mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 25 Jun 2026

432 papers

  1. When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
  2. At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM AgentsLLM agents and tool use → Software engineering coding agents +1
  4. Reward-Informed Sparse Autoencoders and the Solution-Completeness ConfoundMechanistic interpretability → Steering and interpreting LLM reasoning
  5. Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert MaskingMixture-of-experts → MoE large language models
  6. Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. PTStore (Prefix Tensor Store): Distributed Prefix Caching and Replication for High Throughput Inference ServingEfficient LLM inference and serving → KV cache optimization
  8. Diffusion-corrected Autoregressive Fourier Neural Operator for Droplet Evolution PredictionDiffusion models → Flow matching, time series and science
  9. Quantizing Recursive Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  10. Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data CollectionLLM agents and tool use → Web, search, and research agents
  11. PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh GenerationDiffusion models → 3D, point cloud and scene generation
  12. Tool Use Enables Undetectable Steganography in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  13. JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI AcceleratorsDiffusion models → Image generation, text-to-image and editing
  14. MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data AugmentationDiffusion models → Medical imaging and segmentation
  15. DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient DescentDiffusion models → Diffusion foundations and sampling
  16. Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and VerificationLLM agents and tool use → Software engineering coding agents
  17. COOPA: A Modular LLM Agent Architecture for Operations Research ProblemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Policy Gradient Learning for Distributionally Robust Markov Decision Processes under Wasserstein AmbiguityDeep reinforcement learning methods → RL theory and sample complexity
  19. Qwen-Image-2.0-RL Technical ReportDiffusion models → Image generation, text-to-image and editing +2
  20. Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM DecodingLLM reasoning → Hallucination detection and mitigation +1
  21. Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web AgentsLLM agents and tool use → Web, search, and research agents
  22. Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  23. PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model CalibrationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  24. Perceptual 3D Simulation With Physical World ModelingWorld models → Video-generation world models and simulators
  25. On the Inseparability of Instructions and Data in Shared-Embedding Sequence ModelsLLM safety and security → Prompt injection and agent security
  26. Quantum Generative Diffusion Model for Real-World Time SeriesDiffusion models → Diffusion foundations and sampling
  27. EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token PredictionEfficient LLM inference and serving → Speculative decoding
  28. MemoBench: Benchmarking World Modeling in Dynamically Changing EnvironmentsWorld models → Video-generation world models and simulators
  29. When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA SystemsLLM safety and security → Federated unlearning and poisoning
  30. The Curse of Multiple Mediators: Hidden Interaction Effects in Activation PatchingMechanistic interpretability → Circuits and mechanistic analysis
  31. ReWorld: Representation Learning for World Action ModelsWorld models → World models for autonomous driving
  32. Aloe-Vision: Robust Vision-Language Models for HealthcareMultimodal LLMs / vision-language models → Medical vision-language models
  33. QueenBee Planner: Skill-Evolving Communication Topologies for Token-Efficient LLM Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Internalizing the Future: A Unified Agentic Training Paradigm for World Model PlanningWorld models → World models for language agents +1
  35. Supersede: Diagnosing and Training the Memory-Update Gap in LLM AgentsLLM agents and tool use → Agent memory systems
  36. Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  37. When Does Personality Composition Matter for Multi-Agent LLM Teams?LLM agents and tool use → Social simulation and multi-agent debate
  38. PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-FoldingMechanistic interpretability → Interpreting biomedical and science models
  39. Glite ARF: Verifier-Driven Research with Parallel LLM Coding AgentsLLM agents and tool use → Web, search, and research agents
  40. Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector PlacementLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Towards Evaluation of Implicit Software World Models in Coding LLMsWorld models → World models for language agents
  42. DanceOPD: On-Policy Generative Field DistillationDiffusion models → Flow matching, time series and science
  43. Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency RewardsLLM reasoning → Multimodal reasoning +2
  44. World Action Models Enable Continual Imitation Learning with Recurrent Generative ReplaysWorld models → Embodied and robot world models +1
  45. Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
  46. PhysiFormer: Learning to Simulate Mechanics in World SpaceWorld models → Latent predictive world models +1
  47. Bridging Performance and Generalization in Reinforcement Learning for Agile FlightDeep reinforcement learning methods → RL for robot navigation and UAV control
  48. SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion TransformersDiffusion models → Video generation
  49. Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task PlanningLLM agents and tool use → GUI and mobile agents
  50. Hallucination in World Models is Predictable and PreventableWorld models → World models for language agents
  51. Not All Actions Are Equal: Rethinking Conditioning for Dexterous World ModelWorld models → Embodied and robot world models
  52. Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  53. LA4VLA: Learning to Act without Seeing via Language-Action PretrainingVision-language-action models → Human-video and latent-action pretraining
  54. Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job SearchLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  55. When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Prompt Injection in Automated R'esum'e Screening with Large Language Models: Single and Multi-Injection SettingsLLM safety and security → Prompt injection and agent security
  57. Resource-Aware Neuro-Symbolic Reasoning for Local Small Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  58. EO-WM: A Physically Informed World Model for Probabilistic Earth Observation ForecastingWorld models → Latent predictive world models
  59. E-TTS: A New Embodied Test-Time Scaling Framework for Robotic ManipulationLLM reasoning → Spatial and embodied reasoning
  60. CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMsLLM reasoning → Clinical and biomedical applications +1
  61. Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical AutonomyLLM agents and tool use → Multimodal and embodied agents
  62. Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-ImprovementSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  63. Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training RegimesLLM safety and security → Safety alignment, refusal and guardrails +1
  64. A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLOLLM agents and tool use → Software engineering coding agents
  65. HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  66. Automating Potential-based Reward Shaping with Vision Language Model GuidanceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  67. TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM InferenceLLM reasoning → Multimodal reasoning +2
  68. OpenRCA 2.0: From Outcome Labels to Causal Process SupervisionLLM agents and tool use → Software engineering coding agents
  69. PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action PoliciesVision-language-action models → Failure recovery and robustness
  70. PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action PoliciesVision-language-action models → Efficient VLA inference and adaptation +1
  71. Joint Learning of Experiential Rules and Policies for Large Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  72. Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario GenerationDiffusion models → Diffusion and flow policies for robotics
  73. Heavy-Ball Q-Learning with Residual Weighting CorrectionDeep reinforcement learning methods → RL theory and sample complexity
  74. The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and HumansLLM reasoning → Reasoning benchmarks and evaluation
  75. TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and EditingMixture-of-experts → Vision mixture-of-experts
  76. ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action ModelsVision-language-action models → Safety and adversarial attacks
  77. The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software DevelopmentLLM agents and tool use → Software engineering coding agents
  78. State Representation Matters in Deep Reinforcement Learning: Application to Energy TradingDeep reinforcement learning methods → Adversarial robustness and RL in finance
  79. ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCPLLM agents and tool use → Agent threats, guardrails and governance
  80. Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy OptimizationLLM reasoning → Reasoning benchmarks and evaluation +1
  81. Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQAMultimodal LLMs / vision-language models → Medical vision-language models
  82. A Generalization Theory for JEPA-Based World ModelsWorld models → Latent predictive world models
  83. Semantic Early-Stopping for Iterative LLM Agent LoopsLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. Adaptive Utility driven Resource Orchestration for Resilient AI (AURORA-AI)Deep reinforcement learning methods → RL for energy, networks and operations
  85. RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  86. ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  87. Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health InteractionsMechanistic interpretability → Probing deception, bias and beliefs
  88. How Much Static Structure Do Code Agents Need? A Study of Deterministic AnchoringLLM agents and tool use → Software engineering coding agents
  89. To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program RepairLLM agents and tool use → Software engineering coding agents
  90. Einstein World ModelsWorld models → World models for language agents
  91. Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story WorldsWorld models → Video-generation world models and simulators
  92. Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoEDiffusion models → Diffusion foundations and sampling +1
  93. Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced QueriesLLM safety and security → Jailbreaking
  94. Where Do CoT Training Gains Land in LLM based Agents?LLM reasoning → Prompting and chain-of-thought reasoning +1
  95. Chai: Agentic Discovery of Cryptographic Misuse VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance
  96. A Deterministic Control Plane for LLM Coding AgentsLLM agents and tool use → Software engineering coding agents
  97. GAVEL: Grounded Caption Error Verification and LocalizationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  98. Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World ModelingWorld models → World models for autonomous driving
  99. Diagnosing Task Insensitivity in Language AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  100. PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
All 432
  1. Confidence-Aware Tool Orchestration for Robust Video UnderstandingLLM reasoning → Multimodal reasoning
  2. Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference OptimizationDiffusion models → Diffusion recommenders +1
  3. Information-Aware KV Cache Compression for Long ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  4. TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report GenerationLLM reasoning → Hallucination detection and mitigation
  5. SpatialFlow-GRPO: Where Spatial Credit Drives Image EditingLLM reasoning → Reinforcement learning for reasoning
  6. PlanRL: A Trajectory Planning Architecture for Reinforcement Learning-based Driving ExpertsEnd-to-end autonomous driving → Reinforcement learning for driving +1
  7. Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and TrackingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  8. Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language AgentsLLM agents and tool use → Agent memory systems
  9. Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe SupervisionVision-language-action models → Tactile, force-aware and humanoid VLA
  10. Reasoning Quality Emerges Early: Data Curation for Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  11. NaviCache: Test-Time Self-Calibration Caching for Video GenerationDiffusion models → Video generation
  12. ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIPLLM reasoning → Multimodal reasoning
  13. MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAGRetrieval-augmented generation → Privacy and security of RAG +2
  14. OPID: On-Policy Skill Distillation for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  15. AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce PricingLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  16. LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models AccelerationDiffusion models → Diffusion foundations and sampling
  17. ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion AccelerationDiffusion models → Diffusion foundations and sampling
  18. EGG: An Expert-Guided Agent Framework for Kernel GenerationLLM agents and tool use → Software engineering coding agents
  19. HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual ReductionEfficient LLM inference and serving → Speculative decoding
  20. Knowledge-Based Pull Requests: A Trusted Workflow for Agent-Mediated Knowledge CollaborationLLM agents and tool use → Software engineering coding agents
  21. LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational LithographyWorld models → Latent predictive world models
  22. MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion SegmentationDiffusion models → Medical imaging and segmentation
  23. PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World ModelsWorld models → Video-generation world models and simulators
  24. Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust ModerationLLM reasoning → Reasoning for agents, planning and code +1
  25. PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUsEfficient LLM inference and serving → KV cache optimization
  26. Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric AttentionWorld models → Embodied and robot world models
  27. Autoformalization of Agent Instructions into Policy-as-CodeLLM agents and tool use → Agent threats, guardrails and governance +1
  28. Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal ReasoningLLM reasoning → Multimodal reasoning
  29. From Weights to Features: SAE-Guided Activation Regularization for LLM Continual LearningMechanistic interpretability → SAE features and their applications
  30. Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  31. Discovering Millions of Interpretable Features with Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  32. HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific VisualizationLLM agents and tool use → Multimodal and embodied agents
  33. Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism SwitchMixture-of-experts → Efficient MoE training and inference systems +1
  34. DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual CuesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  35. Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse ProblemsDiffusion models → Flow matching, time series and science
  36. Pingquanqi (Equalizer): A Cross-Domain Sociotechnical Framework for Human-Agent Interaction GovernanceLLM agents and tool use → General LLM agent frameworks and benchmarks
  37. Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought ReasoningLLM reasoning → Causal reasoning in LLMs
  38. Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  39. Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear AttentionMixture-of-experts → Mixture of LoRA experts
  40. Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image DetectionLLM agents and tool use → Multimodal and embodied agents
  41. From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISPLLM reasoning → Spatial and embodied reasoning
  42. DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language ModelsLLM reasoning → Multimodal reasoning
  43. Safety-Regulated Transfer Reinforcement Learning with Adaptive Teacher GuidanceDeep reinforcement learning methods → Safe and constrained RL
  44. VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  45. Radical AI InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  46. What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG AgentLLM agents and tool use → Medical and scientific domain agents
  47. NeuraDock Visual Cognitive Load Agent Tutorial: A Quality-Gated Open-Source EEG Workflow for Alpha Dynamics and Real-Time ApplicationsLLM agents and tool use → Medical and scientific domain agents
  48. Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving KnowledgeRetrieval-augmented generation → Agentic RAG, agents and memory +1
  49. Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation AllocationLLM reasoning → Test-time compute and efficient thinking
  50. Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time DataDeep reinforcement learning methods → RL for games and combinatorial optimization
  51. Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive ContextDiffusion models → Discrete and text diffusion
  52. What Survives When You Compress a Recursive Reasoner for the Edge?LLM reasoning → Test-time compute and efficient thinking
  53. Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  54. Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning TasksLLM reasoning → Diffusion reasoning and test-time scaling +1
  55. Localizing RL-Induced Tool Use to a Single Crosscoder FeatureLLM agents and tool use → Reinforcement learning for LLM agents +1
  56. Epiphany-Aware KV Cache Eviction Without the Attention MatrixLLM reasoning → Test-time compute and efficient thinking +1
  57. Soft Token Alignment for Cross-Lingual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  58. Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent
  59. Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result
  60. A Stable Aggregation Method for Quantum Federated Learning
  61. Cross-Platform Generalisation Failure in Mental Health Natural Language Processing: A Five-Axis Fairness Audit of Transformer Models on Social Media
  62. Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores
  63. Data Science Approaches to Evaluating Honours Candidates
  64. The Accuracy-Efficiency Paradox Quantifying Net Energy Loss in on-Device Energy Forecasting
  65. Beyond Information Retrieval: Generative AI as an Epistemic Arbiter to Enhance Collaborative Problem-Solving
  66. Foundation-Model Earth Representations Enable Regional-Scale Forest Aboveground Biomass Monitoring Across the Northeastern United States
  67. The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Explanations
  68. OpenMHC: Accelerating the Science of Wearable Foundation Models
  69. HantaWatch: Federated Learning for Hantavirus Genomic Surveillance
  70. Token-Level Cross-Modal Transformer with Contrastive Multi-Task Learning for Breast Cancer Subtype Classification and Survival Prediction
  71. Learning 3D Affordances for Blade Insertion in Cluttered Stowing
  72. AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors
  73. On the Necessity of a Liquid Substrate for Mesh Intelligence
  74. RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation
  75. Training Observable Control Policies to Expose Agent State Through Actions
  76. On the stability of scale-space metrics
  77. Spectral Subsurface Scattering from RGB via Biophysical Skin Inversion
  78. Global Explanations for Multivariate Time Series Forecasting Models via K-Order Markov Approximations
  79. Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing
  80. Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
  81. CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
  82. Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification
  83. SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction
  84. Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC
  85. hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freeways
  86. DeLux: Cross-Modal Local Artifact Restoration in Video Using Neuromorphic Data
  87. Fast-Mixing Markov Chains without Gradients
  88. Productionized Fairness Measurement Under Privacy Constraints
  89. Radar Guided Camera Verification for Automatic Emergency Braking Rethinking Object Detection in Radar Camera Fusion
  90. Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics
  91. Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling
  92. Advancing Speaker-Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordings
  93. Benchmarking Multi-Modal Graph-based Social Media Popularity Prediction
  94. The Context-Ready Transformer
  95. Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition
  96. Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
  97. Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros
  98. Boundary condition fidelity for bottom-hole pressure and CO2 plume prediction in geological carbon storage
  99. Tessellating The Earth
  100. Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints
  101. TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images
  102. DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
  103. SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds
  104. Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
  105. Sampling the Schwinger Model with Gauge-Equivariant Diffusion
  106. Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
  107. Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks
  108. The Decision Geometry of Covariance Estimation for the Global Minimum-Variance Portfolio under Heavy Tails
  109. Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns
  110. Geometry-Conditioned Fourier Neural Operators for Cubic Nonlinear Schrodinger Dynamics on Periodic Domains
  111. Directed Graph Topology Inference via Graph Filter Identification
  112. Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing
  113. Learning in Markovian bandits with non-observable states and constrained decision epochs
  114. Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026
  115. SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models
  116. Unified Zero-Shot Time Series Forecasting: A Darts Foundation
  117. GRAFT: Biological Graph and Hypergraph Benchmarks for Linked Gene Expression and Phenotypic Trait Prediction in Arabidopsis thaliana
  118. From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation
  119. Compression-Driven Anomaly Detection in Brain MRI Using an Interpretable Quantum Autoencoder
  120. DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning
  121. Automated brain tumor detection in MRI images using CNN and ResNet architectures
  122. DnA: Denoising Attention for Visual Tasks
  123. Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance
  124. Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
  125. Autoregressive Boltzmann Generators
  126. When are likely answers right? On Sequence Probability and Correctness in LLMs
  127. Error-Conditioned Neural Solvers
  128. All you need is log
  129. Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipeline
  130. Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching
  131. SAM2Matting: Generalized Image and Video Matting
  132. Language-Based Digital Twins for Elderly Cognitive Assistance
  133. RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
  134. Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding
  135. OctoSense: Self-Supervised Learning for Multimodal Robot Perception
  136. LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank
  137. Blackwell Approachability and Gradient Equilibrium are Equivalent
  138. Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
  139. ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
  140. See & Sniff: Learning Visuo-Olfactory Representations
  141. Multilingual Reasoning Cascades Need More Context
  142. Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
  143. A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets
  144. AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reported Breakdowns
  145. Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity
  146. Generative Models on Analog Hardware with Dynamics
  147. Simulation-based inference for rapid Bayesian parameter estimation in epidemiological models: a comparison with MCMC
  148. Recovering Governing Equations from Solution Data: Identifiability Bounds for Linear and Nonlinear ODEs
  149. How Good Can Linear Models Be for Time-Series Forecasting?
  150. Exact and Deterministic Patch Descriptor Retrieval via Hierarchical Normalization
  151. How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation
  152. BetXplain: An Explanation-Annotated Dataset for Detecting Manipulative Betting Advertisements on Social Media
  153. Ribbon: Scalable Approximation and Robust Uncertainty Quantification
  154. RSPC: A Benchmark for Modeling Stress and Psychiatric Conditions in Digitally Mediated Relationships using Psychiatrist Annotations
  155. Effective Covariance Dynamics in Solvable High-Dimensional GANs
  156. The Geometry of Updates: Fisher Alignment at Vocabulary Scale
  157. LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
  158. From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan
  159. Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
  160. CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
  161. Compositionality and the lexicon in evolutionary semantics
  162. SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting
  163. Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization
  164. Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
  165. Syntactic Belief Update as the Driver of Garden Path Processing Difficulty
  166. Graph Neural Networks Applications Across Domains: All Insights You Need
  167. Explaining Temporal Graph Neural Networks via Feature-induced Information Flow
  168. Forecasting With LLMs: Improved Generalization Through Feature Steering
  169. LISA: Likelihood Score Alignment for Visual-condition Controllable Generation
  170. RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage
  171. Stochastic Gradient Optimization with Model-Assisted Sampling
  172. Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
  173. DMuon: Efficient Distributed Muon Training with Near-Adam Overhead
  174. Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
  175. fTNN: a tensor neural network for fractional PDEs
  176. FlameVQA: A Physically-Grounded UAV Wildfire VQA Benchmark with Radiometric Thermal Supervision
  177. Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs
  178. Efficient foundation decoders for fault-tolerant quantum computing
  179. Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding
  180. Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
  181. Transformer-Based Classification of Bacterial Raman Spectra with LOOCV
  182. Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
  183. Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
  184. Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference
  185. SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
  186. Pseudo-Text-Conditioned 3D Grounding DINO for Organ Localization in Abdominal CT
  187. Finding Stationary Points by Comparisons
  188. PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views
  189. Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning
  190. Parametric Open Source Games
  191. How to evaluate clustering with ground truth?
  192. NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models
  193. Symplectic Neural Networks for Learning Non-Separable Hamiltonians
  194. MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment
  195. On-board Remote-Sensing Foundation Models for Unsupervised Change Detection of Disaster Events
  196. Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning
  197. Uncertainty quantification via conformal prediction in data assimilation
  198. Event-Aware Instructed Assistant for Referring Video Segmentation
  199. Enabling self-supervised learned primal dual with Noise2Inverse
  200. Decision-Aligned Evaluation of Uncertainty Quantification
  201. Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
  202. Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation
  203. In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
  204. XMSE-Aware Adaptive Empirical Bayes Estimation
  205. Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
  206. Computer Vision for MOBA Analytics: A Dataset and Baseline for Visibility Analysis in Dota 2
  207. RedVox: Safety and Fairness Gaps in Speech Models Across Languages
  208. Term-Centric Hierarchy Induction from Heterogeneous Corpora
  209. Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
  210. TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment
  211. PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation
  212. GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning
  213. Neural Texture Compression using Hypernetworks
  214. Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
  215. Learning to Recover Task Experts from a Multi-Task Merged Model
  216. SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages
  217. Tractography-Driven Synthetic Data Generation for Fiber Bundle Segmentation in Tracer Histology
  218. Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI
  219. Asymptotically Optimal Learning for Parametric Prophet Inequalities
  220. Bridging Vision and Language Concepts through Optimal Transport Semantic Flow
  221. RIS-Assisted Proactive Handover for Reliable mmWave Wireless Networks
  222. Accelerated sampling using SamAdams variable timesteps and position-adaptive Langevin dynamics
  223. Heterogeneous Neural Predictivity from Language Models During Naturalistic Comprehension
  224. A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models
  225. Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy
  226. Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance
  227. Rolling Shutter Relative Pose Estimation Made Practical
  228. Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT
  229. AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems
  230. LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation
  231. Context-Aware Synthesis of Optimization Pipelines for Warehouse Optimization
  232. Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication
  233. Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection
  234. Ordinal Neural Collapse as a Representation Prior for Visual Navigation
  235. The Capability Frontier: Benchmarks Miss 82% of Model Performance
  236. Identifying the Unknown: Prompt-Free Open Vocabulary Anomaly Recognition for Robot-Object Interaction
  237. Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection
  238. Quantization in Federated Learning: Methods, Challenges and Future Directions
  239. FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following
  240. Computational Analysis of Heart Rate Variability in Healthy Adults
  241. Data-Driven Duration Management -- Term Structure Forecasting Using Machine Learning
  242. Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction
  243. KARLA: Knowledge-base Augmented Retrieval for Language Models
  244. From Vajrayana Tara to Bengali Baul: A Computational Study of Lexical Transmission Across Buddhist, Shakta, and Vaishnava Traditions in Bengal
  245. Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
  246. Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games
  247. Evaluation Pitfalls and Challenges in Multimedia Event Extraction
  248. Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
  249. Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis
  250. Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data
  251. ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
  252. Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication
  253. Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
  254. ConvMemory v3: A Validity Context Layer for Conversational Memory via Target-Conditioned Relation Verification
  255. Structure Before Collapse: Transient semantic geometry in next-token prediction
  256. Depth-Semantic Alignment and Affinity-Guided Fusion for Structured Radar Point Cloud Generation
  257. PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation
  258. LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
  259. Do Image Editing Models Understand Lighting?
  260. Robust Onion: Peeling Open Vocab Object Detectors Under Noise
  261. Scientific discovery as meta-optimization: a combinatorial optimization case study
  262. State-specific respiratory signatures for affective and stress recognition: Interpretable respiratory markers, autocorrelation lags, and compact CNN models
  263. Socratic agents for autonomous scientific discovery in high-dimensional physical systems
  264. Full spectrum Unlearnable Examples via Spectral Equalization
  265. A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI
  266. Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution
  267. Extracting Neural Materials from Images
  268. Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation
  269. Kalman Prototypical Networks for Few-shot Fault Detection in Combined Cycle Gas Turbines
  270. DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors
  271. Intracranial Aneurysm Classification and Segmentation via Tri-Axial ROI and Multi-Task Learning
  272. Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation
  273. Learning Motion Feasibility from Point Clouds in Cluttered Environments
  274. Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification
  275. Attributed, But Not Incremental: Cannibalization-Corrected Attribution for Large-Scale Advertising
  276. DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
  277. NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
  278. SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
  279. Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
  280. TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
  281. Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence
  282. LAMP: Lane-Aligned Motion Primitives for Feasible Trajectory Prediction
  283. Generating Special Triangulations with Transformers
  284. Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space
  285. SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context
  286. Scalable Operator Learning via Nystr"om Approximation With Denoising Applications
  287. CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
  288. LayersReg: A Layer-by-Layer Progressive Regressor for Reliable Intraoperative 3D/2D Registration
  289. FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics
  290. Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions
  291. λ-PSD: Scalable Approximate SNR-Optimised Polynomial Stein Discrepancies
  292. Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean
  293. Sketched Linear Contrastive Learning: Approximation, Optimization, and Statistical Scaling
  294. TaskTok: Delving into Task Tokens for Task-driven Image Restoration
  295. LogicIR: Logic Gate Networks for Image Restoration
  296. LLM-based Models for Detecting Emerging Topics in Service Feedback
  297. Content-Based Smart E-Mail Dispatcher Using Large Language Models
  298. Empirical Software Engineering TerraProbe: A Layered-Oracle Framework for Detecting Deceptive Fixes in LLM-Assisted Terraform
  299. SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
  300. A Multi-Level Validation and Traceability Framework for AI-Generated Telescope Scheduling Decisions
  301. EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
  302. IDEA: Insensitive to Dynamics Mismatch via Effect Alignment for Sim-to-Real Transfer in Multi-Agent Control
  303. Revisiting Action Factorization for Complex Action Spaces
  304. Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework
  305. scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology
  306. Explainable Ensemble-Based Machine Learning Models for Detecting the Presence of Cirrhosis in Hepatitis C Patients
  307. SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Satellite Networks
  308. Coarse-to-Fine: A Hybrid Self-Supervised Method for Non-rigid 3D Shape Matching
  309. PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
  310. PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting
  311. Compiler-Driven Approximation Tuning for Hyperdimensional Computing
  312. Can Large Language Models Reliably Code Qualitative Humanitarian Data? A Benchmark Study Against Human Expert Adjudication
  313. CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry
  314. VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation
  315. The inattentional gap in task conditioned AI models that omit otherwise reportable safety critical signals
  316. Theory-Scale Auto-Formalization of Logics for Computer Science
  317. Assessing Post-Reform Changes in Risk Disclosure Quality with a Multidimensional Text Analysis Approach
  318. Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting
  319. Forget, Anticipate and Adapt: Test Time Training for Long Videos
  320. Budget-Aware Keyboardless Interaction
  321. DanceDuo: Bridging Human Movement and AI Choreography
  322. Learning Probabilistic Filters with Strictly Proper Scoring Rules
  323. Clinical Harness for Governable Medical AI Skill Ecosystems
  324. Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs
  325. An Empirical Study of LLM-Generated Specifications for VeriFast
  326. Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News
  327. Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting
  328. Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs
  329. Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization
  330. When Does Quality-Aware Multimodal Fusion Matter? A Leakage-Safe Diagnostic for Decision-Level Dependence
  331. A Causal Foundation Model for Structure and Outcome Prediction
  332. 3D Spatial Pattern Matching