mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 31 May 2026

331 papers

  1. Position: Behavioral Systems Require Behavioral TestsLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. LeafData: An Agentic System for Data MigrationLLM agents and tool use → Web, search, and research agents
  3. Rethinking Fairness in LLM-Based Recommender Systems: A SurveyLLM reasoning → LLM reasoning for recommendation
  4. Blurry Window AttentionEfficient LLM inference and serving → KV cache optimization
  5. The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team SizeLLM agents and tool use → General LLM agent frameworks and benchmarks
  6. Target Updates May Stabilize Linear Q-Learning: Periodic and Soft DynamicsDeep reinforcement learning methods → RL theory and sample complexity
  7. A New Framework for Cybersecurity Refusals in AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  8. Inference Cost Attacks for Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → Privacy and security of RAG
  9. CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  10. D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output RewritingLLM safety and security → Jailbreaking
  11. On the Limits of Token Reduction for Efficient Unified Vision Language TrainingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  12. Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU FabricsEfficient LLM inference and serving → KV cache optimization
  13. TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series ReasoningLLM reasoning → Time series reasoning +1
  14. Splatshot: 3D Face Avatar Generation from a Single Unconstrained PhotoDiffusion models → 3D, point cloud and scene generation
  15. LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Collaboration TopologiesLLM agents and tool use → Software engineering coding agents
  16. Perception First: A Frontier Native-Video Model with Self-Consistency for Implicit Video Question AnsweringLLM reasoning → Multimodal reasoning
  17. MURMUR: An Efficient Inference System for Long-Form ASREfficient LLM inference and serving → Audio and omni-modal token compression
  18. SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video GenerationDiffusion models → Robustness, privacy and adversarial aspects +1
  19. Sparse Autoencoders for Interpretable Emotion Control in Text-to-SpeechMechanistic interpretability → Activation steering methods
  20. OmniOPD: Logit-Free On-Policy Distillation via Speculative VerificationKnowledge distillation → On-policy and self-distillation for LLMs +1
  21. Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case StudyLLM safety and security → Safety alignment, refusal and guardrails
  22. Cross-lingual Self-Consistency for Multilingual Reasoning with Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  23. An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  24. Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion ModelsDiffusion models → Flow matching, time series and science
  25. LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting WorldVision-language-action models → Tactile, force-aware and humanoid VLA
  26. Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference MisalignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  27. Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial IntelligenceLLM agents and tool use → Medical and scientific domain agents
  28. Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM PromptsLLM reasoning → Reasoning for agents, planning and code +1
  29. Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy ExecutionLLM agents and tool use → Agent memory systems
  30. DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question AnsweringLLM agents and tool use → Medical and scientific domain agents
  31. Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model SystemsLLM agents and tool use → Tool learning and function calling
  32. Autopilot-Preserving Residual Q-Learning with HJB-Inspired Finite-Action Risk Filtering for Fixed-Wing UAV Command SupervisionDeep reinforcement learning methods → RL for robot navigation and UAV control
  33. UniD3: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and ReasoningRetrieval-augmented generation → Medical and biomedical RAG
  34. Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document ParsingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  35. Fail-Closed Lowering of Resident KV Claims onto LLM Serving RuntimesEfficient LLM inference and serving → KV cache optimization
  36. Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical MemoryLLM agents and tool use → Software engineering coding agents
  37. Efficient Exploration for Iterative Nash Preference OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  38. Training-free image inversion for one-step diffusion modelsDiffusion models → Image generation, text-to-image and editing
  39. BRo-JEPA: Learning Modular Transformations in Latent SpaceWorld models → Latent predictive world models
  40. Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware ObservabilityLLM agents and tool use → Software engineering coding agents
  41. All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  42. Diamonds in the Sky: Pareidolic Animals in CloudsDiffusion models → 3D, point cloud and scene generation
  43. Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. LongAttnComp: Cross-Family Context Compression for Long-Context ReasoningEfficient LLM inference and serving → Efficient reasoning and agent inference
  45. Reducing Token Usage of State-in-Context Agents using MinificationLLM agents and tool use → Software engineering coding agents
  46. TukaBench: A Culturally Grounded Jailbreak Benchmark for African LanguagesLLM safety and security → Jailbreaking
  47. SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project WorkspacesLLM agents and tool use → Agent threats, guardrails and governance
  48. DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred ImagesDiffusion models → 3D, point cloud and scene generation
  49. SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent SystemsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  50. SkillAdaptor: Self-Adapting Skills for LLM Agents from TrajectoriesLLM agents and tool use → Agent skill learning and evolution
  51. What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear RegressionKnowledge distillation → General knowledge distillation methods
  52. Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual ReasoningLLM reasoning → Multimodal reasoning +1
  53. RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  54. ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction AlignmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  55. DeepIPCv3: Event-Aware Multi-Modal Sensor Fusion for Sudden Pedestrian Crossing AvoidanceEnd-to-end autonomous driving → End-to-end system architecture
  56. Agentic Clustering: Controllable Text Taxonomies via Multi-Agent RefinementLLM agents and tool use → Web, search, and research agents
  57. Trust Region On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  58. Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?LLM reasoning → Spatial and embodied reasoning
  59. Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to InterventionLLM reasoning → Test-time compute and efficient thinking
  60. Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving ChunkingLLM reasoning → Knowledge- and tool-augmented reasoning +1
  61. Training-Free Imitation Learning with Closed-Form Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  62. HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable SimulationLLM agents and tool use → Financial trading and forecasting agents
  63. Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast SamplingDiffusion models → Flow matching, time series and science +1
  64. Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMsLLM reasoning → Spatial and embodied reasoning +1
  65. DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  66. Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  67. ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic PlanningWorld models → World models for navigation
  68. Can LLM Agents Sustain Long-Horizon Organizational Dynamics?LLM agents and tool use → General LLM agent frameworks and benchmarks
  69. Low-Resource Safety Failures Are Action Failures, Not Representation FailuresLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  70. "Skill Issues'': Data-Centric Optimization of Lakehouse AgentsLLM agents and tool use → Software engineering coding agents
  71. CA-BED: Conversation-Aware Bayesian Experimental DesignLLM reasoning → Test-time compute and efficient thinking
  72. Bridging Multimodal Fusion and Expert Routing via Spectral Reliability Descriptors for Robust Object DetectionMixture-of-experts → Vision mixture-of-experts
  73. Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking
  74. BraveGuard: From Open-World Threats to Safer Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  75. Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future TrendsWorld models → Video-generation world models and simulators
  76. Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-ExpertsMixture-of-experts → Efficient MoE training and inference systems
  77. Expected Value Alignment for Generative Reward Modeling in Formal Mathematics VerificationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  78. ASE-26: a curriculum for agentic software engineering as a disciplineLLM agents and tool use → Software engineering coding agents
  79. Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  80. Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated RationalesSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  81. Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific BranchesLLM reasoning → Reasoning benchmarks and evaluation
  82. Schedule-Level Shared-Prefix Reuse for LLM RL TrainingMixture-of-experts → Efficient MoE training and inference systems
  83. SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill RevisionLLM agents and tool use → Agent skill learning and evolution
  84. Spiking and Event-driven Neuromorphic Mamba Models for Efficient Speech RecognitionState-space sequence models (S4, Mamba) → Speech and audio SSMs
  85. HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White PapersMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  86. From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  87. Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA ChallengeLLM reasoning → Multimodal reasoning
  88. Implicit Drifting Policy: One-Step Action Generation via Conditional Expert GeometryDiffusion models → Diffusion and flow policies for robotics
  89. Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLAWorld models → Embodied and robot world models +1
  90. Deep Research as Rubric for Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
  91. Strong Stochastic Flow MapsDiffusion models → Diffusion foundations and sampling
  92. MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial RoutingDeep reinforcement learning methods → RL for games and combinatorial optimization
  93. ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning TasksLLM reasoning → Test-time compute and efficient thinking
  94. Chameleon: Style-Content Disentangled Framework for Cross-Domain Object CompositingDiffusion models → Image generation, text-to-image and editing
  95. On the Generalization Gap in Self-Evolving Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  96. Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene GraphsOffline RL and imitation learning from data → Robot manipulation imitation learning
  97. Leyline: KV Cache Directives for Agentic InferenceLLM agents and tool use → Software engineering coding agents +1
  98. DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-ExpertsMixture-of-experts → MoE large language models
  99. MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  100. 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via CodeLLM agents and tool use → Multimodal and embodied agents
All 331
  1. Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
  2. TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation ReasoningLLM reasoning → Clinical and biomedical applications
  4. ExpWeaver: LLM Agents Learn from Experience via Latent RAGLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. OPD+: Rethinking the Advantage Design for On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +2
  6. Temporally-Aligned Evaluation for Audio-Driven Talking Head GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  7. A Unified Benchmark for Dynamic Medical Treatment Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
  8. τ0-WM: A Unified Video-Action World Model for Robotic ManipulationWorld models → Embodied and robot world models
  9. Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  10. DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMsDiffusion models → Discrete and text diffusion +1
  11. Hybrid Verified Decoding: Learning to Allocate Verification in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  12. Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  13. SWARD: Stochastic Window-Attention-Based Relational Distillation for Cross-Architectural Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  14. Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform SpreadingDiffusion models → Discrete and text diffusion
  15. Subliminal Learning Is Steering Vector DistillationMechanistic interpretability → Activation steering methods
  16. Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision SupportLLM reasoning → Chain-of-thought reasoning for driving
  17. Data Enrichment for Symbolic Regression Using Diffusion ModelsDiffusion models → Flow matching, time series and science
  18. An Open-Source Benchmark and Baseline for Multi-temporal Referring SegmentationLLM reasoning → Multimodal reasoning +1
  19. Make Your VLA More Robust Without More Data By Interleaving Motion PlanningVision-language-action models → 3D and spatial-aware VLA
  20. Lost in Delusion: Examining LLM Safety Under User Delusions and DistressLLM safety and security → Safety alignment, refusal and guardrails
  21. HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question AnsweringLLM reasoning → Clinical and biomedical applications
  22. Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural ManipulationVision-language-action models → Efficient VLA inference and adaptation
  23. Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  24. Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information DecompositionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  25. Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  26. COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional GenerationDiffusion models → Image generation, text-to-image and editing
  27. When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent CodingLLM agents and tool use → General LLM agent frameworks and benchmarks
  28. Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reductionDeep reinforcement learning methods → RL with diffusion and flow models
  29. FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit DeliberationLLM agents and tool use → Financial trading and forecasting agents
  30. AIREP: A Protocol for Per-Decision Evidence in AI Runtime Governance
  31. Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges
  32. LoRA-Diffusion: Parameter-Efficient Fine-Tuning via Low-Rank Trajectory Decomposition
  33. Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
  34. Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling
  35. Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governance in Everyday Human-Chatbot Interaction
  36. Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting
  37. A Formal Kinetic Theory for Zeroth-Order Newton Dynamics:Stein-Corrected Hessian Estimation and Curvature--Variance Trade-offs
  38. MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models
  39. Cross-Modal Hierarchical Fusion for from Multi-Sensor Ground Observation
  40. Multi-Agent DRL for QoS and Energy Optimization in RIS-Enabled Open-RAN Industrial 6G TN/NTN Networks
  41. Geometric Fairness-Aware Routing for Federated Edge Networks
  42. Measuring the Occupation-Level Impact of AbbVie Intelligence: AI Applicability Analysis, 2024-2025
  43. Interpolation between Convolution and Attention via K-Nearest Neighbors
  44. VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference
  45. Disagreement-Based Cross-Model Routing for Implicit Video Question Answering
  46. Active Inference for Adaptive Traffic Signal Control in Noisy Nonstationary IoT Environments
  47. AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?
  48. Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling
  49. Efficient Temporal Modeling for Mobile Sleep Staging via Lightweight Random Attention
  50. Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
  51. Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages
  52. Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
  53. Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing
  54. NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis
  55. AMN: An Adaptive Multi-Scale Fusion Network with Boundary and Uncertainty Modeling for Nuclei Segmentation
  56. Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment
  57. Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
  58. SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models
  59. Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF
  60. SegTune: Structured and Fine-Grained Control for Song Generation
  61. Semantic Retrieval for Product Search in E-Commerce
  62. CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability
  63. ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
  64. Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
  65. Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX
  66. A Minimalist Brain-Computer Musical Interface for Real-Time Emotion-Driven Sonification: System Design and Preliminary Evaluation
  67. Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
  68. Peacemaker at ATE-IT: Automatic term extraction from Italian text for waste management data using encoder model
  69. Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics
  70. Transferring Information Across Interventions in Causal Bayesian Optimization
  71. Before and After Temperature: A Distributional View of Creative LLM Generation
  72. Spatially Distributed Task-Oriented Compression for Multi-Emitter Localization and Characterization with Spectral Overlap
  73. UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
  74. The Value of Spike Timing: A Leakage-Resistant Benchmark of SNN Design Choices for Network Intrusion Detection
  75. CEAR: Certified Ensemble Adversarial Robustness in DNNs
  76. Learning from Saturated Data: Signals Beyond Correctness for LLM Training
  77. Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks
  78. On the Uncertainty Quantification Ability of Tabular Foundation Models
  79. Learning-based Directed Graph Abstraction of Combinatorial Spaces for Order-Preserving Search in Mixed-Combinatorial Nonlinear Optimization
  80. Target localization, identification and sensing using latent symmetries
  81. DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis
  82. GovAI-Pipe: A Layered AI Governance Pipeline for Citizen-Facing AI in Turkey's e-Government Gateway
  83. Agent Skills Should Go Beyond Text: The Case for Visual Skills
  84. Differentially Private Datastore Generation for Retrieval-Augmented Inference
  85. GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
  86. Neural Network Compression by Approximate Differential Equivalence
  87. Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
  88. PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
  89. GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning
  90. Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
  91. Beyond Access: Guided LLM Scaffolding for Independent Learning in Undergraduate Statistics
  92. From Performance to Representational Adequacy: A Representational Bootstrap Framework for Adaptive Biological Systems
  93. ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo
  94. Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research
  95. AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
  96. FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors
  97. ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats
  98. FlowSDR: Sufficient Dimension Reduction via Conditional Normalizing Flows
  99. Towards Optimal Robustness in Learning-Augmented Paging
  100. Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors
  101. FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normalization for Robust Long-Term Time-Series Forecasting
  102. Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware
  103. HOLA: Holistic Multi-Modal Alignment for Open-Set 3D Recognition
  104. Conditioned free-energy density of proteins using unbalanced solutions to constraint satisfaction problems
  105. SEArch: Optimistic Policy Selection Between Scene Noise and Drift for UAV Radar Search
  106. Digital Twin-Assisted Adaptive Multi-Agent DRL for Intelligent Spectrum and Resource Management in Open-RAN UAV-Enabled 6G Networks
  107. DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis
  108. Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery
  109. PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
  110. A Communication-Centric 6G-LLM Architecture for Scalable Tactical Autonomous Defense Vehicle Networks
  111. FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting
  112. When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
  113. Structure and Scale in Simplicial Sequence Modelling
  114. Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
  115. ChronosAD: Leveraging Time Series Foundation Models for Accurate Anomaly Detection
  116. Challenger at MultiPRIDE: Is It Hate Speech or Reclaimed?
  117. Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
  118. ResNet-34 with Lightweight Decoder for Accurate and Efficient Segmentation of Fetal Brain MRI
  119. Quantum Algorithm for Distributed Reduction of Entanglements (QADR): A Trainable and Simulation-Efficient QML Framework
  120. Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting
  121. BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
  122. Knowledge-Intensive Video Generation
  123. AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks
  124. KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
  125. Event-Based Vision in Space: Applications, Trends, and Future Directions
  126. Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination
  127. GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
  128. Exploiting In-Sensor Computing for Energy-Efficient Earth Observation
  129. Emergent Ordinal Geometry in Transformers Trained on Local Comparisons
  130. PALTO: Physics-Informed Active Learning for Tri-Gate FinFET Design Optimization for Vertical Power Delivery
  131. IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages
  132. Beyond Sinusoids: A Morlet Wavelet Framework for Transformer Positional Encoding
  133. Statistical Inference on Gradient Flows
  134. Distribution-free changepoint localization after sequential change detection
  135. Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
  136. SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback
  137. Variation Spaces for Encoder--Decoder Neural Operators: Approximation and Generalization
  138. Functional Clustering of Survival Data via Smoothed Log-Hazard Trajectories: A Risk-Dynamics Perspective
  139. Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline Diagnosis Using Multimodal Connectomes
  140. Differing Roles of Leisure and Productivity in GDP - A Machine Learning based comparative analysis of Germany and USA
  141. Application of Algorithms in Energy-Efficient Design Platforms for Green Building
  142. DAGGER: Gradient-Free Construction of Transiently Amplifying Networks under Hard Connectivity Constraints
  143. Advanced Mathematics Learning Behavior Prediction and Academic Early Warning Model Based on Multimodal Data Analysis
  144. Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
  145. Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancing
  146. Analysis of Ethnic Disparities in Autism Spectrum Disorder among Toddlers
  147. Riemannian Optimization for Hadamard Products of Low-Rank Matrices
  148. TECCI: Tricky Edits of Collected and Curated Images
  149. Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations
  150. The Shape of Wisdom: Decision Trajectories in Language Models
  151. Linear Strategic Classification with Endogenous Improvements
  152. PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis
  153. The Case for Model Science: Verify, Explore, Steer, Refine
  154. pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements
  155. Topological Ignorability for Structural Causal Effects Beyond Means
  156. Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies
  157. Temporal Motif Signatures for Temporal Graph Neural Networks
  158. Revisiting Neural Processes via Fourier Transform and Volterra Series
  159. AI From the Margins (AIM): Rethinking Participatory AI Design Through the Lived Experience of Minoritized Communities
  160. Fairness in two-player zero-sum games with bandit feedback
  161. HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
  162. When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
  163. CoSTL: Comprehensive Spatial-Temporal Representation Learning for Moment Retrieval and Highlight Detection
  164. memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations
  165. From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication
  166. Context-aware child-directed speech detection from long-form recordings
  167. Local MixVR: Breaking the Communication-Sample Dependence in Distributed Learning
  168. STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing
  169. A Per-Component Diagnostic Protocol for Neural HJB-PIDE Solvers under Control-Dependent L'evy Jumps
  170. Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
  171. Rank-Aware Quantile Activation for Motion-Robust Crop Segmentation in UAV Imagery
  172. HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
  173. R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking
  174. LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems
  175. Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture
  176. Digging Up Citations: FOSSIL, a Dataset and Workflow for Reference Extraction in Law and the Humanities
  177. How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?
  178. Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
  179. Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context
  180. MiCU: End-to-End Smart Home Command Understanding with Large Language Model
  181. Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
  182. CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation
  183. A Fiber Criterion for Representation Identifiability in Supervised Learning
  184. Measuring the Symmetry--Data Exchange Rate
  185. Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback
  186. Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows
  187. When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression
  188. Test-Time Training for Zero-Resource Dense Retrieval Reranking
  189. A Multiscale Network with Supervised Contrastive Learning for Real-Time Facial Emotion Recognition
  190. Before the Model Learns the Bug:Fuzzing RLVR Verifiers
  191. MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
  192. AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
  193. Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment
  194. TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images
  195. Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining
  196. Child-directed speech facilitates production, not comprehension, in BabyLMs
  197. Ask4VG: Risk-Aware Question Selection for Reducing Prior-Driven Answers in Medical VQA
  198. A Finite-Calibration Regime Map for LLM Judge Panels
  199. TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
  200. Data Collection for Training Quality-Control AI in Carpet Manufacturing
  201. ProductWebGen: Benchmarking Multimodal Product Webpage Generation
  202. Learning Neural Deformation Representation for 4D Dynamic Shape Generation
  203. Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
  204. PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
  205. AI-IoT-Robotics Integration: Survey of Frameworks, Emerging Trends, and the Path Toward Connected Robotics
  206. Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
  207. Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions
  208. Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach
  209. FVSpec: Real-World Property-Based Tests as Lean Challenges
  210. Automated Erythrocyte Detection and Tracking for Retinal Blood Flow Quantification in Erythrocyte-Mediated Angiography
  211. Theoretical Analysis of Engression and Reverse Markov Engression
  212. Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
  213. A Registry-Bound LLM Pipeline for Evidence-Grounded Trait Extraction across Tropical Plants, Aquatic Species, and Exotic Pets
  214. Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning
  215. Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
  216. Robust Asynchronous Planning via Auto-Formalization
  217. UME: A Unified Meta-Generalization Framework for Cross-Domain ETA
  218. Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States
  219. MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts
  220. SS-ZKR: Spatial-Semantic Zero-Knowledge Routing for Privacy-Preserving Multi-Agent Collaboration
  221. Towards Regret Guarantees for One-Step Lookahead Bayesian Optimization
  222. CryoProt: A Protein Pretraining Framework with Cross-Box Interactions on Cryo-EM Density Maps
  223. COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space
  224. Silent Failures in Federated Personalization of Foundation Models
  225. Lodestar: An Online-Learning LLM Inference Router
  226. PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
  227. Machine Learning Surrogate Modeling for Homogenization of Hyperelastic Materials with Boolean Microstructures
  228. Cellular Sheaf Neural Operators for Structure-Preserving Surrogate Modeling of Constrained PDEs
  229. One Channel to Rule Them All: Rethinking Input Representation for Visual Place Recognition
  230. Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial
  231. Efficient Synthetic Network Generation via Latent Embedding Reconstruction