Estimation
  403. Beamforming Design Via GNN in mmWave Cell-Free Massive MIMO Using Sub-6 GHz CSI
  404. MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulation
  405. Learning-Assisted Congestion-Aware Route Scheduling for Semiconductor Fab Material Control Systems
  406. TSExplorer: An interactive data annotation and exploration tool for time-series data
  407. Trajectory-Initialized Neural Double Q-Routing for Large-Scale Overhead Hoist Transport Systems
  408. Lot Machine: Multimodal Lot Extraction from Auction Catalogs
  409. UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory
  410. Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability
  411. When the Martingale Never Stops Firing: Anytime-Valid Gating on Real Forecast Streams
  412. Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
  413. Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus
  414. ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation
  415. ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction
  416. HorizonNet for visual terrain navigation
  417. Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
  418. Beyond Accuracy: Quantifying Pulmonary Attribution in Anatomy-Guided Chest X-Ray Classification Under Domain Shift
  419. CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target
  420. Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
  421. Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry
  422. SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding
  423. FlowVVTON: Flow-Guided Mask-Free Video Virtual Try-On
  424. End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios
  425. Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs
  426. Generalization as a robust performance property of learning-enabled dynamical systems
  427. Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
  428. Towards Cognitive Process-Aware Proactive Writing Support
  429. ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mesh Splatting
  430. Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
  431. From Metaheuristics to Exact Methods: A CP-SAT Approach for Multi-Objective Healthcare Workforce Scheduling
  432. Benchmarking External Generalization of SPD Matrix Learning for Resting-State fMRI Connectome Prediction
  433. Inherent Trade-offs when Enforcing Correct Data Symmetries in Multi-head Self-attention
  434. SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision
  435. Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
  436. ImageCAS-X: a dataset and benchmark for coronary artery segmentation and centerline extraction in coronary CT angiography
  437. Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
  438. Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
  439. TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
  440. Quantitative Evidence Mining for Plausibility-Aware Biomedical AI: A Narrative Review and Conceptual Framework
  441. Foundation Models Meet Agriculture: Challenges Beyond Pretraining
  442. Uncertainty of Vision Medical Foundation Models
  443. PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning
  444. DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
  445. RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
  446. Convergence rates for the RMSprop optimizer with full control of the hyperparameters
  447. Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention
  448. Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation
  449. Auditing MCQA Benchmarks through Probability Landscapes
  450. MCSeg: Pre-training and Fine-tuning Volumetric Pyramid Transformer for Multi-modal Cardiac Image Segmentation
  451. Beat-Synchronous Tokenization for ECG Transformers
  452. Beyond Churn: Predicting Financial Fragmentation in Retail Banking with Temporal Machine Learning
  453. Seeing the Unseen: Camouflaged Object Detection Beyond the Visible Spectrum
  454. Co-Annotator: Expert-Distilled ViT and VLM for Visual and Documentation Guidance in Age-Related Macular Degeneration
  455. Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
  456. Proximity3D: Shape from Capacitive Proximity on Sensing Manifold
  457. CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels
  458. Coarse composition suffices: tabular in-context learning for multi-activity antimicrobial peptide profiling
  459. Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurchase Recommendation
  460. Learning PDE Time-Stepping with Neural Cellular Automata
  461. Do Small Models Use the Law You Give Them? Measuring Context Use on a Bilingual Bangladesh Legal Benchmark
  462. Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends
  463. Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS
  464. Generative multi-domain transfer learning for fault detection in data-scarce wind turbines
  465. Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning
  466. Context Staircase: Signature-Aligned Dynamics of Token Embeddings under Small Initialization
  467. One AI Signal, Many Human Judgments: A Bayesian Cascade Analysis of AI-based Credibility Indicators in Online Information Spread
  468. Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models
  469. Lazy Grounding: Attacking Search Agents with Factual Evidence
  470. AIA2: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness
  471. Dynamic Hub-and-Spoke Memory for Streaming Video Understanding
  472. SELECT: SELEctive Context Transfer for Class-Incremental Semantic Segmentation
  473. Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding
  474. Strengthening Recursive Constructions for Zero-Error Shannon Capacity
  475. Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization
  476. Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts
  477. Multivariate Scientific Data Compression with Learned Cross-Variable Latent Decorrelation and Autoregressive Entropy Modeling
  478. Estimating Population-Risk Curves Along Nonconvex Gradient Flows from the Training Sample
  479. Using Prosody to Predict Syntactic Structure
  480. Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
  481. OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection
  482. A Borel Concept Class of VC Dimension One with a Non-PAC Consistent Learner in ZFC
  483. PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
  484. LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
  485. CoLa-ICD: A Knowledge-Enhanced Framework for Long-Tail Automated Medical Coding
  486. Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
  487. Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration
  488. Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models
  489. LaMoC: Loss-Aware Modular Compression for LLMs
  490. Fairness in multi-class multi-group classification problems via contextial coherent risk measures
  491. Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction
  492. Label Semantic Expansion via Label Guided Neural Topic Modeling
  493. Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
  494. When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection
  495. Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment
  496. When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs
  497. The PUR-1 Cyber-Physical Digital Twin
  498. ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
  499. ConCA: Concentration-Aware Channel Attention for Fine-Grained Visual Recognition
  500. Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts
  501. Science sandboxes measure the scientific capability of AI agents
  502. AI-enabled Low-Cost 3D Maize Ear Morphometry Platform at Breeding Scale
  503. CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation
  504. Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings
  505. CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests
  506. Repeatability Characterisation and Error Budget of a Consumer Structured-Light Scanner for 3-D Wound Geometry:A Rigid-Phantom Study
  507. Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention
  508. TPR-Attention for Combinatorial Generalization
  509. Manac'a-1B: An Open, Reproducible Brazilian-Portuguese Language Model and a Tokenizer-Aware, Paired Evaluation
  510. Supraglacial Lake Fate Is Knowable Long Before the Season Ends
  511. Can LLMs Take the Pulse of the Economy? A Real-Time Evaluation of LLM Nowcasts on Macroeconomic Indicators
  512. COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learning
  513. AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
  514. A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets
  515. Graph4BiLO: Graph Neural Network Approximation for Bilevel Mixed-Integer Linear Optimization
  516. SMOTE-VAR: An Uncertainty-Aware Oversampling Method for Predicting Depression Remission in University Students