mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 16 Jun 2026

479 papers

  1. Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded AuditRetrieval-augmented generation → RAG robustness and adaptive retrieval
  2. Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative ModelingDiffusion models → Diffusion foundations and sampling
  3. AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI AgentsLLM agents and tool use → Agent memory systems
  4. Centralized PPO-Based DRL for Multi-UAV-BS Positioning and Trajectory Optimization in Disaster Response NetworksDeep reinforcement learning methods → RL for robot navigation and UAV control
  5. Agentic AI Enhances Physician Trust in Clinical Decision MakingLLM agents and tool use → Medical and scientific domain agents
  6. The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to MistakesLLM reasoning → Test-time compute and efficient thinking +1
  7. Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to JusticeLLM reasoning → Reasoning for agents, planning and code
  8. When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web ExplorationLLM agents and tool use → Web, search, and research agents
  9. Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound imagesMultimodal LLMs / vision-language models → Medical vision-language models
  10. Multimodal Image Colorization: Quantifying the Impact of Text-Conditioned Guidance on Grayscale-to-Color TranslationDiffusion models → Image generation, text-to-image and editing
  11. MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  12. TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-DistillationKnowledge distillation → Multimodal distillation
  13. Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase OutcomesLLM agents and tool use → Social simulation and multi-agent debate
  14. Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX frameworkLLM agents and tool use → Agent threats, guardrails and governance
  15. Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?LLM agents and tool use → GUI and mobile agents
  16. CEO-Bench: Can Agents Play the Long Game?LLM agents and tool use → General LLM agent frameworks and benchmarks
  17. Effects of sparsity and superposition on loss in simple autoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  18. Do as the Romans Do: Learning Universal Behaviors from Heterogeneous AgentsOffline RL and imitation learning from data → Inverse reinforcement learning
  19. When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?LLM reasoning → Reinforcement learning for reasoning +1
  20. MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level RetrievalRetrieval-augmented generation → Multimodal RAG
  21. Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime PredictionDeep reinforcement learning methods → Quantum reinforcement learning
  22. Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise ApplicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector DatabasesRetrieval-augmented generation → Privacy and security of RAG
  24. Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video GenerationDiffusion models → Video generation
  25. PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model UnlearningLLM safety and security → Machine unlearning
  26. Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-TuningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  27. ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use DriftLLM agents and tool use → Tool learning and function calling
  28. LLM Parameters for Math Across Languages: Shared or Separate?LLM reasoning → Mathematical reasoning
  29. VISUALSKILL: Multimodal Skills for Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  30. Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMsLLM reasoning → Multimodal reasoning +1
  31. Beyond Prediction: Tail-Aware Scheduling for LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  32. Signature filtering: a lightweight enhancement for statistical watermark detection in large language modelsLLM safety and security → Watermarking generated content and models
  33. CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue AgentsEfficient LLM inference and serving → KV cache optimization
  34. JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree DraftingEfficient LLM inference and serving → Speculative decoding
  35. Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  36. LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  37. CaVe-VLM-CoT: An Interpretable Vision-Language Model FrameworkMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  38. When Can We Trust the Sparse Lens? A Certification Framework for SAE FaithfulnessMechanistic interpretability → SAE features and their applications
  39. SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  40. PAIWorld: A 3D-Consistent World Foundation Model for Robotic ManipulationWorld models → Embodied and robot world models
  41. SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  42. Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical MasksDiffusion models → Medical imaging and segmentation
  43. Self-CTRL: Self-Consistency Training with Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking +1
  44. SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed BehaviorMechanistic interpretability → Sparse autoencoder training and evaluation
  45. Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG SystemsRetrieval-augmented generation → Privacy and security of RAG
  46. SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning VectorLLM safety and security → Machine unlearning
  47. Attribution-Guided and Coverage-Maximized Pruning for Structural MoE CompressionMixture-of-experts → MoE large language models
  48. Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-MotionWorld models → Video-generation world models and simulators
  49. Visual Verification Enables Inference-time Steering and Autonomous Policy ImprovementVision-language-action models → Reinforcement learning and post-training
  50. EventDrive: Event Cameras for Vision-Language Driving IntelligenceEnd-to-end autonomous driving → VLMs for autonomous driving
  51. ReproRepo: Scaling Reproducibility Audits with GitHub Repository IssuesLLM agents and tool use → Web, search, and research agents
  52. EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal NavigationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  53. Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  54. Zone of Proximal Policy Optimization: Teacher in Prompts, Not GradientsKnowledge distillation → On-policy and self-distillation for LLMs +1
  55. Looped World ModelsWorld models → Latent predictive world models
  56. RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical SkillsLLM agents and tool use → Medical and scientific domain agents
  57. Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill ScannersLLM agents and tool use → Agent threats, guardrails and governance
  58. Learning from the Self-future: On-policy Self-distillation for dLLMsKnowledge distillation → On-policy and self-distillation for LLMs
  59. A Red-Team Study of Anthropic Fable 5 & Opus 4.8 ModelsLLM safety and security → Jailbreaking
  60. Kolmogorov Regression for Robust Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  61. EgoCS-400K: An Egocentric Gameplay Dataset for World ModelsWorld models → Video-generation world models and simulators
  62. All Smoke, No Alarm: Oracle Signals in Agent-Authored Test CodeLLM agents and tool use → Software engineering coding agents
  63. The Measurement Gap in the Automation of EU Law: Benchmarking Doctrinal Legal Reasoning under the EU AI ActLLM reasoning → Reasoning for agents, planning and code
  64. WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic ReasoningLLM reasoning → Clinical and biomedical applications +1
  65. Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI ModelsLLM agents and tool use → Social simulation and multi-agent debate
  66. Knowledge Reutilization in Meta-Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  67. Predicting Immune Biomarkers with MultiModal Mixture-of-Expert Pathology Foundation Models Empowers Precision OncologyMixture-of-experts → Medical and biomedical MoE
  68. Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  69. Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation SystemLLM agents and tool use → Multimodal and embodied agents
  70. Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  71. Deep Reinforcement Learning for Minimum Zero-Forcing SetsDeep reinforcement learning methods → RL for games and combinatorial optimization
  72. HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical PracticeRetrieval-augmented generation → RAG pipeline design and evaluation
  73. Trust the Right Teacher: Quality-Aware Self-Distillation for GUI GroundingKnowledge distillation → Multimodal distillation
  74. S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained DevicesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  75. From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  76. A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  77. Volterra Generative ModelsDiffusion models → Diffusion foundations and sampling
  78. Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare ApplicationsLLM agents and tool use → Medical and scientific domain agents
  79. NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward AlignmentDiffusion models → Diffusion and flow policies for robotics
  80. Intelligence Entropy Principle and the ADE Stability Engineering FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
  81. PseudoBench: Measuring How Agentic Auto-Research Fuels PseudoscienceLLM agents and tool use → Web, search, and research agents
  82. ConSA: Controllable Sparsity in Hybrid Attention via Learnable AllocationEfficient LLM inference and serving → KV cache optimization
  83. Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and ComposeLLM agents and tool use → Agent skill learning and evolution
  84. Uncertainty Quantification for Flow-Based Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness +1
  85. ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  86. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation ScalingEfficient LLM inference and serving → Efficient reasoning and agent inference
  87. Recursive Scaling in Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
  88. LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AILLM agents and tool use → Medical and scientific domain agents
  89. PhaseWin: An Efficient Search Algorithm for Faithful Visual AttributionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  90. LLM Consumer Behavior Theory: Foundations of a Novel Research FieldLLM agents and tool use → Social simulation and multi-agent debate
  91. A T-API-Compliant ReAct Agentic Loop for Optical Networks: Generic vs. Domain-Specific Tool AbstractionsLLM agents and tool use → Agentic AI for wireless networks
  92. VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic TerminationDiffusion models → Discrete and text diffusion
  93. LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth ManipulationDiffusion models → Diffusion and flow policies for robotics
  94. STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-TrainingDiffusion models → Diffusion and flow policies for robotics +1
  95. Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic SegmentationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  96. Beyond Visual Cues: CoT-Enhanced Reasoning for Semi-supervised Medical Image SegmentationLLM reasoning → Clinical and biomedical applications
  97. MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual BiasMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  98. SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMsMixture-of-experts → Expert routing strategies
  99. RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  100. ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
All 479
  1. PreAct: Computer-Using Agents that Get Faster on Repeated TasksLLM agents and tool use → GUI and mobile agents
  2. PearlVLA: Progressive Embodied Action-Plan Refinement in Latent SpaceVision-language-action models → World model-based VLA
  3. Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle OptimizationLLM agents and tool use → Web, search, and research agents
  4. WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFTWorld models → Latent dynamics models and model-based RL +1
  5. ChLogic: Evaluating Robustness of Logical Reasoning in Chinese ExpressionsLLM reasoning → Reasoning benchmarks and evaluation
  6. Condition-Wise Sinkhorn Drifting for One-Shot Learned Channel SimulationDiffusion models → Diffusion for compression and wireless
  7. Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  8. MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical ReasoningLLM reasoning → Multimodal reasoning
  9. AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal AnchorEfficient LLM inference and serving → KV cache optimization +1
  10. GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?LLM agents and tool use → Software engineering coding agents
  11. FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph FlowRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  12. Environment-Grounded Automated Prompt Optimization for LLM Game AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  13. A Framework for Evaluating Agentic Skills at ScaleLLM agents and tool use → Agent skill learning and evolution
  14. Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP BackdoorsLLM safety and security → Backdoor and data poisoning attacks
  15. PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech EnhancementDiffusion models → Audio, speech and music
  16. Continual Self-Improvement with Lightweight Experiential Latent MemoriesLLM reasoning → Reinforcement learning for reasoning +1
  17. MaineCoon: Pursuing A Real-Time Audio-Visual Social World ModelWorld models → Video-generation world models and simulators
  18. Position: Coding Benchmarks Are Misaligned with Agentic Software EngineeringLLM agents and tool use → Software engineering coding agents
  19. LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon StreamsEfficient LLM inference and serving → Visual token pruning in multimodal models
  20. Mind Companion: An Embodied Conversational Agent for Process-Based PsychotherapyLLM agents and tool use → Medical and scientific domain agents
  21. LUMEN: Coordinated Failure Recovery for Distributed LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  22. Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMsLLM reasoning → Reinforcement learning for reasoning
  23. ActWorld: From Explorable to Interactive World Model via Action-Aware MemoryWorld models → Video-generation world models and simulators
  24. LongWebBench: Evaluating Structural and Functional Webpage Generation in Long-Horizon SettingsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  25. Vision-language models for chest radiography do not always need the imageMultimodal LLMs / vision-language models → Medical vision-language models
  26. EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden IntentLLM agents and tool use → Social simulation and multi-agent debate
  27. SuCo: Sufficiency-guided Continuous Adaptive ReasoningLLM reasoning → Test-time compute and efficient thinking
  28. From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  29. EnvRL: Learn from Environment Dynamics in Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  30. See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RLLLM reasoning → Multimodal reasoning +1
  31. Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image TranslationDiffusion models → Medical imaging and segmentation
  32. MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality BlockState-space sequence models (S4, Mamba) → Vision Mamba backbones
  33. From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMsLLM reasoning → Reasoning for agents, planning and code
  34. Beyond Domains: Reusing Web Skills via Transferable Interaction PatternsLLM agents and tool use → Web, search, and research agents
  35. FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory HarnessLLM reasoning → Reasoning for agents, planning and code +1
  36. ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AILLM reasoning → Spatial and embodied reasoning
  37. OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  38. Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action RecognitionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  39. RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image GenerationRetrieval-augmented generation → Multimodal RAG
  40. Flux-Guard: Facial Identity Protection using diffusion modelsDiffusion models → Robustness, privacy and adversarial aspects
  41. MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
  42. Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  43. Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory StraightnessDiffusion models → Image generation, text-to-image and editing
  44. Cordon: Semantic Transactions for Tool-Using LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  45. AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  46. RT-Counter: Real-Time Text-Guided Open-Vocabulary Object CountingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  47. Universal Image Restoration via Internalized Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
  48. Reversal Q-LearningDiffusion models → Diffusion and flow policies for robotics +2
  49. SEAGym: An Evaluation Environment for Self-Evolving LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  50. Continuous-time Optimal Stopping through Deep Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  51. Offline Preference-Based Trajectory EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. Reinforcing Dual-Path Reasoning in Spatial Vision Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  53. OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video GenerationWorld models → World models for autonomous driving +2
  54. Learning to Refine Hidden States for Reliable LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  55. Scaling Enterprise Agent Routing: Degradation, Diagnosis, and RecoveryLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. SPHINX: First Explain, Then ExploreMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  57. GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot PlanningVision-language-action models → 3D and spatial-aware VLA
  58. Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception AuditingLLM reasoning → Prompting and chain-of-thought reasoning
  59. Theoretical Grounding of Out-Of-Distribution Detection With Reinforcement Learning OptimizerDeep reinforcement learning methods → Deep RL algorithms and representations
  60. PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  61. CheckMIABench: Firm Foundations For Membership Inference Attacks on Language ModelsLLM safety and security → Membership inference attacks
  62. WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  63. Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent SimulationLLM agents and tool use → Financial trading and forecasting agents
  64. MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision FactorsLLM agents and tool use → General LLM agent frameworks and benchmarks
  65. MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation EvaluationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  66. LADBench: A Benchmark for Logical Fault Detection in ImagesLLM reasoning → Multimodal reasoning +1
  67. Edit3DGS: Unified Framework for Dynamic Head Editing via 2D Instruction-Guided Diffusion and 3D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  68. CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  69. A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language ModelsLLM reasoning → Audio-language model reasoning
  70. Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity OperationsDeep reinforcement learning methods → RL for robot navigation and UAV control
  71. Enhancing Pathological VLMs with Cross-scale ReasoningLLM reasoning → Clinical and biomedical applications
  72. Attention Alignment Between Humans and Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  73. NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio DramaWorld models → World models for language agents
  74. Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  75. TerraTransfer: Learning End-to-End Driving Policies Without Expert DemonstrationsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  76. Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy ValidationLLM agents and tool use → Financial trading and forecasting agents
  77. Performance-Driven Environment Abstraction with Multi-Timescale LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  78. Implicit vs. Explicit Prompting Strategies for LVLMs in Referential CommunicationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  79. MESSY STREETS: A Benchmark for Geocoding Real-World Addresses
  80. The Signal in the Noise: An Auditable Reliability Layer for Biomedical Text Classification
  81. Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model
  82. The Divergence Hypothesis: Unmasking Lexical Interference and Label Bias in Mental Health NLP
  83. How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
  84. Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
  85. Evaluating the impact of adversarial traffic patterns on vanet communication using veins simulation
  86. Characterization of Thermal Systems from Noisy and Low-resolution Measurements Using Dynamic Mode Decomposition
  87. The Transparency Trap: How AI Disclaimers Create Overconfidence in High-Stakes Decisions
  88. Estimating Treatment Effects for Depression in Longitudinal Therapy Switching Settings
  89. Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities
  90. A Resolution of the SS--RS--GD Inequalities
  91. AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs
  92. Generalized Neural Distributional Regression
  93. Predictive Modeling of High-Altitude Clear Air Turbulence in the United States: A Machine Learning Approach
  94. Improving Survey Participation in Low-Literacy Populations Through Value-Sensitive Conversational AI
  95. Horseshoe Priors for Spatial Small Area Estimation: Regular Variation, Tail Robustness, and Deep Learning
  96. AI for Quality Assurance in the Operating Room
  97. Mapping the Artificial Intelligence Divide in Africa: Infrastructure, Accessibility and Capacity
  98. Toward AI-Resilient Assessment in Computer Science Courses in an AI-Native World
  99. AI Transparency: Governance Compliance or Stakeholder Requirements?
  100. Can Physician Expertise Improve Machine Learning Identification of Delirium?
  101. Random coloured digraphs defined by a Markov logic network
  102. Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement
  103. Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy
  104. CDER-SME: A Cross-Device Event-RGB Micro-Expression Dataset under Multi-Level Stress Induction
  105. A Generalized Formalism of Auto-Regressive Decoding for Speech Processing
  106. FairTutor: Equity-Aware Pedagogical LLM Routing for Budget-Constrained AI Tutoring
  107. Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit
  108. Interpretable and Verifiable Hardware Generation with LLM-Driven Stepwise Refinement
  109. SP-TransientBench: A Real-Captured Single Photon Perception Benchmark
  110. Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction
  111. TS-Fault: Benchmarking Time Series Forecasters Against Structural Faults
  112. Shrinkage priors for Bayesian Substitute Confounders
  113. AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
  114. Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks
  115. A Prototypical Signature Approach for Writer-Independent Offline Signature Verification
  116. Toward Simultaneously Optimal Regret in U-Calibration
  117. Overlapping Schwarz Attention: Hierarchical Attention via Domain Decomposition
  118. On the Residual Scaling of Looped Transformers: Stability and Transferability
  119. DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis
  120. Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging
  121. Compact Geometric Representations of Hierarchies
  122. As You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture
  123. PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization
  124. Exponentially many initializations to avoid barren plateaus
  125. N(CO)2: Neural Combinatorial Optimization with Chance Constraints to Solve Stochastic Orienteering
  126. Architectural Bias in Face Presentation Attack Detection: A Comparative Study of Vision Transformers and Convolutional Neural Networks
  127. Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
  128. Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
  129. Neural Phase Correlation
  130. SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR
  131. MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data
  132. Vines-DB: An RGB image dataset for multi-species ornamental vine segmentation
  133. The Illusion of Improvement: Reject Inference Strategies in Credit Scoring
  134. Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text
  135. Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion
  136. Montreal Forced Aligner and the state of speech-to-text alignment in 2026
  137. What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy
  138. Modeling Doppler Shifts in Radial-Velocity Data with Deep Learning toward Earth-mass Exoplanet Detection
  139. Mixed-Precision Communication-Avoiding SGD for Generalized Linear Models on GPUs
  140. Task-Restricted Symmetries in Recurrent Weight Space
  141. Veriphi: Attack-Guided Neural Network Verification with Dataset-Dependent Training Methods
  142. A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)
  143. TMR-GGNN: Credit Card Fraud Detection based on Time-Aware Multi-Relational Guided Graph Neural Network
  144. RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
  145. Sequential Hiring of Contingent Workers Through Learning-Based Optimization
  146. Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
  147. CAOA -- Completion-Assisted Object-CAD Alignment
  148. Complexity and Scale in AI-Assisted Workflow Management: A Federated Learning Case Study
  149. A Variational Framework for LLM Generator-Regulator Games
  150. Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction
  151. P2CE: Model-Agnostic Plausible Pareto-Optimal Counterfactual Explanations
  152. Searching for Synergy in Shared Workspace Human-AI Collaboration
  153. Bayesian Nonparametric Detection of Anomalies in Multivariate Functional Data
  154. Deep-Learning-Based Pixelated Microwave Filter Design and Characterization using Electro-Optical Electric-Field Measurements
  155. Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis
  156. Learning-Based Decision Making for Combustion Phasing Control in Multi-Fuel CI Engines with Latent Fuel Reactivity Estimation
  157. MOLAR: Learning Multimodal Molecular Representations from Noisy Labels
  158. SCOPE-FL: A Strategy-proof Chain-based Optimal pareto efficient Federated Learning System
  159. RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
  160. Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification
  161. Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
  162. Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
  163. ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets
  164. Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance
  165. Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response
  166. Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models
  167. Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs
  168. ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots
  169. Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection
  170. Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion
  171. A Survey on Data-Driven Models for Soil Moisture Regression and Classification
  172. Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation
  173. TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
  174. TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
  175. DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution
  176. Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds
  177. Starter-Iterator Neural Operator: A Unified Architecture for High-Fidelity Forward and Inverse PDE Problems
  178. A Link between Shock-wave Theory and Symmetry-reduced Stochastic Gradient Descent for Artificial Neural Networks
  179. Protein-Based Fish Species Identification: Dataset, Models, and Insights from Native Bangladeshi Fish
  180. Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
  181. Variable-Width Transformers
  182. MOCHI: Motion Enhancement of Collaborative Human-object Interactions
  183. Sign-Rank, Index, and List Replicability: Connections and Separations
  184. Adaptive Volumetric Mechanical Property Fields Invariant to Resolution
  185. Darshana Graph: A Parallel Commentary Corpus for Comparative Indian Philosophy, with Stylometric and Exploratory Graph Analyses
  186. Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
  187. Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
  188. Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
  189. Analyzing and Encoding the Al-Mawrid Arabic-English Dictionary with the ISO Language Markup Framework and TEI Lex-0
  190. Conformal Prediction Intervals with Tail-Specific Guarantees
  191. The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
  192. DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction
  193. Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation
  194. A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise
  195. IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction
  196. A Convex Quasilinearization Method for Solving Nonlinear PDEs with Physics-Informed Neural Networks
  197. Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports
  198. ReAge3D: Re-Aging 3D Faces with View Consistency
  199. Learning Cardiac Electrophysiology Digital Twins Through Agentic Discovery of Hybrid Structure
  200. Neural Tree Reconstruction for the Open Forest Observatory
  201. Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So
  202. Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)
  203. Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour
  204. Unintended Effects of Geographic Conditioning in Large Language Models
  205. Embedded Machine Learning for Microcontroller-Class Edge Devices: Data, Feature, Evaluation, and Deployment Pipelines
  206. Structural Role Injection in Handlebars-Templated LLM Prompts: Triple-Brace Interpolation, Delimiter Family, and the Limits of HTML Auto-Escaping
  207. First Proof Second Batch
  208. HLS-GPT: A Generative Pretrained Transformer (GPT) for Continental-Scale NASA Harmonized Landsat and Sentinel-2 (HLS) Reflectance Reconstruction Across All Bands on Arbitrary Dates
  209. Querying an astronomical database using large language models: the ALeRCE text-to-SQL system
  210. OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization
  211. IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus
  212. EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning
  213. Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability
  214. Tensor-based second-order causal discovery
  215. Blended Chart Surfaces: A Seamless Explicit Representation for Smooth Surface Fitting
  216. When LLMs Analyze Scars: From Images to Clinically-Meaningful Features
  217. Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond
  218. When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support
  219. ConTex: Reformulating Counterfactual Generation For Time Series Forecasting
  220. When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning
  221. INI-VPINN: A Variational Physics-Informed Neural Network with Implicit Neumann and Interface Handling for Multi-Material Domains with Geometric Singularities
  222. Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation
  223. Reading between the Lines: Leveraging Large Language Models for Global Dementia and Depression Assessment from Clinical Interviews
  224. Fast Nonparametric Conditional Independence Testing via Two-Stage Regression
  225. C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
  226. Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models
  227. AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement
  228. Multiple cyclicity and Wavelet Decomposition with Channel Correlation for Long-term Time Series Forecasting
  229. Differential Privacy of Gaussian Process Posterior Sampling
  230. Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis
  231. Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement
  232. MoCo-AIS: A Contrastive Learning Framework for Similarity Computation of Vessel Trajectories
  233. Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue
  234. SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation
  235. Learning task-specific subspaces via interventional post-training of speech foundation models
  236. A Neuro-Symbolic Approach to Strategy Synthesis for Strategic Logics
  237. Robustness of Similarity-based Positional Encoding Under Rotations: Theoretical Analysis and Experimental Validation
  238. Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model
  239. Small Initialization Matters for Large Language Models
  240. Understanding Long-Term Dynamics of Individual Metro Usage: A Hidden Semi-Markov State Framework with Survival Analysis
  241. MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization
  242. Predictive Analytics in E-Commerce for CustomerBehavior Forecasting using hybrid Ret-DNN withXGBoost Model
  243. How Inference Compute Shapes Frontier LLM Evaluation
  244. KANLib -- A Modular, Extensible and Fast Kolmogorov-Arnold Network Implementation
  245. Nested Sampling: A Critical and Comprehensive Theoretical Guide
  246. Non-negative Elastic Net Decoding for Information Retrieval
  247. DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue
  248. Learn to Quantify Social Interaction with Constraints for Pedestrian Walking
  249. Dimensionality Controls When Modularity Helps in Continual Learning
  250. AI Adoption Across a Multinational Workforce: Sociotechnical Conditions for GenAI Acceptance in Human Resources
  251. Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
  252. Structural Preservation and the Logical Expressiveness of Graph Neural Networks
  253. Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations
  254. StepGuard: Guarding Web Navigation via Single-Step Calibration
  255. A Quantitative Analysis of Multimodal Biomarkers in Alzheimer's Disease
  256. Meta-classification of one-class classification models using ranking correlation and nearest neighbor
  257. A homotopy-type-theoretic generalization of neurosymbolic inference
  258. WallZero: Mastering the Game of WallGo with Strategic Analysis
  259. Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
  260. High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach
  261. Perceptual compensation for tonal context in self-supervised speech models
  262. From Drift to Coherence: Stabilizing Beliefs in LLMs
  263. Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity
  264. When Multiple Scripts Matter: Evaluating ASR in Clinical Settings
  265. Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows
  266. DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
  267. Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation
  268. Conservation Laws for Modern Neural Architectures
  269. No-Free-Fairness: Fundamental Limits and Trade-offs in Learning Systems
  270. Million-scale multimodal pollen microscopy with expert-guided foundation models
  271. QueryMarket: Cost-Aware Online Active Learning in Data Markets
  272. The Slop Paradox: How Synthetic Standardization Erodes Clinical Uncertainty and Cross-Modal Alignment in AI-Rewritten Radiology Reports
  273. Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars
  274. Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery
  275. MIVE: A Minimalist Integer Vector Engine for Softmax LayerNorm and RMSNorm Acceleration
  276. On Response-Adaptive Targeting Strategies for Multi-Treatment Experiments
  277. A Neuromorphic Trigger for Efficient Audio Event Detection
  278. Talking to Your Data: Exploring Embodied Conversation as an Interface for Personal Health Reflection
  279. Horizon-Uniform Sensitivity and Decay of Terminal Reward Perturbations in Discrete-Time Pontryagin Systems
  280. A fairness-aware extension of Stochastic Multicriteria Acceptability Analysis for ranking
  281. BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics
  282. ED3R: Energy-Aware Distributed Disaster Detection via Cooperative Agents in Robotic Systems
  283. GSPan: A Continuous Gaussian Primitive Representation for Arbitrary-Scale Pansharpening
  284. Heterogeneous SAR-optical fusion for near-real-time land use and land cover mapping under cloud contamination: A novel framework and global benchmark dataset
  285. Structured Adversarial Camouflage via Voronoi Diagrams
  286. Confusion-Aware Transfer Teacher Curriculum Learning Framework: Disentangling Scoring and Pacing Effects
  287. SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segmentation and LLM-Driven Tumour Microenvironment Characterisation in Histopathology
  288. FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories
  289. Delta-Based Target Reformulation for Short-Term Electricity Load Forecasting Using LSTM and Transformer Models
  290. LLMs Infer Cultural Context but Fail to Apply It When Responding
  291. Geometrical fairness in graph neural networks
  292. Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
  293. ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series of Molecular Dynamics
  294. Handling Feature Heterogeneity with Learnable Graph Patches
  295. FacProcessTwin: An LLM-Based System for Process Twin Development
  296. Non-asymptotic Tail Bounds for the Kostlan--Shub--Smale Field: Tensor PCA and Spherical k-Spin Complexity
  297. Temporal Preference Optimization for Unsupervised Retrieval
  298. TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
  299. Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific
  300. Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
  301. A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction
  302. SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches
  303. Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets
  304. Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification
  305. Prompt Perturbation for Reliable LLM Evaluation over Comparison Graphs
  306. SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation
  307. The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer
  308. Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere
  309. Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting
  310. Proximal Mediation Analysis with Hidden Recanting Witnesses
  311. TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization
  312. Understanding LLMs in Title-Abstract Screening: From Disagreements to Recommendations
  313. Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
  314. LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks
  315. Surrogate Assisted Pedestrian Protection Design via a Foundation Model Orchestrated Workflow
  316. DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack
  317. When Dynamics Models Read the Wrong Time Steps: Label-Free Event Credit Re-Anchoring for Robust Global Readouts
  318. Reducing Learner Redundancy in Boosting via Residual Orthogonalization
  319. Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery
  320. An Autonomous AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts
  321. SpatioTemporal Causal Network Diagnostics for Geographic Tipping Point Early Warning
  322. Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings
  323. TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks
  324. Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition
  325. Non-negative Matrix Factorisation with Topological Regularisation
  326. Public transit gains and spatially uneven travel demand changes after NYC congestion pricing
  327. Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates
  328. MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
  329. Beyond IGO-Flow: Toward Convergence Analysis of IGO in Continuous Spaces
  330. An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars
  331. GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
  332. FoundCause: Causal Discovery with Latent Confounders from Observational Data
  333. Anytime-valid Optimal Policy Identification
  334. Unlocking LLM Code Correction with Iterative Feedback Loops
  335. Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning
  336. MagicSim: A Unified Infrastructure for Executable Embodied Interaction
  337. When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs
  338. LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline
  339. Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement
  340. Reconfigurable Computing Challenge: Transformer for Jet Tagging on Versal AI Engines
  341. A Bayesian Boolean Matrix Factorization with Application to Copy Number Analysis in Cancer
  342. Online LLM Selection via Constrained Bandits with Time-Varying Demand
  343. Multi-Adapter PPO: A Cross-Attention Enhanced Wavelength Selection Framework for LIBS Quantitative Analysis
  344. StereoFactory: A Unified Merging Framework for Robust Stereo Matching
  345. AIPatient Arena: EHR-grounded evaluation of large language models in end-to-end clinical consultation workflows
  346. ReRAM-aware Model Finetuning addressing I-V Non-linearity and Retention Errors
  347. Perron--Frobenius Operator Matching for Generative Modeling
  348. ResAware: Cross-Environment Website Fingerprinting via Resource-Privileged Distillation
  349. AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting
  350. Operator Boosting Produces Pareto-Efficient PDE Surrogates
  351. Dissecting model behavior through agent trajectories
  352. Credibility-Weighted Pricing of Autonomous Vehicle Liability Under Operational Design Domain Shift
  353. A Machine-Learned Comorbidity Index
  354. AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
  355. Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining
  356. Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
  357. Contact-Based Fringe Projection Profilometry for High-Resolution 3-D Surface Measurement of Reflective and Transparent Objects
  358. Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos
  359. UoU: A Universal Fingerprint Foundation Model Based on Large-Scale Unsupervised Learning
  360. MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense
  361. Visual Retrieval-Augmented Generation for Silhouette-Guided Animal Art
  362. Impact of Hand Impairment and Occlusions on Hand Pose Estimation Accuracy in Augmented Reality Applications
  363. Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty
  364. Martingale Doppelg"anger-Eval: An Identification Framework for Auditing Candlestick Understanding in Vision-Language Models
  365. Feynman Kac Reweighted Schr"odinger Bridge Matching for Surface-Based Tau PET Harmonization
  366. Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces
  367. L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification
  368. Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows
  369. Discrete Autoregressive Transformer for Generative Mechanism Synthesis
  370. Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies
  371. Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
  372. Treatment Response Optimized Clinical Decision Support AI System via Digital Twin Simulation
  373. Bridging Spatial And Frequency Views For Disaster Assessment: Benefits And Limitations
  374. The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
  375. SoK: AI-Augmented Binary Reversing
  376. Damage Adaptation in Seconds for Architected Materials
  377. Improving and Evaluating Hand-Object Interaction Detection
  378. MeiBRD: Meta-Learning Intraoperative Biomechanical Residual Deformation
  379. Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework