mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 9 Feb 2026

521 papers

  1. Breaking the Factorization Barrier in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  2. Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample ApproachDeep reinforcement learning methods → RL theory and sample complexity
  3. CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark GenerationLLM safety and security → Prompt injection and agent security
  4. ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion AutoencodersDiffusion models → Medical imaging and segmentation
  5. Learning to Drive in New Cities Without Human DemonstrationsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  6. Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and CritiqueMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  8. VisPhyWorld: Probing Physical Reasoning via Code-Driven Video ReconstructionLLM reasoning → Spatial and embodied reasoning +1
  9. NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  10. Mirror: A Multi-Agent System for AI-Assisted Ethics ReviewLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  12. Basic Legibility Protocols Improve Trusted MonitoringLLM safety and security → Prompt injection and agent security
  13. Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement AttacksLLM reasoning → Reasoning for agents, planning and code +2
  14. VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  15. Effective Reasoning Chains Reduce Intrinsic DimensionalityLLM reasoning → Prompting and chain-of-thought reasoning
  16. Rethinking Global Text Conditioning in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  17. Generalizing GNNs with Tokenized Mixture of ExpertsMixture-of-experts → MoE for time series and graphs
  18. Feature salience - not task-informativeness - drives machine learning model explanationsLLM safety and security → Watermarking generated content and models
  19. Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion TransformersDiffusion models → Audio, speech and music
  20. MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  21. VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  22. CausalGDP: Causality-Guided Diffusion Policies for Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  23. EExApp: GNN-Based Reinforcement Learning for Radio Unit Energy Optimization in 5G O-RANDeep reinforcement learning methods → RL for energy, networks and operations
  24. AIDev: Studying AI Coding Agents on GitHubLLM agents and tool use → Software engineering coding agents
  25. n-Musketeers: Reinforcement Learning Shapes Collaboration Among Language ModelsLLM reasoning → Reinforcement learning for reasoning
  26. Quantifying Epistemic Uncertainty in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  27. FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge BasesLLM agents and tool use → Web, search, and research agents
  28. Boltzmann Reinforcement Learning for Noise resilience in Analog Ising MachinesDeep reinforcement learning methods → Deep RL algorithms and representations
  29. CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision SupportLLM agents and tool use → Medical and scientific domain agents
  30. SceneSmith: Agentic Generation of Simulation-Ready Indoor ScenesLLM agents and tool use → Multimodal and embodied agents
  31. Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-Author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory DetectionLLM reasoning → Multimodal reasoning +1
  32. An Actor-Critic-Identifier Control Design for Increasing Energy Efficiency of Automated Electric VehiclesDeep reinforcement learning methods → RL for energy, networks and operations
  33. PABU: Progress-Aware Belief Update for Efficient LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  35. Benchmarking the Energy Savings with Speculative Decoding StrategiesEfficient LLM inference and serving → Speculative decoding
  36. Agent Banana: High-Fidelity Image Editing with Agentic Thinking and ToolingLLM agents and tool use → Multimodal and embodied agents
  37. UI-Venus-1.5 Technical ReportLLM agents and tool use → GUI and mobile agents
  38. DMamba: Decomposition-enhanced Mamba for Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  39. Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  40. TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic ManipulationVision-language-action models → Reinforcement learning and post-training +1
  41. WorldCompass: Reinforcement Learning for Long-Horizon World ModelsWorld models → Latent dynamics models and model-based RL +1
  42. Robustness Is a Function, Not a Number: A Factorized Comprehensive Study of OOD Robustness in Vision-Based DrivingEnd-to-end autonomous driving → End-to-end system architecture
  43. ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow DistillationDiffusion models → Diffusion foundations and sampling
  44. Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent DefenseLLM agents and tool use → Agent threats, guardrails and governance
  45. DirMoE: Dirichlet-routed Mixture of ExpertsMixture-of-experts → MoE large language models
  46. iGRPO: Self-Feedback-Driven LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  47. Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case StudyLLM reasoning → Multimodal reasoning
  48. When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  49. InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  50. Contraction Metric Based Safe Reinforcement Learning Force Control for a Hydraulic Actuator with Real-World TrainingDeep reinforcement learning methods → RL for robot navigation and UAV control
  51. WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World ModelsWorld models → World models for navigation
  52. stable-worldmodel-v1: Reproducible World Modeling Research and EvaluationWorld models → Latent predictive world models
  53. A Behavioural and Representational Evaluation of Goal-Directedness in Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Digital Twin and Agentic AI for Wild Fire Disaster Management: Intelligent Virtual Situation RoomLLM agents and tool use → Multimodal and embodied agents
  55. CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time ComputeLLM reasoning → Test-time compute and efficient thinking +1
  56. CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal RungsLLM reasoning → Causal reasoning in LLMs
  57. StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text DetectorsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  58. Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request AcceptanceLLM agents and tool use → Software engineering coding agents
  59. Efficient and Stable Reinforcement Learning for Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  60. Denoise Stepwise Signals by Diffusion Model Based ApproachDiffusion models → Diffusion foundations and sampling
  61. Stress-Testing Alignment Audits With Prompt-Level Strategic DeceptionLLM safety and security → Prompt injection and agent security
  62. Do Reasoning LLMs Refuse What They Infer in Long Contexts?LLM reasoning → Reasoning for agents, planning and code +1
  63. AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly DetectionLLM reasoning → Time series reasoning +1
  64. TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  65. Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM SystemsLLM reasoning → Reasoning for agents, planning and code +1
  66. AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM RecommendersLLM agents and tool use → Agentic recommender systems
  67. Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  68. WildReward: Learning Reward Models from In-the-Wild Human InteractionsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  69. VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  70. Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and EditingDiffusion models → Video generation
  71. Bayesian Preference Learning for Test-Time Steerable Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  72. FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language ModelsMixture-of-experts → MoE large language models
  73. Negative-Aware Diffusion Process for Temporal Knowledge Graph ExtrapolationDiffusion models → Discrete and text diffusion
  74. Robust Policy Optimization to Prevent Catastrophic ForgettingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  75. Addressing data annotation scarcity in Brain Tumor Segmentation on 3D MRI scan Using a Semi-Supervised Teacher-Student FrameworkKnowledge distillation → Distillation for medical imaging
  76. Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal StructureLLM reasoning → Prompting and chain-of-thought reasoning
  77. Taming Scylla: Understanding the multi-headed agentic daemon of the coding seasLLM agents and tool use → Software engineering coding agents
  78. Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View CombinationsMixture-of-experts → Multimodal MoE models
  79. Shifting the Breaking Point of Flow Matching for Multi-Instance EditingDiffusion models → Image generation, text-to-image and editing
  80. Welfarist Formulations for Diverse Similarity SearchRetrieval-augmented generation → Vector search and ANN indexes
  81. Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert SilencingLLM safety and security → Mixture-of-experts routing safety
  82. From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  83. Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  84. Reasoning aligns language models to human cognitionLLM reasoning → Reasoning benchmarks and evaluation
  85. SoK: The Pitfalls of Deep Reinforcement Learning for CybersecurityDeep reinforcement learning methods → Adversarial robustness and RL in finance
  86. Learning To Sample From Diffusion Models Via Inverse Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +2
  87. LLaDA2.1: Speeding Up Text Diffusion via Token EditingDiffusion models → Discrete and text diffusion
  88. Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph ExpansionRetrieval-augmented generation → Privacy and security of RAG
  89. Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  90. From Robotics to Sepsis Treatment: Offline RL via Geometric PessimismOffline RL and imitation learning from data → Offline RL algorithms
  91. High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  92. Gradient Preconditioning for Efficient and Reliable Reward-Guided GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  93. Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMsMixture-of-experts → Expert routing strategies +1
  94. Improving Reconstruction of Representation AutoencoderDiffusion models → Diffusion foundations and sampling
  95. Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action SpacesDeep reinforcement learning methods → Deep RL algorithms and representations
  96. VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion ModelingDiffusion models → Audio, speech and music
  97. OSCAR: Optimization-Steered Agentic Planning for Composed Image RetrievalLLM agents and tool use → Multimodal and embodied agents
  98. Mimic Intent, Not Just TrajectoriesVision-language-action models → Human-video and latent-action pretraining +1
  99. Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine TranslationDeep reinforcement learning methods → RL training of language and agent models
  100. SDFed: Bridging Local Global Discrepancy via Subspace Refinement and Divergence Control in Federated Prompt LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
All 521
  1. DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  2. Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache EvictionEfficient LLM inference and serving → KV cache optimization
  3. Conditional Sequence Modeling for Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  4. SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  5. Modeling Score Approximation Errors in Diffusion Models via Forward SPDEsDiffusion models → Diffusion foundations and sampling
  6. ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMsLLM safety and security → Backdoor and data poisoning attacks
  8. Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based ApproachesLLM agents and tool use → Web, search, and research agents
  9. QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence ModelingLLM reasoning → LLM reasoning for recommendation
  10. Combined Constrained Sampling and Reinforcement Learning for Robotic ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  11. Three Lessons from Citizen-Centric Participatory AI DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  13. UniPlan: Vision-Language Task Planning for Mobile Manipulation with Unified PDDL FormulationLLM reasoning → Spatial and embodied reasoning
  14. Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPOLLM reasoning → Reasoning for agents, planning and code
  15. GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-SolvingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  16. Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  17. Learning Self-Correction in Vision-Language Models via Rollout AugmentationLLM reasoning → Multimodal reasoning +1
  18. Contextual Rollout Bandits for Reinforcement Learning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  19. Characterizing, Evaluating, and Optimizing Complex ReasoningLLM reasoning → Test-time compute and efficient thinking
  20. Beyond Correctness: Learning Robust Reasoning via TransferLLM reasoning → Reinforcement learning for reasoning
  21. Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc QueriesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  22. SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving ScenariosVision-language-action models → VLA for autonomous driving +1
  23. Demo-ICL: In-Context Learning for Procedural Video Knowledge AcquisitionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  24. From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI AgentLLM agents and tool use → Agent threats, guardrails and governance
  25. TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model AccelerationDiffusion models → Discrete and text diffusion +2
  26. On Protecting Agentic Systems' Intellectual Property via WatermarkingLLM agents and tool use → Agent threats, guardrails and governance +1
  27. SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed DomainsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  28. D2-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization StrategyDiffusion models → Inverse problems and image restoration
  29. ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  30. Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion TransformersDiffusion models → 3D, point cloud and scene generation
  31. Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement LearningLLM reasoning → Test-time compute and efficient thinking +1
  32. Reinforcement Learning with Backtracking FeedbackDeep reinforcement learning methods → RL training of language and agent models
  33. MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph RetrievalLLM reasoning → Reasoning for agents, planning and code +1
  34. Does Your Reasoning Model Implicitly Know When to Stop Thinking?LLM reasoning → Test-time compute and efficient thinking
  35. What, Whether and How? Unveiling Process Reward Models for Thinking with Images ReasoningLLM reasoning → Multimodal reasoning +2
  36. OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path ExplorationLLM reasoning → Test-time compute and efficient thinking
  37. ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier DetectionEfficient LLM inference and serving → KV cache optimization
  38. CoTZero: Annotation-Free Human-Like Vision Reasoning via Hierarchical Synthetic CoTLLM reasoning → Multimodal reasoning +1
  39. Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent SystemLLM agents and tool use → Reinforcement learning for LLM agents
  40. Vec-QMDP: Vectorized POMDP Planning on CPUs for Real-Time Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  41. Latent Reasoning with Supervised Thinking StatesLLM reasoning → Prompting and chain-of-thought reasoning
  42. Personalized Autonomous Driving via Optimal Control with Clearance Constraints from QuestionnairesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  43. Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought CompressionLLM reasoning → Test-time compute and efficient thinking
  44. Improving Data and Reward Design for Scientific Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  45. Is Flow Matching Just Trajectory Replay for Sequential Data?Diffusion models → Flow matching, time series and science
  46. SWE Context Bench: A Benchmark for Context Learning in CodingLLM agents and tool use → Software engineering coding agents
  47. Fast Flow Matching based Conditional Independence Tests for Causal DiscoveryDiffusion models → Diffusion foundations and sampling
  48. Moral Sycophancy in Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  49. New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVRLLM reasoning → Reinforcement learning for reasoning
  50. PISCO: Precise Video Instance Insertion with Sparse ControlDiffusion models → Video generation
  51. Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic SystemsLLM agents and tool use → Reinforcement learning for LLM agents
  53. Inverting Data Transformations via Diffusion SamplingDiffusion models → Diffusion foundations and sampling
  54. A Statistical Framework for Alignment with Biased AI FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  55. SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health ComorbiditiesLLM agents and tool use → Medical and scientific domain agents
  56. A Unified Framework for Multimodal Image Reconstruction and Synthesis using Denoising Diffusion ModelsDiffusion models → Medical imaging and segmentation
  57. STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency PredictionDiffusion models → Diffusion and flow policies for robotics
  58. Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with TransformersLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  59. Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  60. When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial ReasoningWorld models → World models for language agents +1
  61. When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  62. SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution +1
  63. Weak-Driven Learning: How Weak Agents make Strong Agents StrongerLLM agents and tool use → General LLM agent frameworks and benchmarks
  64. CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge ConflictsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  65. Pretraining with Token-Level Adaptive Latent Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking
  66. Sparsity-Aware Evolution for Model MergingMechanistic interpretability → Sparse autoencoder training and evaluation
  67. RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and ReflectionLLM reasoning → Reasoning for agents, planning and code
  68. DrugR: Optimizing Molecular Drugs through LLM-based Explicit ReasoningLLM reasoning → Clinical and biomedical applications
  69. Chain-of-Caption: Training-free improvement of multimodal large language model on referring expression comprehensionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  70. Self-Supervised Bootstrapping of Action-Predictive Embodied ReasoningLLM reasoning → Spatial and embodied reasoning +1
  71. Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
  72. Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature
  73. Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
  74. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains
  75. Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations
  76. A Hybrid Machine Learning Approach for Graduate Admission Prediction and Combined University-Program Recommendation
  77. Mathematical Foundations of Modeling ETL Process Chains
  78. Large Language Models and Book Summarization: Reading or Remembering, Which Is Better?
  79. Equitable Multi-Task Learning for AI-RANs
  80. Automated Concept Discovery for LLM-as-a-Judge Preference Analysis
  81. Quantum-Inspired Self-Attention in a Large Language Model
  82. Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations
  83. The Influence of Iconicity in Transfer Learning for Sign Language Recognition
  84. M-QUEST -- Meme Question-Understanding Evaluation on Semantics and Toxicity
  85. Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
  86. How does fine-tuning improve sensorimotor representations in large language models?
  87. Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding
  88. Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
  89. MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models
  90. What Is the Alignment Tax?
  91. REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
  92. Property-Driven Evaluation of GNN Expressiveness at Scale: Datasets, Framework, and Study
  93. LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
  94. Econometric vs. Causal Structure-Learning for Time-Series Policy Decisions: Evidence from the UK COVID-19 Policies
  95. Attn-QAT: 4-Bit Attention With Quantization-Aware Training
  96. CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
  97. Autonomous AI and Ownership Rules
  98. Benchmarking Early Deterioration Prediction Across Hospital-Rich and MCI-Like Emergency Triage Under Constrained Sensing
  99. ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling
  100. BioLM-Score: Language-Prior Conditioned Probabilistic Geometric Potentials for Protein-Ligand Scoring
  101. Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
  102. Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling
  103. Charting the Future of AI-supported Science Education: A Human-Centered Vision
  104. WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery
  105. PCReg-Net: Progressive Contrast-Guided Registration for Cross-Domain Image Alignment
  106. Spectral Collapse in Diffusion Inversion
  107. KidMesh: Computational Mesh Reconstruction for Pediatric Congenital Hydronephrosis Using Deep Neural Networks
  108. The Effective Depth Paradox: Topology and Trainability in Deep CNNs
  109. Conditional Generative Models for High-Resolution Range Profiles: Capturing Geometry-Driven Trends in a Large-Scale Maritime Dataset
  110. MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models
  111. Agent Mars: Multi-Agent Simulation for Multi-Planetary Life Exploration and Settlement
  112. Data-driven registration and modeling of brain deformation for image-guided neurosurgery
  113. Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol
  114. PEST: Physics-Enhanced Swin Transformer for 3D Turbulence Simulation
  115. Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval
  116. On the Use of a Large Language Model to Support the Conduction of a Systematic Mapping Study: A Brief Report from a Practitioner's View
  117. Silence Routing: When Not Speaking Improves Collective Judgment
  118. When LLMs get significantly worse: A statistical approach to detect model degradations
  119. MPA: Multimodal Prototype Augmentation for Few-Shot Learning
  120. SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech
  121. The effect of whitening on explanation performance
  122. Mutual Information Collapse Explains Disentanglement Failure in β-VAEs
  123. Collective Behavior of AI Agents: the Case of Moltbook
  124. Measuring Inclusion in Interaction: Inclusion Analytics for Human-AI Collaborative Learning
  125. STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory
  126. VLM-Guided Iterative Refinement for Surgical Image Segmentation with Foundation Models
  127. Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
  128. RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdata
  129. Do Neural Networks Lose Plasticity in a Gradually Changing World?
  130. When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
  131. Barycentric alignment for instance-level comparison of neural representations
  132. A Lightweight Multi-View Approach to Short-Term Load Forecasting
  133. Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh
  134. Wearable environmental sensing to forecast how legged systems will interact with upcoming terrain
  135. Genocide by Algorithm in Gaza: Artificial Intelligence, Countervailing Responsibility, and the Corruption of Public Discourse
  136. Fair Feature Importance Scores via Feature Occlusion and Permutation
  137. ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest
  138. Gradient Residual Connections
  139. One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning
  140. Weighted Wasserstein Barycenter of Gaussian Processes for exotic Bayesian Optimization tasks
  141. Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity
  142. All-in-One Conditioning for Text-to-Image Synthesis
  143. Faster Rates For Federated Variational Inequalities
  144. Minimum Distance Summaries for Robust Neural Posterior Estimation
  145. What do Geometric Hallucination Detection Metrics Actually Measure?
  146. Decoding Future Risk: Deep Learning Analysis of Tubular Adenoma Whole-Slide Images
  147. A Hybrid Deterministic Framework for Named Entity Extraction in Broadcast News Video
  148. SemanticMoments: Training-Free Motion Similarity via Third Moment Features
  149. UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation
  150. Counterfactual Maps: What They Are and How to Find Them
  151. Epistemic Throughput: Fundamental Limits of Attention-Constrained Inference
  152. Uncertainty-Aware Multimodal Emotion Recognition through Dirichlet Parameterization
  153. SpinCastML an Open Decision-Making Application for Inverse Design of Electrospinning Manufacturing: A Machine Learning, Optimal Sampling and Inverse Monte Carlo Approach
  154. Importance inversion transfer identifies shared principles for cross-domain learning
  155. A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation
  156. Distributed Hybrid Parallelism for Large Language Models: Comparative Study and System Design Guide
  157. From Adam to Adam-Like Lagrangians: Second-Order Nonlocal Dynamics
  158. Predicting magnetism with first-principles AI
  159. Patient foundation model for risk stratification in low-risk overweight patients
  160. Framework for Integrating Zero Trust in Cloud-Based Endpoint Security for Critical Infrastructure
  161. Learning to Remember, Learn, and Forget in Attention-Based Models
  162. DRAGON: Robust Classification for Very Large Collections of Software Repositories
  163. NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control
  164. AntigenLM: Structure-Aware DNA Language Modeling for Influenza
  165. Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning
  166. Enhanced Graph Transformer with Serialized Graph Tokens
  167. Predicting Open Source Software Sustainability with Deep Temporal Neural Hierarchical Architectures and Explainable AI
  168. scBench: Evaluating AI Agents on Single-Cell RNA-seq Analysis
  169. Autoregressive Image Generation with Masked Bit Modeling
  170. chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies
  171. Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models
  172. Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction
  173. CIC-Trap4Phish: A Unified Multi-Format Dataset for Phishing and Quishing Attachment Detection
  174. Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction
  175. ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
  176. ShapeCond: Fast Shapelet-Guided Dataset Condensation for Time Series Classification
  177. GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments
  178. ARO: A New Lens On Matrix Optimization For Large Models
  179. Data Science and Technology Towards AGI Part I: Tiered Data Management
  180. From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection
  181. Universal Coefficients and Mayer-Vietoris Sequence for Groupoid Homology
  182. Paradox of De-identification: A Critique of HIPAA Safe Harbour in the Age of LLMs
  183. Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning
  184. Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models
  185. StretchTime: Adaptive Time Series Forecasting via Symplectic Attention
  186. When do neural ordinary differential equations generalize on complex networks?
  187. Beyond Transcripts: A Renewed Perspective on Audio Chaptering
  188. Distributionally Robust Optimization via Generative Ambiguity Modeling
  189. Learning to Coordinate via Quantum Entanglement in Multi-Agent Reinforcement Learning
  190. Modeling 3D Pedestrian-Vehicle Interactions for Vehicle-Conditioned Pose Forecasting
  191. MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
  192. Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fields
  193. How Should We Model the Probability of a Language?
  194. GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search
  195. pixelLOG: Logging of Online Gameplay for Cognitive Research
  196. Provably robust learning of regression neural networks using β-divergences
  197. Online monotone density estimation and log-optimal calibration
  198. DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
  199. Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration
  200. Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion
  201. AMS-HD: Hyperdimensional Computing for Real-Time and Energy-Efficient Acute Mountain Sickness Detection
  202. Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks
  203. GEMSS: A Variational Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems
  204. Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit
  205. Positive Distribution Shift as a Framework for Understanding Tractable Learning
  206. Mitigating Memorization Where It Happens
  207. OmniReview: A Large-scale Benchmark and LLM-enhanced Framework for Realistic Reviewer Recommendation
  208. Discrete Bridges for Mutual Information Estimation
  209. Winner's Curse Drives False Promises in Data-Driven Decisions: A Case Study in Refugee Matching
  210. Scalable Delphi: Large Language Models for Structured Risk Estimation
  211. DeepQuali: Initial results of a study on the use of large language models for assessing the quality of user stories
  212. Contrastive Learning for Diversity-Aware Product Recommendations in Retail
  213. Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
  214. Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals
  215. Differentiable Logical Programming for Quantum Circuit Discovery and Optimization
  216. Learning Potentials for Dynamic Matching and Application to Heart Transplantation
  217. Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Scholar Recommendation
  218. Large Language Models for Geolocation Extraction in Humanitarian Crisis Response
  219. Understanding Dynamic Compute Allocation in Recurrent Transformers
  220. Near-optimal Swap Regret Minimization for Convex Losses
  221. Magnitude Distance: A Geometric Measure of Dataset Similarity
  222. FlattenGPT: Depth Compression for Transformer with Layer Flattening
  223. Discovering Interpretable Algorithms by Decompiling Transformers to RASP
  224. Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization
  225. Cutting Through the Noise: On-the-fly Outlier Detection for Robust Training of Machine Learning Interatomic Potentials
  226. Deciding the Satisfiability of Combined Qualitative Constraint Networks
  227. Affective Flow Language Model for Emotional Support Conversation
  228. Any-to-All MRI Synthesis: A Unified Foundation Model for Nasopharyngeal Carcinoma and Its Downstream Applications
  229. Kirin: Improving ANN efficiency with SNN Hybridization
  230. Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity
  231. textttlrnnx: A library for Linear RNNs
  232. Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AI
  233. How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs
  234. Root Cause Analysis Method Based on Large Language Models with Residual Connection Structures
  235. The Use of AI Tools to Develop and Validate Q-Matrices
  236. MOVA: Towards Scalable and Synchronized Video-Audio Generation
  237. LakeHopper: Knowledge-Aware Adaptation of Column Type Annotators across Data Lakes
  238. Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems
  239. On the Meta-Design of Allocation Problems
  240. A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
  241. Amortising Inference and Meta-Learning Priors in Neural Networks
  242. VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars
  243. Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
  244. FreqLens: Interpretable Frequency Attribution for Time Series Forecasting
  245. Efficient Brain Extraction of MRI Scans with Mild to Moderate Neuropathology
  246. HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training
  247. Belief Offloading in Human-AI Interaction
  248. MVAnimate: Enhancing Character Animation with Multi-View Optimization
  249. Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms
  250. On the Expressive Power of GNNs for Boolean Satisfiability
  251. Map of Encoders -- Mapping Sentence Encoders using Quantum Relative Entropy
  252. Foundation Inference Models for Ordinary Differential Equations
  253. Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation
  254. Artifact Reduction in Undersampled 3D Cone-Beam CTs using a Hybrid 2D-3D CNN Framework
  255. SynSacc: A Blender-to-V2E Pipeline for Synthetic Neuromorphic Eye-Movement Data and Sim-to-Real Spiking Model Training
  256. FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editing
  257. Rotated Lights for Consistent and Efficient 2D Gaussians Inverse Rendering
  258. Data Reconstruction: Identifiability and Optimization with Sample Splitting
  259. QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill
  260. Zero-shot System for Automatic Body Region Detection for Volumetric CT and MR Images
  261. PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments
  262. Exploring SAIG Methods for an Objective Evaluation of XAI
  263. TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
  264. FactSim: Fact-Checking for Opinion Summarization
  265. Intermediate Results on the Complexity of STRIPS11
  266. Why do we Trust Chatbots? From Normative Principles to Behavioral Drivers
  267. Technosocial risks of ideal emotion recognition technologies: A defense of the (social) value of emotional expressions
  268. Do Images Clarify? A Study on the Effect of Images on Clarifying Questions in Conversational Search
  269. Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm
  270. Challenges in Translating Technical Lectures: Insights from the NPTEL
  271. Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation
  272. Trapped by simplicity: When Transformers fail to learn from noisy features
  273. PBLean: Pseudo-Boolean Proof Certificates for Lean 4
  274. Old wine in old glasses: Comparing computational and qualitative methods in identifying incivility on Persian Twitter during the #MahsaAmini movement
  275. CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation
  276. OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
  277. ALIVE: Animate Your World with Lifelike Audio-Video Generation
  278. The Theory and Practice of MAP Inference over Non-Convex Constraints
  279. Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
  280. 6G-Bench: An Open Benchmark for Semantic Communication and Network-Level Reasoning with Foundation Models in AI-Native 6G Networks
  281. Learning to Judge: LLMs Designing and Applying Evaluation Rubrics
  282. A Machine Learning accelerated geophysical fluid solver
  283. WiFlow: A Lightweight WiFi-based Continuous Human Pose Estimation Network with Spatio-Temporal Feature Decoupling
  284. Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models
  285. Two-Stage Data Synthesization: A Statistics-Driven Restricted Trade-off between Privacy and Prediction
  286. Deep Learning-Based Fixation Type Prediction for Quality Assurance in Digital Pathology
  287. LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection
  288. We Should Separate Memorization from Copyright
  289. Debate is efficient with your time
  290. CauScale: Neural Causal Discovery at Scale
  291. Revisiting [CLS] and Patch Token Interaction in Vision Transformers
  292. Do Multilingual LLMs have specialized language heads?
  293. Enhancing Genetic Algorithms with Graph Neural Networks: A Timetabling Case Study
  294. ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregation
  295. Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration
  296. Overview and Comparison of AVS Point Cloud Compression Standard
  297. Constructive conditional normalizing flows
  298. An Attention Mechanism for Robust Multimodal Integration in a Global Workspace Architecture
  299. Kissan-Dost: Bridging the Last Mile in Smallholder Precision Agriculture with Conversational IoT
  300. TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models
  301. FairRARI: A Plug and Play Framework for Fairness-Aware PageRank
  302. retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers
  303. An arithmetic method algorithm optimizing k-nearest neighbors compared to regression algorithms and evaluated on real world data sources
  304. Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment
  305. M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data
  306. DNS: Data-driven Nonlinear Smoother for Complex Model-free Process
  307. FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction
  308. Rho-Perfect: Correlation Ceiling For Subjective Evaluation Datasets
  309. GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing
  310. How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location
  311. GISA: A Benchmark for General Information-Seeking Assistant
  312. Incremental (k, z)-Clustering on Graphs
  313. TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
  314. Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
  315. Causal Schr"odinger Bridges: Constrained Optimal Transport on Structural Manifolds
  316. Thegra: Graph-based SLAM for Thermal Imagery
  317. Automatic regularization parameter choice for tomography using a double model approach
  318. Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering
  319. TreeTensor: Boost AI System on Nested Data with Constrained Tree-Like Tensor
  320. Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
  321. Estimation of Fish Catch Using Sentinel-2, 3 and XGBoost-Kernel-Based Kernel Ridge Regression
  322. Are Vision Foundation Models Foundational for Electron Microscopy Image Segmentation?
  323. A General Theory of Proportionality with Additive Utilities
  324. Is Meta-Path Attention an Explanation? Evidence of Alignment and Decoupling in Heterogeneous GNNs
  325. Understanding Image2Video Domain Shift in Food Segmentation: An Instance-level Analysis on Apples
  326. Empirical Study of Observable Sets in Multiclass Quantum Classification
  327. CLEAR: A Knowledge-Centric Vessel Trajectory Analysis Platform
  328. Gesture Matters: Pedestrian Gesture Recognition for AVs Through Skeleton Pose Evaluation
  329. Time-Delayed Transformers for Data-Driven Modeling of Low-Dimensional Dynamics
  330. Learning Credal Ensembles via Distributionally Robust Optimization
  331. Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization
  332. Reliability-aware Execution Gating for Near-field and Off-axis Vision-guided Robotic Alignment
  333. TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation
  334. Estimating Aleatoric Uncertainty in the Causal Treatment Effect
  335. Decentralized Spatial Reuse Optimization in Wi-Fi: An Internal Regret Minimization Approach
  336. When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment
  337. RIFLE: Robust Distillation-based FL for Deep Model Deployment on Resource-Constrained IoT Networks
  338. Large Language Models and Impossible Language Acquisition: "False Promise" or an Overturn of our Current Perspective towards AI
  339. USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation
  340. Understanding and Optimizing Attention-Based Sparse Matching for Diverse Local Features
  341. The Connection between Kriging and Large Neural Networks
  342. Prism: Spectral-Aware Block-Sparse Attention
  343. LLMs + Security = Trouble
  344. Radial M"untz-Sz'asz Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
  345. Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms
  346. Optimizing Spectral Prediction in MXene-Based Metasurfaces Through Multi-Channel Spectral Refinement and Savitzky-Golay Smoothing
  347. Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting
  348. RealSynCol: a high-fidelity synthetic colon dataset for 3D reconstruction applications
  349. Altruism and Fair Objective in Mixed-Motive Markov games
  350. Modalities, a PyTorch-native Framework For Large-scale LLM Training and Research
  351. OJBKQ: Objective-Joint Babai-Klein Quantization
  352. Schr"odinger bridge problem via empirical risk minimization
  353. Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
  354. Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
  355. ViGoEmotions: A Benchmark Dataset For Fine-grained Emotion Detection on Vietnamese Texts
  356. Learning Human-Like Badminton Skills for Humanoid Robots
  357. WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints
  358. Roadmap to Quantum Aesthetics
  359. Circuit Representations of Random Forests with Applications to XAI
  360. E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
  361. TKGB: A Comprehensive Benchmark for Temporal Knowledge Graph Forecasting
  362. The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs
  363. All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
  364. UrbanGraphEmbeddings: Learning and Evaluating Spatially Grounded Multimodal Embeddings for Urban Science
  365. Effect-Level Validation for Causal Discovery
  366. Language-Guided Transformer Tokenizer for Human Motion Generation
  367. UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Models
  368. Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
  369. PACC: Protocol-Aware Cross-Layer Compression for Compact Network Traffic Representation
  370. Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference
  371. A Generative Model for Joint Multiple Intent Detection and Slot Filling
  372. CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment
  373. Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback
  374. TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
  375. JUSTICE: Judicial Unified Synthesis Through Intermediate Conclusion Emulation for Automated Judgment Document Generation
  376. On the Dynamics of Delayed Generalization in Linear Models
  377. Automatic Generation of Polynomial Symmetry Breaking Constraints
  378. The Vibe-Automation of Automation: A Proactive Education Framework for Computer Science in the Age of Generative AI
  379. When Does Context Help? Error Dynamics of Contextual Information in Large Language Models
  380. Trust-Based Incentive Mechanisms in Semi-Decentralized Federated Learning Systems
  381. Knowledge Augmented Entity and Relation Extraction for Legal Documents with Hypergraph Neural Network
  382. Noise Stability of Transformer Models
  383. Tighnari v2: Mitigating Label Noise and Distribution Shift in Multimodal Plant Distribution Prediction via Mixture of Experts and Weakly Supervised Learning
  384. Linguistics and Human Brain: A Perspective of Computational Neuroscience
  385. Language Modeling and Understanding Through Paraphrase Generation and Detection
  386. Puda: Private User Dataset Agent for User-Sovereign and Privacy-Preserving Personalized AI
  387. Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes
  388. Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification
  389. PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding
  390. G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
  391. Language Predicts Identity Fusion Across Cultures and Reveals Divergent Pathways to Violence
  392. Discrete Adjoint Schr"odinger Bridge Sampler
  393. PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognition
  394. Linearization Explains Fine-Tuning in Large Language Models
  395. On convexity and efficiency in semantic systems
  396. Document Reconstruction Unlocks Scalable Long-Context RLVR
  397. Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling
  398. Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization
  399. Generating Adversarial Events: A Motion-Aware Point Cloud Framework
  400. InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation
  401. Investigating Writing Professionals' Relationships with Generative AI: How Combined Perceptions of Rivalry and Collaboration Shape Work Practices and Outcomes
  402. Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
  403. Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators
  404. Distribution-Free Robust Predict-Then-Optimize in Function Spaces
  405. CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization
  406. LLMs and people both learn to form conventions -- just not with each other
  407. Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation
  408. Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Video
  409. PEGAsus: 3D Personalization of Geometry and Appearance
  410. Interpretable Dynamic Network Modeling of Tensor Time Series via Kronecker Time-Varying Graphical Lasso
  411. Dreaming in Code for Curriculum Learning in Open-Ended Worlds
  412. Chamelion: Reliable Change Detection for Long-Term LiDAR Mapping in Transient Environments
  413. Large Language Models in Peer-Run Community Behavioral Health Services: Understanding Peer Specialists and Service Users' Perspectives on Opportunities, Risks, and Mitigation Strategies
  414. Nexus: Inferring Join Graphs from Metadata Alone via Iterative Low-Rank Matrix Completion
  415. Information Geometry of Absorbing Markov-Chain and Discriminative Random Walks
  416. Nansde-net: A neural sde framework for generating time series with memory
  417. Fundamental Limits of Community Detection in Contextual Multi-Layer Stochastic Block Models
  418. A Causal Machine Learning Framework for Treatment Personalization in Clinical Trials: Application to Ulcerative Colitis
  419. Evasion of IoT Malware Detection via Dummy Code Injection
  420. Spherical Steering: Geometry-Aware Activation Rotation for Language Models
  421. DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentation