mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 25 Sep 2026

514 papers

  1. Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache CompressionEfficient LLM inference and serving → KV cache optimization
  2. Regime Boundary Alignment for Evidence-Gated Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  3. On Evaluating and Improving Conversational Agents in ProductionLLM agents and tool use → Social simulation and multi-agent debate
  4. Toward Interactive Understanding of Code APIsLLM agents and tool use → Software engineering coding agents
  5. Find Something You Can't Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA ModelsVision-language-action models → Reinforcement learning and post-training +1
  6. Grasp2Twist: Learning Bimanual Dexterous Jar Opening by Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  7. EngramRAG: Dynamic Usage-Weighted Topology and Synaptic Consolidation for Multi-Hop Agentic MemoryLLM agents and tool use → Agent memory systems
  8. Receiver-Conditioned Latent Communication gives 94% CacheBackEfficient LLM inference and serving → Efficient reasoning and agent inference
  9. Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bitLLM agents and tool use → Tool learning and function calling
  10. Reasoning Concentrates Errors, and Self-Consistency Never NoticesLLM reasoning → Reasoning benchmarks and evaluation
  11. SilentCall: Hidden Tool-Call Backdoors in Open-Weight Agents, and How to Catch ThemLLM agents and tool use → Agent threats, guardrails and governance +1
  12. TriO: Tri-Modal Unsupervised Occupancy World Model for Anything PerceptionWorld models → World modeling from LiDAR generation
  13. Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  14. Mechanistic Interpretability Reveals Shared Causal Subspaces in Brain-to-Speech DecodersMechanistic interpretability → Circuits and mechanistic analysis
  15. CSI-Agent: LLM-Assisted Few-Shot Adaptation for Cross-Domain Wi-Fi CSI SensingLLM agents and tool use → Agentic AI for wireless networks
  16. Does Vision-Language Pretraining Granularity Matter? A Controlled Evaluation of Vision-Language Objectives Across Chest X-Ray Interpretation TasksMultimodal LLMs / vision-language models → Medical vision-language models
  17. Goal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case StudyLLM agents and tool use → Software engineering coding agents
  18. Symbolic Guidance for LLM Agents in Distributed Multiagent CoordinationLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAsLLM agents and tool use → Multimodal and embodied agents +1
  20. On-Policy Attention LinearizationLLM reasoning → Test-time compute and efficient thinking
  21. BioDyad: Synchronize Biomedical Discovery and Machine Learning EngineeringLLM agents and tool use → Medical and scientific domain agents
  22. Cache-Aware Conv3D Lowering Across Embedded World-Model DecodersWorld models → Video-generation world models and simulators
  23. Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic CoreLLM agents and tool use → Software engineering coding agents
  24. ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse ProblemsDiffusion models → Inverse problems and image restoration
  25. Overview of the TREC 2025 Million Large Language Models trackLLM agents and tool use → Web, search, and research agents
  26. Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement LearningLLM reasoning → Clinical and biomedical applications +1
  27. EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity TasksLLM reasoning → Reasoning for agents, planning and code +1
  28. GT-VLA: Target-Conditioned Trace Guidance for Generalizable Robotic ManipulationVision-language-action models → Generalist VLA models and benchmarks
  29. Choir: An Open Protocol for Distributed Multi-Agent AutoformalizationLLM agents and tool use → Software engineering coding agents
  30. Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-TrainingKnowledge distillation → On-policy and self-distillation for LLMs
  31. CyberWorld: World Models for Sample-Efficient Autonomous Cyber DefenseWorld models → World model security and GUI agents +1
  32. NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-SpeechDiffusion models → Audio, speech and music
  33. FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content PersonalizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  34. Agents Can Use Base Models to Evade AI DetectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  35. COUNTERMEM: World-Model Verified Counter-Factual Memory for Language AgentsWorld models → World models for language agents +1
  36. CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video UnderstandingLLM agents and tool use → Multimodal and embodied agents
  37. Deep Reinforcement Learning for Equity Trading: Benchmarking Actor-Critic Methods with Forward RetrainingDeep reinforcement learning methods → Adversarial robustness and RL in finance
  38. PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  39. Omni-IO Skills: Harnessing Your Agent Omni-NativeLLM agents and tool use → Software engineering coding agents
  40. SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility ConditionsLLM reasoning → Multimodal reasoning +1
  41. DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop ExecutionEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  42. ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise ConflictsVision-language-action models → Failure recovery and robustness
  43. MammoClaw: Towards Skill-Evolving Agent Harness for Breast Cancer Mammography AnalysisLLM agents and tool use → Medical and scientific domain agents
  44. Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning EfficiencyLLM reasoning → Test-time compute and efficient thinking
  45. First-Order Stationarity of Reverse DiffusionsDiffusion models → Diffusion foundations and sampling
  46. Learning Robot Policies from Sparse Success Signals via STL-Guided Stein Variational Policy GradientDeep reinforcement learning methods → RL for robot locomotion and manipulation
  47. User Model Extraction via Belief Self-DistillationKnowledge distillation → Knowledge distillation for LLMs
  48. Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not TransferLLM agents and tool use → Software engineering coding agents
  49. Trust Guided Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
  50. Strategically Diverse Sampling for Self-TrainingLLM reasoning → Reinforcement learning for reasoning +1
  51. DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese EducationLLM agents and tool use → Educational agents and math problem solving
  52. Multi-agent Scaling Across Disjunctive and Compensatory TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  53. Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIPLLM safety and security → Vision-language and text-to-image safety
  54. EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  55. A Flow Matching Framework for Neural Representational DissimilarityDiffusion models → Flow matching, time series and science
  56. Structured Reasoning Agentic Framework for Interpretable Critical View of Safety AssessmentLLM reasoning → Clinical and biomedical applications
  57. Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource EfficiencyLLM agents and tool use → Web, search, and research agents
  58. Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled AnalysisLLM reasoning → Multimodal reasoning +1
  59. TemplateCraft: Agentic Visual Template GenerationLLM agents and tool use → Multimodal and embodied agents
  60. From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-TrainingMultimodal LLMs / vision-language models → Medical vision-language models
  61. ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMsMultimodal LLMs / vision-language models → Medical vision-language models
  62. Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  63. Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate SynthesisLLM agents and tool use → Social simulation and multi-agent debate
  64. CognitiveReality: Robot-Agnostic Semantic Gaussian Mapping with an LLM Agent for Immersive Collaborative VR TeleoperationLLM agents and tool use → Multimodal and embodied agents
  65. Evaluating the accuracy of KV cache reuse techniquesEfficient LLM inference and serving → KV cache optimization
  66. Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic LayersMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  67. ActKV: Efficient LLM Agents through Action-Guided KV Cache ManagementLLM agents and tool use → Agent memory systems +1
  68. InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open DataWorld models → Embodied and robot world models
  69. Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory OptimizationEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  70. ContraFM-S2O: Flow Matching-Based One-step SAR-to-Optical Image Translation Model with Contrastive LearningDiffusion models → Inverse problems and image restoration
  71. RECAST: From Log Replay to Closed-Loop Driving Simulation with View-Complete ActorsEnd-to-end autonomous driving → Generative simulation for driving
  72. A Safety-Bounded SDC-to-MCP Gateway for Medical AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  73. Open Vocabulary Domain UnlearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  74. DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World ModelsWorld models → Embodied and robot world models +1
  75. Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model AnswersRetrieval-augmented generation → RAG robustness and adaptive retrieval
  76. AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  77. Towards VLA-Dreamer: Refining VLA Behavior Using World ModelsWorld models → Embodied and robot world models +2
  78. Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent WorkflowsLLM agents and tool use → Software engineering coding agents
  79. G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow PoliciesOffline RL and imitation learning from data → Offline multi-agent RL
  80. MA-WAM: Multi-Agent World-Action Model for Test-Time PlanningWorld models → Latent dynamics models and model-based RL
  81. DIAL: Position-Debiased LLM Judges with Adaptive Human Preference CalibrationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  82. Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric ModelingOffline RL and imitation learning from data → Robot manipulation imitation learning
  83. Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal ConditioningDiffusion models → 3D, point cloud and scene generation
  84. Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMsLLM reasoning → Audio-language model reasoning
  85. AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User SideLLM agents and tool use → Agentic recommender systems
  86. WorldTS: World Modeling for Multimodal Covariate-aware Time Series ForecastingWorld models → Latent predictive world models
  87. I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?World models → Latent predictive world models
  88. CRNDiff: Count-Native Diffusion Framework via Chemical Reaction NetworksDiffusion models → Flow matching, time series and science
  89. JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions ModelsDeep reinforcement learning methods → RL training of language and agent models
  90. Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One YearKnowledge distillation → Federated, robust and private distillation
  91. Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?LLM reasoning → Multimodal reasoning +1
  92. INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region RefinementEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  93. LocUS: Head Selection and Subspace Projection for Targeted Activation SteeringMechanistic interpretability → Activation steering methods
  94. Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  95. DualManip: Agentic Dynamic Manipulation via Dual-Path Semantic Reasoning and Geometric AdaptationLLM reasoning → Spatial and embodied reasoning +2
  96. DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  97. A Flatness-Generalization Relation in the Teacher-Student Tree-Committee MachineKnowledge distillation → General knowledge distillation methods
  98. Up and Down the Abstraction Ladder: Code-Based Skills for Language AgentsLLM agents and tool use → Agent skill learning and evolution
  99. Quantum Diffusion Models for Medical Image AnalysisDiffusion models → Medical imaging and segmentation
  100. Modeling quantum neural network gradient with reinforcement learningDeep reinforcement learning methods → Quantum reinforcement learning
All 514
  1. CG-Probes: Recovering Guardrail Directions from Patient Query EmbeddingsLLM safety and security → Safety alignment, refusal and guardrails
  2. Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse AutoencodersLLM safety and security → Machine unlearning +1
  3. Cheap, open agents make LLM pollution harder to mitigateLLM agents and tool use → Social simulation and multi-agent debate
  4. Where Compute Matters: Heterogeneous Attention for Efficient Video DiffusionDiffusion models → Video generation
  5. Kintsugi-VLA: Turning Failed Robot Rollouts into Recovery Data through Interventional RecoverabilityVision-language-action models → Failure recovery and robustness
  6. DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM ServingLLM agents and tool use → Software engineering coding agents +1
  7. TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak AttacksLLM safety and security → Jailbreaking
  8. Precision at Speed: Sample-Efficient Online Model-Based Reinforcement Learning for Hydraulic Excavator ControlDeep reinforcement learning methods → RL for robot navigation and UAV control
  9. Robust Successor FeaturesDeep reinforcement learning methods → Deep RL algorithms and representations
  10. ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce RerankerLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  11. The Linear Representation Hypothesis for Vision-Language-Action ModelsVision-language-action models → VLA architectures and generalization +1
  12. FLIP: Final Layer Inference-Time Probing for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  13. PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-ResolutionDiffusion models → Inverse problems and image restoration
  14. FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  15. CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  16. Does Uniform Discrete Diffusion Need Time?Diffusion models → Discrete and text diffusion
  17. SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  18. FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot ManipulationVision-language-action models → World model-based VLA
  19. FTB Graph: Determining and Validating First-token Broadcasters and Language-Identity Head Circuits in Multilingual Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  20. MVVBench: Benchmarking 4D Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  21. PORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling ProblemOffline RL and imitation learning from data → Offline RL algorithms
  22. OneWorld: Learning Consistent Physics Across Actions in World ModelsWorld models → Latent predictive world models
  23. LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent DraftingRetrieval-augmented generation → Legal and financial RAG
  24. Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing MechanismsLLM agents and tool use → Financial trading and forecasting agents
  25. MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal MemoryLLM agents and tool use → Medical and scientific domain agents
  26. Self-Play Search Distillation for Large Language Model ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  27. UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in UltrasoundMultimodal LLMs / vision-language models → Medical vision-language models
  28. Causeway: Restoring Task Accessibility for Instruction Switching in VLA PoliciesVision-language-action models → Failure recovery and robustness
  29. ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement LearningLLM agents and tool use → Tool learning and function calling +1
  30. QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage RerankingLLM reasoning → Knowledge- and tool-augmented reasoning
  31. From annotation to reasoning: Culture in language modelsLLM reasoning → Reasoning benchmarks and evaluation
  32. From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native DeeplinksLLM agents and tool use → GUI and mobile agents
  33. CacheReforge: Bounded Recovery for Stale KV Caches under Evolving AdaptersEfficient LLM inference and serving → KV cache optimization
  34. TISD: On-Policy Self-Distillation with Trajectory InterventionKnowledge distillation → On-policy and self-distillation for LLMs
  35. VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RLVision-language-action models → Reinforcement learning and post-training
  36. Persistent Negatives for Adversarial Black-Box On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  37. SkillEvoReg: Regularizing Agent Skill Evolution Against OverfittingLLM agents and tool use → Agent skill learning and evolution
  38. Learning Chance-Constrained MDPs with Bellman Distributional CertificatesDeep reinforcement learning methods → RL theory and sample complexity
  39. The KV Cache Is the New Memory WallEfficient LLM inference and serving → KV cache optimization
  40. Enhancing Assessment of Self-Consistency in LLM Explanations using Perturbation StrengthLLM reasoning → Reasoning benchmarks and evaluation
  41. Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape AnalysisDiffusion models → Discrete and text diffusion +1
  42. Aligning One-Step Generative Models with Reward-Weighted Transport DistillationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  43. MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  44. Fast Plans, Faithful Actions: Closing the Planning-Execution Gap in Hierarchical Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  45. Evaluation Is All You Need for Multi-Modal Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  46. Understanding the Role of Prompt Template in Knowledge Distillation for Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  47. Evaluating Real-Time Voice Agents: From Component Quality to Grounded OutcomesLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM AgentsLLM agents and tool use → Agent memory systems +1
  49. ConsultMind:Towards Automated Diagnostic Consultation via Uncertainty-Aware ReasoningLLM reasoning → Clinical and biomedical applications
  50. Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  51. Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create MoreLLM reasoning → Prompting and chain-of-thought reasoning
  52. Timo: Taming Multimodal Diffusion Transformer for Human Motion GenerationDiffusion models → Video generation
  53. Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache EvictionEfficient LLM inference and serving → KV cache optimization
  54. Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM WorkflowsLLM agents and tool use → Software engineering coding agents
  55. Analyzing and Mitigating Cost-Inefficient Behaviors in Coding AgentsLLM agents and tool use → Software engineering coding agents
  56. EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight DetectionMixture-of-experts → Vision mixture-of-experts
  57. RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User IntentLLM agents and tool use → Agentic recommender systems
  58. Recommendation World Models for Future-State ControlWorld models → Latent dynamics models and model-based RL
  59. The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?LLM reasoning → Test-time compute and efficient thinking
  60. MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  61. Learning Vision-Based Agile Gap Traversal: Differentiable Simulation with a Warm-Started CriticDeep reinforcement learning methods → RL for robot navigation and UAV control
  62. StarWM: Self-Supervised Trained Attention Routing for Robust World ModelsWorld models → Video-generation world models and simulators
  63. LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  64. DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume RenderingDiffusion models → 3D, point cloud and scene generation
  65. Prompt Injection Detection for Email Agents Through Attack Chain ModelingLLM safety and security → Prompt injection and agent security
  66. Recursive Self-Improvement via On-Policy Distillation for ReasoningKnowledge distillation → On-policy and self-distillation for LLMs
  67. Algebraic Integer Quantization for Machine Learning Applications
  68. Child ASR Adaptation with Adult Retention: An Empirical Study
  69. PanoPed: Beyond Bounding Boxes for Sim-to-Real Panoramic Pedestrian Tracking
  70. Autonomous Driving Research Requires a Community-Driven Data Paradigm
  71. HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning
  72. A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing
  73. LENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis
  74. Multi-Jurisdictional Legal Identity Assurance for Capability Gating: A Design-Science Proposal for Tiered, Reusable Identity Assurance of Natural, Juridical, and Machine Entities
  75. Partial AUC Maximization from Positive-unlabeled Data
  76. Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
  77. Airfoil2Vec: Spectral Geometry-Conditioned Neural Surrogate Models for Airfoil Aerodynamics and a Downforce-Generating CFD Dataset
  78. Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation
  79. Do Evidence-Reading Diagnostics Improve Interface Selection in Small LLM Recommenders?
  80. CRASM-Gate: Deterministic-First Constraint- and Role-Aware Semantic Mapping with Selective Model Assistance Across Heterogeneous Industrial Standards
  81. Resolving the Missing Financial Data Crisis: A Generative AI Pipeline for SEC 10-K Extraction
  82. Beyond Discrimination: Calibrated Geoprior Fusion for Bioacoustic Monitoring
  83. The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
  84. Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles
  85. Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
  86. Position: Let's Strengthen Verifiability If We Can't Enforce Reproducibility
  87. A Mesoscopic View of Transformer Weights Through Row and Column Scale Fields
  88. Learned Compression of SAR Phase-History Data: A Rate-Honest Feasibility Study on GOTCHA
  89. Hyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling
  90. Period Segmentation in Transition Network Analysis: A Topological Data Analysis Approach
  91. GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games
  92. Memory as Middleware for Self-Improving AI Agents
  93. When Should a Human Take Back Control? Optimal Delegation under Turbulent AI Risk
  94. mu-bench: A Multilingual Utterance Transcription Benchmark
  95. ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting
  96. Correcting the Dropout-LayerNorm Expectation Gap Improves Protein Structure Models
  97. Contract monitoring: governing AI via separation of powers
  98. Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox
  99. Graph Forward Distribution Matching for Molecular Inverse Design
  100. Tracing Decoder Artifacts for Compact Synthetic Speech Screening
  101. Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation
  102. Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence
  103. ControlGS: Conditioning Neural Gaussians for Downstream-Processing-Aware XR Rendering
  104. ScreenHaystack: Finding Blind Zones in GUI Grounding
  105. Who Governs Data in the AI Era? A Computational Analysis of the U.S. Privacy Workforce in Job Postings
  106. Depth Any Seen: Which Surfaces and How Far?
  107. Continuous-Time Trajectory Generation from Discrete Observations with Stochasticity
  108. A Benchmark for LLM's Understanding of Middle School and High School Science Topics
  109. Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding
  110. Representation Learning for Exact Preimages
  111. VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale
  112. Human Activity Recognition via Ultra-Wideband Data: A Framework for Dimensionality Reduction, Pattern Discovery, and Predictive Modeling
  113. Is invariance all you need for algorithmic fairness? Removing demographic information can create new bias
  114. What Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation
  115. SenseAgent: An LLM Agent for Adaptive Cross-Domain IMU Sensing
  116. VC Dimension and Expressivity of Real-Valued Transformers
  117. Type-Balanced Federated Learning for Visual Analog Meter Reading
  118. Integrating Language Models into Listened and Imagined Speech Decoding from MEG
  119. Can Circuit Alignment Predict OOD Generalization?
  120. Identifiability Limits of Gravitational Wave Phase Deviations: Multiclass Classification with a Multihead Neural Network
  121. Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game
  122. Lagrangian and Hamiltonian Neural Networks With a Dissipative System
  123. Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix
  124. Evasion Attacks on Cost-Utility-Based Adversarial Training for Online AutoML in IoT Networks
  125. Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows
  126. Toward Embedding-Based Psychometrics: Structural Modeling of Assessment-Item Semantics With Contextual Scores
  127. Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs
  128. Extraction of clinical findings from mammography and breast ultrasound reports: a comparison between specialists and Artificial Intelligence
  129. Double-Edged Sword of Mediated Visibility: How Visual Framing Undermines Congresswomen's Perceived Competence
  130. IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages
  131. SNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression
  132. Improving Audiovisual Speech Recognition through Synthetic Visual Data Augmentation
  133. Model-Agnostic Online Certificate-Driven Calibration for Time Series Forecasting Under Distribution Shift
  134. Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction
  135. Simple Extensions of Single-Objective Acquisition Functions and Hedge Strategies for Multi-Objective Bayesian Optimization
  136. Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations
  137. Artificial Neural Network Assisted Modelling of Tangent Galvanometer Measurements for the Determination of Horizontal Component of Earth's Magnetic Field
  138. Recipe-Matching, Not Equivalence
  139. Vibe Analysis: Exploring LLM Adoption by Data Visualization Practitioners
  140. ROTE: Benchmarking Neural Memorization on Complexity-Controlled Symbolic Sequences
  141. Facial classification Using Hybrid Quantum Machine Learning
  142. PredRA: Fast Medical Image Translation by Deterministic Component Extraction and Controlled Stochastic Refinement
  143. Improving Medical Calculation of LLMs with Embedded Coding
  144. MAESTRO: a Multimodal Auditory-attention Egocentric Speech-TRacking Open corpus
  145. Context-dependent agent evaluation with orthogonal equilibrium learning
  146. Auditing Quality Filters for Long-Tail Human Data Curation
  147. Knowledge-Driven XRD Phase Identification via Multi-View Retrieval and Explanation
  148. DOHF: Online Diffusion Fine-tuning with Doob's h-transform Guidance
  149. TemporalGraphLLM: Temporal Graph Neural Networks with Large Language Models for Dynamic Text-Attributed Graphs
  150. A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
  151. IndustryLLM: Failure-Driven LLM Training for Industrial Procurement
  152. Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals
  153. AirLog: Store-Level Indoor Life Logging Made Easy
  154. Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks
  155. LLM Judge Validation Under Sparse Overlap: From Inference to Design
  156. Averaged Mirror Descent and Dual Gradient Methods: Convergent Algorithms for Entropic Gromov-Wasserstein Problems
  157. A Surgical Foundation Model Reveals Task-Dependent Label Efficiency
  158. Relational Compression: A Framework for Relational Fidelity in Constrained Representations
  159. Awaken, Then Scale: Tiny Adaptation for MRI Reconstruction
  160. Beyond Sparsity: Weight Location and Network Context in Pruned MRI Reconstruction
  161. Video-to-Music Generation for Gameplay Videos
  162. Medium-Term Multi-Resolution Electric Load Forecasting using Economic Data and Foundation Model
  163. Electric Potential Patterns Forecasting in the Southern Hemisphere with Deep Learning Techniques
  164. seq2cause: One Autoregressive Backbone, Four Causal Discovery Tasks in Event Sequences
  165. Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?
  166. Rate-Adaptive One-Step Diffusion Compression for AIGC Images
  167. Working with AI: A Design Framework for Human-AI Collaboration
  168. CP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows
  169. SelfCue: Making a 3D CT Report Generator Say What It Already Knows
  170. FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders
  171. Gap-free Differentially Private PCA for Gaussian Data
  172. Statistical attribute alignment for black-box generative AI via output post-processing
  173. New LoRA Skills Should Read but Never Write
  174. GraphWrit3R: End-to-End 3D Scene Graph Writing
  175. Common-Mode Collapse and Recovery in Direct Feedback Alignment
  176. How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI
  177. OC-GS: Gaussian Splatting for Irregular Turntable Capture
  178. Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach
  179. Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum
  180. Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights
  181. Generalization behavior of OPTQ and the role of regularization
  182. Online Learning via Learned Latent Bayesian Tracking
  183. MexHat: A Dataset for Hate Speech Detection in Mexican Spanish Videos
  184. Two Conformal Constructions for Adaptive Within-Document AI-Text Screening
  185. BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment
  186. Can You Check That? The Checkability Boundary for Local LLM Network Automation
  187. NEXT: Physics-Informed Neuro-Spectral Exponential Time Differencing Architectures
  188. HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning
  189. Retrainable physics-integrated neural differentiable modeling of sintering across material systems
  190. Forensic Twins: Self-Supervised Residual Learning for AI-Generated Image Forensics
  191. Statistical Foundations for a Google Play User-Review Sentiment Index: Signal Fusion, Shrinkage, Distributional Validation, and Dynamic Smoothing
  192. Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
  193. ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
  194. SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery
  195. Evaluating Cultural Awareness of LLMs for Haitian Creole
  196. Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity
  197. Retail Product Search: A Practical Approach at Target
  198. UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting
  199. Scaling Density Functional Theory with Gaussian Splatting
  200. "AI is (not) the new...": A Diagnostic Analogy Framework for Generative AI's Cultural Impacts
  201. Game Arena: Strategic LLM Evaluation in Competitive Environments
  202. Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
  203. LandscapeSHAP: Which Persistent Homology Class Gets the Credit?
  204. PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents
  205. Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks
  206. Uncertainty-Aware Federated Learning for Infant Movement Analysis
  207. KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning
  208. Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers
  209. Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality
  210. Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding
  211. Implicit Neural Representation for Hyperspectral Video Compression
  212. AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy
  213. AFA-Net: A Differential Attention Approach for Auditory Attention Detection
  214. Decodable In-Context State and Model Output Across Training
  215. Differential Attention Unlocks Complementary EEG and Speech Fusion for Emotion Recognition
  216. Intent2Tc: Automated Intent-to-Traffic Control Translation with Language Models
  217. Multivariate conformal uncertainty propagation in multitask atomistic simulation: Successes and pitfalls
  218. Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
  219. Evaluating Budgeted Context Projection with Unexecuted Companion Runs
  220. Towards Whole-Study Screening for Congenital Heart Disease in Fetal Ultrasound Using Multiple Instance Learning
  221. Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness
  222. Equation discovery with Bayesian tree-adjoining grammars
  223. OpenVAM: Open-World Visual Attention Modeling with VLMs
  224. Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
  225. Programs-of-Layers in LLMs through the Lens of Cortical Areas
  226. Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
  227. Progressive Memory Transformer: Memory-Aware Attention for Time-Series
  228. The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
  229. ChronoFuseGS: Multi-Temporal Gaussian Fusion with Per-Splat Persistence and Change Visualization
  230. Bridging Body and Brain: Gene-Driven Morphology--Control Co-Design
  231. CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support
  232. More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting
  233. LUCID: Learning Under Confounding for Inference and Discovery in Time Series
  234. CytoSPM: Open-Vocabulary Cytopathology Detection with Structured Prompt Bank
  235. Benchmarking Attention for Tabular Foundation Models
  236. Geometric Moment Contraction for Stochastic Nesterov Acceleration
  237. UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning
  238. Why Alzheimer's Speech Screening Fails to Generalize: Bridging the Deployment Gap via Cross-Corpus Evidence Anchoring
  239. Softmax Reparameterization for Output-Head Quantization
  240. MoTop: Motion-Topological Model For Micro AU Detection
  241. Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains
  242. Cognitive Skills in the Age of AI: Computing Students and Experts Perceptions
  243. Identifying Scientists on X
  244. MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries
  245. Agentic Limit Order Books: Phase Transitions and Market Impact
  246. PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding
  247. Deterministic Regime Switching and Feasibility Inversion in Dynamic Tensor Rematerialization
  248. Gauss What You Need: Compact Gaussian Splatting Across Scene Scales
  249. Geometric Inconsistency Localization in Multi-View Image Sets
  250. RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models
  251. Purin: A Biology-inspired Mechanism for Artificial Neural Networks
  252. WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery
  253. Acoustic-to-Text KV Compression for Full-Duplex Speech Models
  254. Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion
  255. Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution
  256. Self-Supervised Representation Learning: From Spectral Foundation Models to Auroral Emission Spectra
  257. FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps
  258. Preserve-and-Compose Training for Composed Image Retrieval
  259. Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture
  260. Light Field Primitive for Novel View Synthesis
  261. ALF: An Active Learning Framework for Scientific Discovery
  262. Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews
  263. Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation
  264. Accounting for Bias Enables Sustainable LLM Evaluation
  265. Where a Model Sends Its Own Repeated Token
  266. BAT-CLIP: Trimodal Alignment of Brain, Audio and Text
  267. SPO: Discovering Adaptive Large Neighborhood Search Operators via Stackelberg Program Optimization
  268. Semantic Navigation for Issue Localization in Code Repository
  269. TaskIR: Task-Driven Image Restoration via Degradation Adaptation and Task Feedback
  270. Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting
  271. Audio emotion recognition for atypical hearing
  272. Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models
  273. BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio
  274. SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations
  275. ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation
  276. Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence
  277. Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection
  278. Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift
  279. HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models
  280. FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification
  281. Seeing Semantic Shift: Difference-Aware Sentence-Level Temporal Segmentation of Sign Language Videos
  282. Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge
  283. Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding
  284. AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
  285. Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue
  286. Frame the adversary: a structure-aware attack methodology
  287. From Shortcut Learning to Discrete Neural Insertion Sort
  288. Double-stream registration with pyramid fusion for HDR video with alternating exposures
  289. Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
  290. The Residual Stream's Effective Depth
  291. Block Sparse Attention with Log-Linear Complexity
  292. SAGE: A sampling-aware global evaluation benchmark for species distribution modeling
  293. OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas
  294. Band-Selection Stability and Semantic Segmentation Performance: A Study on Hyperspectral City
  295. Externalized CPDAG Summaries Improve LLM Causal Deduction
  296. Distributed Learning as a Service: The Developer's Perspective
  297. Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference
  298. KuaFu: Compressing Long User Behavior into Understanding at Billion Scale
  299. Exploiting Spatial Structure for Transductive Few-Shot Classification of Whole-Slide Images
  300. Aurora-X: Built for Extreme Time Series Forecasting
  301. Robust Graph Clustering Network for Multiple Missing Data
  302. Metacognitive Selective Ensemble for Mobile Systems
  303. Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance
  304. Refining Cytology Predictions with Conditional Random Fields
  305. Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search
  306. Group recovery after trimming, and level-free flagging, in robust clusterwise regression
  307. Same Text, Different Numbers: The Divergence of LLM-Based Measures
  308. G2PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation
  309. TRACKGRAPH: Online Open-Vocabulary 3D Scene Graphs via Image-Space Tracking
  310. Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
  311. Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Models
  312. PICO: Projection-Informed Consistency Optimisation for 6DoF Surgical Tool Pose Estimation
  313. Self-Supervised Perceptually Interpretable Monocular Depth Estimation
  314. Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries
  315. THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer
  316. FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators
  317. STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence
  318. A Comprehensive Study of Content Representations for Speech Synthesis
  319. Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change
  320. LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers
  321. Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings
  322. FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generation
  323. MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens
  324. Gradient Surgery for Physics-Informed Neural Networks
  325. Where and When to Force: Routed Forcing for Streaming Avatars
  326. IDM-Net: A Lightweight Illumination-Decoupled Modulation Network for Low-Light Image Enhancement
  327. Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
  328. Low-Bit Recurrent States in Hybrid Language Models
  329. DAPEVO: Deep Adaptive Patch Frame-Event Visual Odometry
  330. Spackle: Completing Large View Single Image NVS with Adaptive Gaussians
  331. Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
  332. ManiVid: Unified and Explainable Forensic Analysis of Manipulated Videos
  333. EPOC: Endpoint-Preserving Online Correction With Compressed Residual State for Multi-Horizon Time Series Forecasting
  334. Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring
  335. JevSoup: System-One Routing for Training-Free LoRA Composition
  336. Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations
  337. Cross-Backend QIEO: Universal Runtime Portability across OpenMP5, CUDA, HIP, and Multi-Language Interfaces
  338. Training Graph Foundation Models on The Web Graph
  339. Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC
  340. Conformal Prediction under Exponential-Tilt Joint Shift
  341. Retraction-Based Gradient Projection Algorithms on Manifolds
  342. Warned alike, AI agents avoid the less-crowded road while people take it
  343. Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos
  344. EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting
  345. Tight Stochastic Condition-Number Dependence in Nonconvex-Strongly-Concave Minimax Optimization
  346. Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
  347. Universal Drift Correction for Multidimensional Scanning Microscopy
  348. Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting
  349. Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development
  350. AC Power Flow Contingency Analysis Using a Single Deep Neural Network
  351. MDSkin-Net: Multi-Task Skin Lesion Analysis Driven by Pattern Analysis Priors and Spatial Alignment Regularization
  352. I-Parakeet: Integer-Only Conformer ASR on Mobile NPU
  353. Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translation
  354. Peer-Grounded Counterfactual Path Planning for Chronic Health Management
  355. PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices
  356. Subject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings
  357. Adaptive Interaction Graphs for Particle Simulation
  358. Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness
  359. Learning Provable Neural Network Observer for Uncertain Dynamical Systems
  360. A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory
  361. Counterfactual Online Conformal Prediction Under Adaptive Logging
  362. Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems
  363. XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security
  364. Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion
  365. Towards Universal Representation-Based Process Control
  366. Feature Selection for Tabular Foundation Models: Exploring Feature Utility in Low-Data Molecular Prediction
  367. Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models
  368. Missingness-Aware Conformal Prediction Under Cross-Hospital Distribution Shift
  369. Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance
  370. NavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation
  371. Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes
  372. Insurance Reserve Intelligence Platform
  373. HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models
  374. LLPR: Location-aware learning and physics-based reconstruction for raindrop removal from a single image
  375. Selective Amortization of Full-Budget Counterfactual Reasoning for Visual Token Communication
  376. Training-Free Bottleneck Width Planning for Convolutional Autoencoders
  377. Skill Profiling with Attributable Reasoning (SPAR): A Wearable Analysis System for Boxing
  378. Differentiable RNA Secondary Structure Extraction for Deep Learning
  379. Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging
  380. ORCA: Evaluating LLMs on Data Science Code Translation
  381. Beyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI
  382. Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
  383. Anatomy-Aware Dexterity-Driven Design Optimization of Surgical Continuum Robots
  384. From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia
  385. From Mono to Stereo: Accelerating Binocular Gaussian Splatting via Reprojection and Selective Patching
  386. SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages
  387. Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation
  388. TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise
  389. Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors
  390. Learning Polarization Image Restoration with General Restoration Priors
  391. TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
  392. When 10,000 Windows Are Not 10,000 Tests: Auditing Statistical Confidence in Sliding-Window Time-Series Classification
  393. Werracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts
  394. NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors
  395. Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4
  396. CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems
  397. Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence
  398. VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control
  399. Combining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation
  400. LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information
  401. SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion
  402. LUMO (Lightweight Unified Multilingual Orchestrator): A Privacy Preserving Offline Voice Assistant
  403. Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
  404. On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting
  405. PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints
  406. Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
  407. Design-Ignoring versus Design-Respecting World Models for Epidemiology
  408. TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
  409. Population loss in shallow ReLU networks: Bias & families of critical points
  410. Image Reconstruction from Phase with Untrained Neural Priors
  411. Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation
  412. Conditional Predictive Sufficient Statistics for Visual Representation Learning
  413. MARCEDES: Score-based causal discovery under non-Gaussianity with continuous optimization
  414. A Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code