mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 3 Sep 2026

492 papers

  1. Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  2. CoVeR: Coverage-Based Routing of Verifier Calls in Agentic RetrievalLLM agents and tool use → Web, search, and research agents
  3. BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge RetrievalLLM agents and tool use → Web, search, and research agents +1
  4. Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. Assessing Adversarial Robustness of Latent Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  6. Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode TimeLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  7. GzDRL: Reproducible and Scalable Deep Reinforcement Learning with GazeboDeep reinforcement learning methods → RL for robot locomotion and manipulation
  8. ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion UnderstandingLLM agents and tool use → Multimodal and embodied agents
  9. Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block TrainingDiffusion models → Image generation, text-to-image and editing
  10. LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved ManufacturabilityLLM agents and tool use → Multimodal and embodied agents
  11. EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor HypergraphLLM agents and tool use → Agent memory systems
  12. Extremely Sparse Supervision Incentivizes Reasoning AbilityLLM reasoning → Prompting and chain-of-thought reasoning
  13. La Agente 'Optima: Towards Agentic Self-Driving LaboratoriesEnd-to-end autonomous driving → Large language models for driving +1
  14. Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. VISTA: Dense Multi-Label Classroom Coding with Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  16. From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMsLLM reasoning → Test-time compute and efficient thinking
  17. Repeat-After-Me: Black-Box Adaptive Visual Prompt InjectionLLM safety and security → Prompt injection and agent security
  18. Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or OneDiffusion models → Discrete and text diffusion
  19. Discriminative Flow Matching: Beyond Time-Conditioning in Generative Restoration via Flow-State RepresentationsDiffusion models → Flow matching, time series and science
  20. MaxKernel: Agentic Kernel Generation for TPUsLLM agents and tool use → Software engineering coding agents
  21. What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding AgentsLLM agents and tool use → Software engineering coding agents +1
  22. LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  23. Rethinking Indirect Prompt Injection as a Test-Time Search ProblemLLM safety and security → Prompt injection and agent security
  24. Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention PerspectiveLLM reasoning → Test-time compute and efficient thinking
  25. Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety RefusalLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  26. PerfReasoning: How Well Do LLMs Reason on Hardware Performance?LLM reasoning → Reasoning for agents, planning and code
  27. Client-Side Probing of Deleted Ridge Statistics in Federated UnlearningLLM safety and security → Federated unlearning and poisoning
  28. Shared circuits predict whether LLMs generalize across formats in arithmetic reasoningLLM reasoning → Mathematical reasoning +1
  29. When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts ModelsMixture-of-experts → Expert routing strategies
  30. GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge ExpansionLLM agents and tool use → Web, search, and research agents
  31. What Attention Recalls and Recurrence Controls in Hybrid Language ModelsEfficient LLM inference and serving → KV cache optimization
  32. Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial MarketsLLM agents and tool use → Financial trading and forecasting agents
  33. Scalable Edge-assisted Fusion and Path Prediction for Connected Autonomous VehiclesWorld models → World models for autonomous driving +1
  34. VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  35. SharedSAE: One Feature Dictionary Across Language ModelsMechanistic interpretability → SAE features and their applications
  36. MedProb: Probing Internal Representations of Vision-Language Models for Medical Question AnsweringMultimodal LLMs / vision-language models → Medical vision-language models +1
  37. Abstraction AgentLLM agents and tool use → Reinforcement learning for LLM agents
  38. Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Evidence Integration in Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  40. From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and GovernanceLLM agents and tool use → Social simulation and multi-agent debate
  41. Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution MatchingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  42. Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual GenerationDiffusion models → Diffusion and flow policies for robotics +1
  43. When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  44. EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?LLM agents and tool use → Software engineering coding agents
  45. FailureSpot: Label-Efficient Timestamp-Level Failure Detection for Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  46. Temporal Self-Distillation: Learning Visual State Tracking in Videos Without SupervisionKnowledge distillation → Detection and dense prediction distillation
  47. Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  48. GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic ManipulationWorld models → Embodied and robot world models +1
  49. Rethinking On-Policy Distillation of Large Language Models II: One Training ExampleKnowledge distillation → On-policy and self-distillation for LLMs
  50. SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  51. SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations CenterLLM reasoning → Reasoning for agents, planning and code +1
  52. A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann VehicleEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  53. Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  54. Environment Evolution for Terminal AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  55. Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVRLLM reasoning → Reinforcement learning for reasoning +1
  56. Conditioning Degenerate Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  57. CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker DistillationLLM reasoning → Multimodal reasoning
  58. TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  59. Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  60. Subspace Inference Enables Efficient Active Reward Learning from PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  61. Spurious Advantage Hidden in GRPOLLM reasoning → Reinforcement learning for reasoning
  62. DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video GenerationDiffusion models → Diffusion foundations and sampling
  63. Representational alignment yields generalizable safety in language modelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  64. A Black Box for Agentic Processes: Blockchain-Anchored Evidence for AI Agent Communication, Human Oversight, and GRC AuditsLLM agents and tool use → Agent threats, guardrails and governance
  65. InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  66. Unlocking Lossless Speedups in LLMs via Discrete DiffusionDiffusion models → Discrete and text diffusion
  67. The Dually Flat Geometry of Planning as InferenceDeep reinforcement learning methods → Deep RL algorithms and representations
  68. Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue SynthesisDiffusion models → Audio, speech and music
  69. IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish RecognitionMultimodal LLMs / vision-language models → Agricultural vision-language models
  70. MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex TerrainsDiffusion models → Diffusion and flow policies for robotics
  71. FiMI Banking: A Sovereign Model for Indian Retail BankingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  72. RARF: Region-Aware Rectified Flows for 3D Brain MRI InpaintingDiffusion models → Medical imaging and segmentation
  73. WorldReward: Reward Modeling for Camera-Conditioned World ModelsWorld models → Embodied and robot world models +1
  74. VestigeKV: The NoPE-MLA KV Cache Carries Its Own Sparse-Attention Signal in a Vestigial BranchEfficient LLM inference and serving → KV cache optimization
  75. Computationally Efficient Pathology Segmentation using Knowledge Distillation from Foundation ModelsKnowledge distillation → Distillation for medical imaging
  76. Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPOLLM reasoning → Reinforcement learning for reasoning +1
  77. RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series ForecastingRetrieval-augmented generation → Time series and agricultural RAG
  78. Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World ModelsWorld models → Embodied and robot world models +1
  79. Speak for Me: Giving LLMs the Situational Awareness to Participate in a MeetingLLM agents and tool use → General LLM agent frameworks and benchmarks
  80. Value-Preserving Architectures for Agentic AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  81. OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D MappingDiffusion models → 3D, point cloud and scene generation
  82. From Misconceptions to Evidence: What Science Teachers Make Visible When Co-Designing Agentic Learning AppsLLM agents and tool use → Educational agents and math problem solving
  83. Revisiting Topological Graphs for Macro Action based Closed-loop Reinforcement Learning of Vision Language Navigation in Continuous EnvironmentDeep reinforcement learning methods → RL for robot locomotion and manipulation
  84. GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene GraphsLLM reasoning → Spatial and embodied reasoning +1
  85. A hybrid pipeline for dynamic ontology-based semantic mappingWorld models → World models for navigation
  86. Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering RobustnessLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  87. A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious BehaviorsLLM agents and tool use → Agent threats, guardrails and governance
  88. STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentationRetrieval-augmented generation → RAG pipeline design and evaluation
  89. Bioinfoysis Technical ReportLLM agents and tool use → Medical and scientific domain agents
  90. Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain OperationsLLM agents and tool use → Social simulation and multi-agent debate
  91. GRASP: Graph-Retrieval Automated Scoring Pipeline for Label-Free Multi-Topic Essay GradingRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  92. Flip, Don't Shuffle: Watermarking LLMs at the Speed of InferenceLLM safety and security → Watermarking generated content and models
  93. Multi-step Proximal Policy Improvement in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
  94. Semantic Bayesian World ModelsWorld models → World models for language agents
  95. When Vision Meets Graphs: A Survey on Graph Reasoning and LearningLLM reasoning → Multimodal reasoning
  96. Inferring Hidden User Models from the Behavior of Personalized LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  97. SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-ResolutionDiffusion models → Inverse problems and image restoration
  98. SVG-Score: Human-Aligned Evaluation of Text-to-SVG GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  99. LLaDA-Image: Building Strong Image Generators with Fully Open Training RecipesDiffusion models → Image generation, text-to-image and editing
  100. DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic DecisionsLLM agents and tool use → Agent threats, guardrails and governance
All 492
  1. IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak AttacksLLM safety and security → Safety alignment, refusal and guardrails
  2. Rethinking World Models for Safety-Critical Embodied SystemsWorld models → World models for navigation
  3. SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic SimulationLLM agents and tool use → Multimodal and embodied agents +1
  4. Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAGRetrieval-augmented generation → Privacy and security of RAG
  5. Unfold The World: Factorize 4D Properties in Reinforcing Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  6. Proactive Service Agents: A Unified Decision Framework, Methods, and EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. What Do CAE Simulation Agents Really Need Beyond a Generic Harness?LLM agents and tool use → Software engineering coding agents
  8. MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO?Vision-language-action models → Failure recovery and robustness
  9. AlcaTRAz - Anchored Tree-Rule Defense Against JailbreaksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  10. ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  11. A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural EntitiesMechanistic interpretability → Knowledge and representations inside LLMs
  12. WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action ModelsWorld models → Embodied and robot world models +2
  13. CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  14. Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Offline multi-agent RL
  15. Extracting Forgotten Prompts from Targeted Unlearned ModelsLLM safety and security → Machine unlearning
  16. Stabilizing Camera-Controlled Novel View Synthesis at Inference TimeDiffusion models → 3D, point cloud and scene generation
  17. </think> Doesn't Stop Reasoning: Analysis of Spurious CoT TerminationLLM reasoning → Prompting and chain-of-thought reasoning +1
  18. EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse AutoencodersDiffusion models → Robustness, privacy and adversarial aspects +1
  19. Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence EstimationLLM reasoning → Reasoning for agents, planning and code +1
  20. FailBench: How Reliable are VLMs at Judging Robot Task Success?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  21. SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +1
  22. Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy CorrectionsVision-language-action models → Human-video and latent-action pretraining
  23. From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network ControlOffline RL and imitation learning from data → Offline multi-agent RL +1
  24. KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  25. The Attention Triangle in Audio-Video ModelsDiffusion models → Audio, speech and music
  26. Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous DrivingWorld models → World models for autonomous driving +1
  27. Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic PlanningWorld models → Latent predictive world models
  28. Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video GenerationWorld models → Video-generation world models and simulators
  29. Dalek: A Constructive Agent MachineLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  31. LeanGRPO: Eliminating Redundant Recomputation in Diffusion RLDeep reinforcement learning methods → RL with diffusion and flow models
  32. NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
  33. CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary ReasoningLLM reasoning → Multimodal reasoning +1
  34. What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking PreservationEfficient LLM inference and serving → KV cache optimization
  35. Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving PerturbationsLLM reasoning → Reasoning benchmarks and evaluation +1
  36. Towards a Statistical Understanding of Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  37. GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning ServingLLM reasoning → Test-time compute and efficient thinking +1
  38. Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  39. When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational AgentsLLM agents and tool use → Agent memory systems
  40. When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QARetrieval-augmented generation → Medical and biomedical RAG
  41. Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent MemoryLLM agents and tool use → Agent memory systems
  42. Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree CouplingDiffusion models → Flow matching, time series and science
  43. Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI AgentsLLM agents and tool use → GUI and mobile agents
  44. It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning TrajectoriesLLM reasoning → Test-time compute and efficient thinking
  45. Random Attention: Rethinking KV Cache Eviction for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  46. DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  47. Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy DetectionLLM agents and tool use → Web, search, and research agents
  48. TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  49. SurgeGen: A Hybrid Generative Diffusion Framework for Storm Surge Scenario SynthesisDiffusion models → Flow matching, time series and science
  50. RecurTrace: Adaptive Latent Reasoning with Loop-Time MemoryLLM reasoning → Test-time compute and efficient thinking
  51. Spruce: Scalable Private Outsourced Retrieval Using Compact EmbeddingsRetrieval-augmented generation → Privacy and security of RAG
  52. ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  53. Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned RewardsLLM reasoning → Reinforcement learning for reasoning +1
  54. Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent MemoryLLM agents and tool use → Agent memory systems
  55. SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and SynthesisLLM agents and tool use → Web, search, and research agents
  56. FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  57. DE-Venus: A Data-Efficient RLVR Framework for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  58. Iapetus: Content-Aware Hierarchical Scheduling for Collaborative ViT Inference in LEO Satellite NetworksEfficient LLM inference and serving → Serving systems and request scheduling
  59. SelfDR: Self-Distillation from Reasoning for LLM-Based RecommendationLLM reasoning → LLM reasoning for recommendation
  60. TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code GenerationLLM reasoning → Reasoning for agents, planning and code
  61. Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty QuantificationDeep reinforcement learning methods → RL for energy, networks and operations
  62. Latent Energy Action Planning with World ModelsWorld models → Latent predictive world models
  63. R2S-Eval: Robot Evaluation with Real-to-Sim Calibration via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  64. MedQA-MM: Shortcuts Behind Medical Visual ReasoningLLM reasoning → Clinical and biomedical applications
  65. What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through ConversationLLM reasoning → Test-time compute and efficient thinking
  66. Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language ModelsLLM safety and security → Jailbreaking
  67. FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning ExperienceLLM reasoning → Prompting and chain-of-thought reasoning
  68. Speculative Macro Commit for Faster Tool-Using AgentsLLM agents and tool use → Software engineering coding agents
  69. SGD-KV: Summarization Guided KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  70. Language-encoded network topology enables large language models to reason about complex networksLLM reasoning → Knowledge- and tool-augmented reasoning
  71. Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End DrivingWorld models → World models for autonomous driving +2
  72. SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials
  73. Fast Polynomial Transcendentals for LLMs
  74. Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs
  75. SCM-based Fairness and Faithful Explainability for Legal Document Classification
  76. The Delegation Danger Band: Why Mid-Capability Sub-Agents Over-Trust Inherited Stale State
  77. DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians
  78. Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks
  79. SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery)
  80. CNA: An AI-Oriented Comprehensive Normalized Assessment for Healthy Status and Application to Optimize RRT Strategies by Reinforcement Learning
  81. EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems
  82. List Counting Failures Are Not One Phenomenon
  83. A Synthetic Multivariate Refrigerator Time-Series Dataset for Predictive Maintenance
  84. Guiding the coarse levels of semantic IDs makes the fine levels learnable
  85. Cascaded Non-Line-of-Sight Imaging
  86. Calibrating subgrid parametrizations of single-column ocean models via simulation-based inference
  87. Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane
  88. Rollcast: Proper-Score Gated Rolling Anchors for Adaptive Probabilistic Time-Series Forecasting
  89. An Agent Model Abstraction for Human-AI Teaming Cognitive Coupling
  90. Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
  91. Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
  92. Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection
  93. IPGeoAI: Transformer-Based Geolocation with LLM Semantic Fusion
  94. A Sim-to-Real Study of Surface-Code Decoder Benchmarking
  95. DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models
  96. Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI
  97. Fast Surrogate Modeling of Excitable and Oscillatory FitzHugh-Nagumo Dynamics with Parametric Neural Operators
  98. SocioGesture: Real-Time and Adaptive Social Gesture Perception for Human-Robot Interaction
  99. Data-Driven Discovery of Composition-Dependent Constitutive Models for Hyperelasticity and Viscoelasticity of Digital Materials
  100. Mitra-v2 Technical Report
  101. A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs
  102. An Energy-Based Conservative-Dissipative Latent Neural Evolution Operator for Magnetization Dynamics
  103. Towards a universal language of concepts: A survey
  104. Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs
  105. Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes
  106. Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters
  107. Explainable Multimodal Deep Learning Integrating Imaging and Clinical Data for Oral Potentially Malignant Disorder Detection
  108. A Semantic Model of Genetic Evidence: A Step Toward Bridging the Basic-Science-Clinic Gap
  109. BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker
  110. Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification
  111. EyeMakeYou: Identity-, Task-, and Subjective-State-Conditioned Diffusion for High-Frequency Gaze Synthesis
  112. STyMo: Fast and Controllable Few-Shot Motion Style Transfer
  113. Hakken: Predicting future discoveries to fill the gaps in today's knowledge
  114. ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality
  115. When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
  116. Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization
  117. Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning
  118. Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation
  119. Nested Inductive Bias Framework for SPD Manifold Learning
  120. A Roadmap for MEG Foundation Models
  121. On-board ML for Trace Gas detection in Imaging Spectroscopy data
  122. Topology-Aware Training and Spatial Diagnostics for Fiber Bundle Segmentation in Tracer Histology
  123. TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio
  124. Conformity Breaks Conformal Prediction
  125. HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals
  126. Segmentation of the aorta in 4D flow MRI using 4D convolutional kernels and learning from sparse annotations
  127. ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory
  128. STEMPix: A Phase-Transition-Material-Based Pixel Sensor for Resolving Edge-Movement Direction
  129. Recovering molecules from coarse-grained beads: free-energy-conditioned generative backmapping across chemical space
  130. A Repeated-Measurement Study for Cultural Analytics of English Song Lyrics Using Five Large Language Models
  131. Beyond a Universal Forecasting Selector: Demand-Conditioned Model Selection across Demand Patterns and Horizons
  132. Optimal Stratified Allocation for Rare-Event Onset Forecasting in Dependent Sequences
  133. Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters
  134. REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation
  135. AquaBEV: Monocular Underwater BEV Occupancy with 3D Sonar Supervision
  136. A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models
  137. Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures
  138. The Anatomy of an ASR Hallucination
  139. FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding
  140. Evaluation of Phonetic Encoding Algorithms on Transcription Datasets
  141. Development and Evaluation of Ultrasound Image Learning Pipelines for MASLD Risk Stratification
  142. Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection
  143. You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments
  144. What Moves? Localized Motion Representations for Compositional Scene Control
  145. Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys
  146. What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features
  147. On the Abundance of Critical Points of the t-SNE Energy
  148. Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer
  149. AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition
  150. VERGE: Verification-Enhanced Refinement for Grounded Extraction of Early-Onset Colorectal Cancer Symptoms in Clinical Notes
  151. Ultrasound-Based Prediction of Cirrhosis Decompensation Using Large-Scale Computer Vision Models
  152. Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models
  153. Cross-modal triage network: a multimodal deep learning framework for severity-based triage and visual explainability in chest radiographs
  154. Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems
  155. A Quantum Variational Approach to Prototypical Recurrent Unit
  156. Adapting from Downturns: Prediction of Long-Term Conversational-Skill Development in Mental-Health Crisis Counselors
  157. Object Concepts Emerge from Motion
  158. A Constraint-Aware Generative Framework for Synthetic Origin-Destination Demand in Logistics Networks
  159. A Removal Based Approach to Improve LLM Faithfulness at Test-Time
  160. Modular Deep Recurrent Neural Network: Application to Quadrotors
  161. Data-Driven Learning of Unknown Nonlinear Differential Equations Using Functional Analysis
  162. The microscope is the mask: privileged views and labels from a cryo-ET forward model
  163. TNFlow: Amortized Posterior Inference for Trans-Neptunian Object Surface Composition
  164. Iris: Climbing to the Search Frontier
  165. Data-Optimized Contingency Screening: A Machine Learning Approach to Power System Security
  166. BER-PEF: Unified Human Mobility Predictability Evaluation via Bayes Error Rate Estimation
  167. Memory as transformation: LETHE, a self-referential gan-inspired architecture
  168. Scalable Context Orchestration for Serving LLMs Over Voice
  169. Towards AI-Driven Nanomedicine Discovery: A Benchmark and Multimodal Learning Framework for Nano Self-Assembly Prediction
  170. TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation
  171. Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
  172. Principia: Relational Physics Tests for Video Models
  173. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
  174. Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints
  175. ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize
  176. Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
  177. One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
  178. Robust PAC Learning of Concurrent Stochastic Games
  179. Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
  180. Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
  181. A Computationally Feasible Framework for Causal Probabilistic Explanation
  182. Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations
  183. Last Translation Benchmark
  184. A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
  185. Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs
  186. From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
  187. Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomography
  188. Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System
  189. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
  190. Efficient Test-Time Adaptation through Human-AI Interaction
  191. The Natural Language Interaction Protocol and Standard for AI Agents
  192. Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
  193. Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable
  194. BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data
  195. Constant regret in general games via higher-order optimism
  196. The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
  197. Hardware-Aware FP4 FlashAttention-4
  198. Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
  199. Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
  200. DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
  201. Efficient Semantic Understanding from Digital Foveation
  202. A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI
  203. PatchBench: Evaluating AI Agents for Vulnerability Patching
  204. When Models Edit Too Much: On the Fidelity of Minimal Code Edits
  205. Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation
  206. The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations
  207. The Head Complexity of Boolean Functions in Single-Layer Attention
  208. Editable Visual Design
  209. IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations
  210. Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach
  211. Stable and Scalable Bundle Adjustment of Holistic 3D Structures
  212. Instruction Duplication as an Inference-Time Control Primitive
  213. FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models
  214. A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions
  215. LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening
  216. Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data
  217. The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations
  218. RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models
  219. Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition
  220. Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing
  221. Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks
  222. Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
  223. OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models
  224. Investigating the Ability of Large Language Models to Analyze Recipes for Diabetes
  225. Interface-Induced Trajectory Censoring
  226. Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
  227. Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection
  228. More Criticism Does Not Make a Better Review: EquiReview-R
  229. Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations
  230. Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding
  231. Sparse auto-regressive modeling for scene generation from multi-view images
  232. Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords
  233. RuleMem: Active Rule Memory for Long-Term Conversational Agents
  234. Lose the Order, Keep the Hierarchy: Deordering HTN Plans
  235. Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities
  236. Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating
  237. Concept of a Sensor Test Environment for Dusty Agricultural Conditions
  238. CROCODIL: Cross-Model Code Editing with LLMs
  239. FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation
  240. Inferring Affective Consciousness in an Artificial Agent: A Case Study
  241. Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
  242. Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data
  243. GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
  244. High-Dimensional Learning Dynamics of Attention-Indexed Models
  245. Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning
  246. EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments
  247. Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification
  248. Witnesses Explain Anomalies
  249. VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues
  250. Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs
  251. CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
  252. Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation
  253. VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence
  254. A Peer-Relative Representation Learning Framework for Energy Inefficiency Identification in Mobile Network Sites
  255. Almost Free State Prediction Separation
  256. Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications
  257. DCCQ: From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra
  258. Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AI
  259. Transfiver: Human-AI Co-Inference through a Shared Editable State
  260. When Minute-Resolution Monitoring Meets Session-Level Injury Labels: Landmark-Based Discrimination in Elite Women's Football
  261. A Reverse Sign Language Dictionary: Open-Vocabulary Sign Recognition from Continuous Signing via Video Captioning and Description Retrieval
  262. Typological Feature Prediction with Large Language Models: An In-Context Learning Approach
  263. RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents
  264. OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education
  265. From Nowcasting to Forecasting: Adapting a Reanalysis-Trained
  266. Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size
  267. ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
  268. KnowVis: Knowledge-Centric Visual Summarization for Video Lectures
  269. Fill My Mirror: Geometry-Constrained Mirror Inpainting
  270. Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks
  271. Genetic Algorithms for Tractable Bayesian Network Fusion via Pre-Fusion Edge Pruning
  272. Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study
  273. Opening mind by opening architecture: analysis strategies
  274. Artificial Intelligence for Energy Optimization in Data Centers
  275. Counterfactual Routing Using Integer Programming with Constraint Generation
  276. Q-Edge: Symmetry-Reduced Quantum Simulation of Structured Extreme Dependence
  277. Federated Causal Discovery via Regression-Directed Cumulants
  278. Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study
  279. Symmetries and Causality: Causal Effect Identification Beyond IID Data
  280. SignSeek: Learning Transferable Representations for Sign Dictionary Retrieval
  281. Observation-Conditioned Latent Energy Priors for Sparse Implicit Neural Shape Completion
  282. MetaStructAtlas: A Grounded 3D Vision-Language Dataset and Benchmark for Functional and Structural Reasoning in Whole-Body PET/CT
  283. Semantic-Aware Subgraph State Space Model for WSI Classification in Histopathology
  284. Resolution-Aware Experimental Design under Partial Identifiability
  285. DropClick: Semi-Automated One-Click Segmentation for Agricultural Robotic Data
  286. Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language
  287. Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation
  288. ARCOS: Zero-shot Boundary Localization for Corneal Layer Segmentation Across Optical Coherence Tomography Devices
  289. Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography
  290. Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
  291. Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations
  292. PL-SCEA: Reconfiguring Pretrained Attention for Few-Shot Industrial Anomaly Detection
  293. Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements
  294. The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function Classification
  295. Relative Prime Factorization and Finite-State Presentations under Fixed Finite-Monoid Observation
  296. Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers
  297. Analysis of Prompt Engineering for Drug Toxicity Prediction
  298. Residual neural networks overcome the curse of dimensionality for semilinear heat equations
  299. Test-time adaptation for speech enhancement with an autoregressive speech prior
  300. A computable representation of the physical laboratory enables verifiable workflows
  301. ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
  302. Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++
  303. On the Interaction Between Model Compression and Test-Time Adaptation
  304. Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling
  305. KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records
  306. How Far Can Synthetic Data Take Thai OCR?
  307. LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks
  308. Correlated initialization of deep residual networks
  309. Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors
  310. WeatherNext 3: Increasing resolution and performance of global weather models with raw observations
  311. HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews
  312. Language, Language Models, and What We're Talking About
  313. Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMG
  314. FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
  315. WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval
  316. GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
  317. Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
  318. TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates
  319. Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws
  320. EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation
  321. Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion
  322. Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection
  323. LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues
  324. An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data
  325. Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails
  326. PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing
  327. Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
  328. BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI
  329. Spectral characteristics of autoencoder parameters as a vector representation of data
  330. Pattern Over-Generalization of Knowledge Graph Embedding
  331. Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps
  332. Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings
  333. AutoGraphForge: Towards Automated Graph Theory Discovery
  334. SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration
  335. Mind the Gap: Robustness Risks in PII Detection Systems
  336. BMCTrack-d: Pig re-identification and tracking via back marks in challenging camera settings
  337. Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency Penalty
  338. A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds
  339. The Psychological Costs of Artificial Intelligence Adoption in Software Engineering
  340. Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems
  341. STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface Reconstruction
  342. Preserving Knowledge across Space and Time for Continual Video Deepfake Detection
  343. OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement
  344. Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery
  345. Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks
  346. When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals
  347. TraveL: Transformer-based Multi-view Path Distributional Representation Learning
  348. Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations
  349. The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems
  350. Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models
  351. Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
  352. Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage
  353. StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios
  354. To What Extent Do Large Language Models Understand Bangla Idioms?
  355. Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation
  356. Neural-Collapse-guided Task-Free Continual Anomaly Detection
  357. A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant
  358. Spectral Convergence of Random Feature Method in Multiple Dimensions
  359. TabScope: Question-Adaptive Scope Selection for Table Question Answering
  360. Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory
  361. Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data
  362. Computing stable configurations of confined smectic liquid crystals with a deep variational framework
  363. FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation
  364. When Depth Hurts: Reliability-Aware Geometry Distillation for Depth-Free RGB-D Salient Object Detection
  365. SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
  366. FrameBench:A Language Understanding Benchmark Based on Frame Semantics
  367. Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT
  368. Grassmann--Pl"ucker Parametrization of Convolutional Filter Subspaces: Regularity and Closed Embeddings
  369. Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-Consistency
  370. Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming
  371. From Zero to Hero: An Open LLM Ecosystem for Armenian
  372. P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
  373. Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem
  374. PointGT: Simultaneous Geometry and Texture Editing for Point-Based Representations
  375. A Large Open Multi-Energy Corpus of Soil Compaction Tests, with Machine-Learning Baselines
  376. Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training
  377. Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour
  378. Introducing SINFONIA: Symplectic, slimplectic and Magnusian (Neural) Flows for Orbital Numerical Integration and Acceleration
  379. How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models
  380. Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue
  381. Beyond .WAV: Design and Software Verification of VocalCap, a Traceable Browser-Based Audio Capture System for Vocal Biomarker Research
  382. Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control
  383. Tensor-based Brain Surface Modeling and Analysis
  384. Multilingual Agent System for Inclusive Wildfire Evacuation Guidance
  385. PACE: Towards Surfacing Hidden Conflicts in User Requests
  386. Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence Transformers
  387. Selective Hypergraph Refinement for Frozen Graph Clustering
  388. An Ensemble-Based Self-Taught Learning Approach for Parking Space Classification Under Limited Data
  389. What is Smoothness?
  390. B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven Methodology
  391. Counting Animals in Camera-Traps Image Sequences without Count Labels: Winning Solution to the iWildCam 2021 Challenge
  392. The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100