mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 6 Aug 2026

428 papers

  1. Why Do LLMs Fail at OCL Generation? A Graph Reasoning PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
  2. DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI AgentsLLM agents and tool use → Agent memory systems
  3. Research Assistant: AstraZeneca's Agentic System for R&DLLM agents and tool use → Medical and scientific domain agents
  4. OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management AgentsLLM agents and tool use → Financial trading and forecasting agents
  5. LIRA: Local Cross-Layer Information Routing for Vision-Language-Action DecodingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  6. Scaling Inherently Interpretable Language ModelsDiffusion models → Discrete and text diffusion
  7. CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive CybersecurityLLM agents and tool use → Agent threats, guardrails and governance
  8. MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and SteeringMechanistic interpretability → Activation steering methods
  9. Shape Your Feed: An LLM-based Agentic System for Conversational RecommendationLLM agents and tool use → Agentic recommender systems
  10. Retrofitting Linear Attention into Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  11. Flowing Through States: Neural ODE Regularization for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  12. CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure PredictionDeep reinforcement learning methods → RL for energy, networks and operations
  13. Bootstrap-Conditioned Action Selection with Tabular Foundation ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  14. Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference servingLLM agents and tool use → Software engineering coding agents +1
  15. TaskSense: Focusing on What Matters in World ModelsWorld models → Latent predictive world models
  16. Confidence Estimation for Financial Vision-Language Models in Chart and Document UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  17. Lost in Interpolation: Why Predictive Feedback Fails in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  18. GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  19. Agentic AI: User Empowerment or Foreclosure?LLM agents and tool use → Social simulation and multi-agent debate
  20. Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution InstabilityEfficient LLM inference and serving → Efficient reasoning and agent inference
  21. Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life EventsLLM agents and tool use → Social simulation and multi-agent debate
  22. StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  23. WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic GraderSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  24. CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent TrainingLLM agents and tool use → Agent threats, guardrails and governance
  25. Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction StudyEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
  26. Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model SelectionVision-language-action models → Efficient VLA inference and adaptation
  27. Learning When to Trust via Selective Context Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  28. ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-ManipulationWorld models → Humanoid and legged locomotion world models
  29. DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment ManipulationVision-language-action models → Human-video and latent-action pretraining
  30. The Bitter Lesson of Tool CallingLLM agents and tool use → Tool learning and function calling
  31. AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information GamesLLM agents and tool use → Reinforcement learning for LLM agents
  32. RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning TransferLLM reasoning → Prompting and chain-of-thought reasoning +1
  33. TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent TrajectoriesLLM agents and tool use → Software engineering coding agents
  34. GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual ActionsWorld models → Embodied and robot world models +1
  35. Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward ConstructionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  37. Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic OperationsRetrieval-augmented generation → Multimodal RAG +1
  38. HarnessOpt-Bench: Evaluating LLMs at Harness OptimizationLLM agents and tool use → Software engineering coding agents
  39. Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation VectorsMechanistic interpretability → SAE features and their applications
  40. On-Policy Self-Distillation without Any SupervisionLLM reasoning → Prompting and chain-of-thought reasoning +1
  41. NeSy-RAG: Neuro-Symbolic RAG for Explainable Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  42. Stochastic Dynamics on Persistence Diagram Space via Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  43. The Illusion of Visual Tool-Use: A Causal Audit of Thinking with ImagesLLM reasoning → Multimodal reasoning +1
  44. MASS: Multiplayer World Models with Authoritative Shared StateWorld models → Video-generation world models and simulators
  45. A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI GovernanceLLM safety and security → Machine unlearning
  46. DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  47. PRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image TranslationDiffusion models → Flow matching, time series and science
  48. EmoWorld: A Decoupled Affective Field for Controllable Emotional Video GenerationDiffusion models → Audio, speech and music
  49. TS-RAG: Retrieval Augmented Generation for Time Series ForecastingRetrieval-augmented generation → Time series and agricultural RAG
  50. Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness EvaluationOffline RL and imitation learning from data → Robot learning from demonstration
  51. Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning EraLLM safety and security → Watermarking generated content and models
  52. VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse DemonstrationsDiffusion models → Diffusion and flow policies for robotics
  53. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement LearningWorld models → World models for language agents +1
  54. Comparative Approaches to Agent Retrieval over Large Skill LibrariesLLM agents and tool use → Web, search, and research agents
  55. SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  56. Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web AgentsLLM agents and tool use → Web, search, and research agents
  57. Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured EnvironmentsLLM reasoning → Spatial and embodied reasoning
  58. iARCS: Iterative Agentic RL for Controllable 3D Scene GenerationLLM agents and tool use → Multimodal and embodied agents
  59. Visual Grounding in Zero-Shot Vision-Language ControlMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  60. Learning Globally Reusable Skills for Coding AgentsLLM agents and tool use → Agent skill learning and evolution
  61. PaDoc: Layout-Grounded Parallel Decoding for Document ParsingEfficient LLM inference and serving → Visual token pruning in multimodal models
  62. Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement ArchitectureLLM agents and tool use → Agent threats, guardrails and governance
  63. Contextual Information Policy Optimization for Search AgentsLLM agents and tool use → Web, search, and research agents
  64. Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-TrainingDiffusion models → Diffusion and flow policies for robotics +1
  65. DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across ScaffoldsLLM agents and tool use → Software engineering coding agents
  66. ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech AssessmentLLM agents and tool use → Medical and scientific domain agents
  67. Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial AgentsLLM agents and tool use → Financial trading and forecasting agents
  68. Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic ShippingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +2
  69. Domain-Grounded Candidate Selection for Agentic Image Editing: A Shadow Removal CaseMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  70. The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents
  71. When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn HistoriesLLM agents and tool use → Tool learning and function calling
  72. ASGE-RR: Agentic Service Graph Embedding with Revisable Reservations for Dynamic AI-Agent CallsLLM agents and tool use → Software engineering coding agents
  73. Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning InferenceDeep reinforcement learning methods → Deep RL algorithms and representations
  74. BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion RecognitionKnowledge distillation → Multimodal distillation
  75. From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World ModelsWorld models → World models for language agents +1
  76. Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and ComputeLLM reasoning → Spatial and embodied reasoning
  77. OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and InteractionLLM reasoning → Audio-language model reasoning +1
  78. Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion FeaturesWorld models → World models for autonomous driving +1
  79. TensorCast: The Missing Tensor Management Layer in Large Language Model InfrastructureEfficient LLM inference and serving → Serving systems and request scheduling
  80. Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +3
  81. OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agentsLLM agents and tool use → Multimodal and embodied agents
  82. Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous ControlDeep reinforcement learning methods → Deep RL algorithms and representations
  83. AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  84. Diff-VF: Training-free High-quality Long Video Generation via Diffusion ModelDiffusion models → Video generation
  85. SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA +2
  86. M3Prune: Hierarchical Collaborative Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  87. AgentExecutor: Partial Code Execution via Agentic Context GenerationLLM agents and tool use → Software engineering coding agents
  88. Certifying Collective Reasoning in Multi-Agent Systems via Koopman Spectral AnalysisLLM reasoning → Reasoning for agents, planning and code +1
  89. Training a Conditioned Video Game Agent on a VLM Annotated DatasetLLM agents and tool use → Reinforcement learning for LLM agents
  90. Stabilizer Design for Policy Iteration in Stochastic Linear Quadratic Control: A Spectrum-Assignment ApproachDeep reinforcement learning methods → RL for games and combinatorial optimization
  91. VLMs for Videogame Data AnnotationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  92. GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World ModelsWorld models → Latent predictive world models
  93. Respect Your Zero-Shot Uncertainty: Conservative Calibration for Test-Time-Adapted Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  94. BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network EdgeEfficient LLM inference and serving → Speculative decoding
  95. Causal Episodic Memory for Feedback-Driven Agent RepairLLM agents and tool use → Agent memory systems
  96. Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action ModelsWorld models → Embodied and robot world models
  97. AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI AgentsWorld models → World model security and GUI agents +1
  98. CodeGrep: An RL-Trained Retrieval Agent for LLM Coding AgentsLLM agents and tool use → Software engineering coding agents
  99. The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
  100. MAVISEG: Manifold Propagation and Visual Prototypes for Zero-Shot Open-Vocabulary Segmentation in Diffusion TransformersDiffusion models → Medical imaging and segmentation
All 428
  1. Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence GroundingLLM agents and tool use → Web, search, and research agents
  2. Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. Runtime Observability for Heterogeneous Attention MemoryEfficient LLM inference and serving → KV cache optimization
  4. Mapping Similarity Spaces across Embedding Models with Synthetic Query ProbingRetrieval-augmented generation → Generation and context integration
  5. ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph CompletionLLM reasoning → Multimodal reasoning +1
  6. Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal RewardingLLM reasoning → Reasoning for agents, planning and code
  7. Agent-Based Test Assertion Generation via Diverse Perspective AggregationLLM agents and tool use → Software engineering coding agents
  8. Energy-Guided Flow MatchingDiffusion models → Flow matching, time series and science
  9. When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  10. Vorch-Omni: Multi-Task Orchestration of Sight and SoundDiffusion models → Audio, speech and music
  11. On-Policy Delta Distillation for Multilingual Math ReasoningLLM reasoning → Prompting and chain-of-thought reasoning +1
  12. XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?World models → Embodied and robot world models
  13. KVAE: Family of Tokenizers for Multimodal Generative ModelsDiffusion models → Diffusion foundations and sampling
  14. When Agentic AI Meets Integrated Sensing and CommunicationLLM agents and tool use → Agentic AI for wireless networks
  15. A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. ChainClaw: A Layered Agent Framework for Reliable On-Chain ExecutionLLM agents and tool use → Agent threats, guardrails and governance
  17. Task-Conditional Flow Matching for Balanced Multilingual Text Embedding AdaptationDiffusion models → Discrete and text diffusion
  18. Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and ReplayLLM agents and tool use → Agent memory systems
  19. GROM: Gradient-Free Rapid One-Shot Machine UnlearningLLM safety and security → Machine unlearning
  20. Vorch-Director: Interactive World Story Model via Noise-Aware Error RectificationDiffusion models → Video generation
  21. Flow-Map Distillation on Relation Manifolds for Image RestorationKnowledge distillation → General knowledge distillation methods
  22. Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image ReasoningLLM agents and tool use → Medical and scientific domain agents
  23. In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool UseVision-language-action models → Reasoning and chain-of-thought in VLA +1
  24. Subliminal Learning is Non-Semantic DistillationMechanistic interpretability → Activation steering methods
  25. CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder CircuitsMechanistic interpretability → Activation steering methods
  26. SpaceVLA: Spatially Grounded VLA for Robotic Manipulation with User-Authored Grasp and Place AnchorsVision-language-action models → 3D and spatial-aware VLA
  27. Unified Agent: Managing Interactions across DevicesLLM agents and tool use → GUI and mobile agents
  28. PhyLatent: Learning Dynamics-Relevant Representations for JEPA World ModelsWorld models → Latent predictive world models
  29. Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled RobotsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  30. One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  31. LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World ModelsWorld models → Embodied and robot world models
  32. StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video UnderstandingLLM agents and tool use → Multimodal and embodied agents
  33. DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World ModelWorld models → World model security and GUI agents +2
  34. Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  35. Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure ReadingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  36. JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action AlignmentVision-language-action models → Human-video and latent-action pretraining
  37. F2Agent: Financial Fusion of Agentic Intelligence for Multimodal TradingLLM agents and tool use → Financial trading and forecasting agents
  38. Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMsLLM reasoning → Test-time compute and efficient thinking
  39. Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  40. Refining Over Resampling: Test-Time Self-Correction for LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  41. ChronoVision: Temporal Reasoning via Latent State ReconstructionLLM reasoning → Multimodal reasoning +1
  42. SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and ExploitationLLM agents and tool use → Agent skill learning and evolution
  43. TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  44. SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill LibrariesLLM agents and tool use → Agent skill learning and evolution
  45. LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin CorrectionLLM reasoning → Reinforcement learning for reasoning
  46. Uncertainty-Aware World Model for Aerial Image-Goal NavigationWorld models → World models for navigation
  47. Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMsLLM reasoning → Multimodal reasoning +1
  48. StepReflect: Structured UI Transition Reflection for Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents
  49. SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic ExecutionLLM agents and tool use → Agent skill learning and evolution
  50. Align-RAG: Alignment Is All You Need for TSFM In-Context LearningRetrieval-augmented generation → Time series and agricultural RAG
  51. When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  52. From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMsLLM safety and security → Safety alignment, refusal and guardrails
  53. Hierarchical Flow Matching for 3D Point Cloud GenerationDiffusion models → 3D, point cloud and scene generation
  54. Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction MergingLLM reasoning → Test-time compute and efficient thinking
  55. OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D ReconstructionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  56. HERA: Historical Evidence Routing Adapter for Physical Prediction in Latent World ModelsWorld models → Video-generation world models and simulators
  57. Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly DiscrepanciesLLM reasoning → Reasoning for agents, planning and code +1
  58. EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  59. DynaPix: Can Vision-Language Models Identify the Exact Future?Multimodal LLMs / vision-language models → Video understanding with MLLMs
  60. APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-TuningLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home AgentsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  62. Learning Context-Free Grammars for Grammar-Constrained Decoding via Declarative Agentic Programming with GuaranteesLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and EditingLLM agents and tool use → Multimodal and embodied agents
  64. When Big Data Becomes a Curse: Spatial Heterogeneity and the Limits of Learning from Passive Acoustic Monitoring Data
  65. Vorch-Human: Unified Multi-Task Human-Centric Generation via Long-Horizon Continuation
  66. FusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion
  67. Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection
  68. Summarize, Judge, Refine: Decoupled Content Understanding and Policy Learning for Multimodal Content Moderation
  69. Reading Anxiety or Reading the Label? Comparing Fine-Tuned and Frontier Models for Anxiety Detection on Social Media
  70. Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators
  71. Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs
  72. R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
  73. Transformer Accelerator (TFA): A Macro-Op INT8 Hardware Chip for Transformer Inference and Machine Translation
  74. ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding
  75. Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
  76. A Reproducibility Study of Partial Residual Ablations in Pre-LN Transformers
  77. Why AI Detection Fails for Academic Integrity
  78. Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures
  79. FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
  80. Algorithmic statistics of retinal images
  81. MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis
  82. Exploiting chemical shift variability enables recovery of overlapping metabolites from 1H nuclear magnetic resonance spectra
  83. Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Screening Assays
  84. Enhanced Real-Time 6-DOF Extended Reality Catheter Tracking for Evaluating Potential Improvement in Efficiency, Precision, and Depth Perception for Cardiac Interventions
  85. NewtonGS: Physics-Structured Object-Level Neural Newtonian Dynamics for Gaussian Scene Animation
  86. Discovering Conceptual Metaphors Across Topics and Media Types
  87. SoRoMoX: Fast, Differentiable, and Parallelizable Soft Robot Models
  88. Characterizing the Quality Profile of AI-Generated C++ in Production
  89. Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning
  90. Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separation
  91. The Sparsity Whisperer
  92. NxN E-valuation: Hypothesis Certification via a Conformal CRT Null
  93. Beyond Co-Movement: Locality by Exposures Enables a Joint Factor-Graph Framework for Portfolio Diversification
  94. Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval
  95. Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness
  96. SLED: Scalable Location Encoding via Distillation
  97. Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques
  98. Pre-Inference Routing for Cost-Efficient Document Field Extraction
  99. Toward surface-based registration of a virtual preoperative cutting guide onto the mandible for reconstruction surgery
  100. Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks
  101. Beyond "AI Language": The case for the idiolectal nature of LLM output
  102. SyncSBC: Decentralized Swarm Behavior Prediction for Synchronized Autonomous Control
  103. Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap
  104. From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models
  105. Implicit Neural Speckle Denoising
  106. Vision-Language Model Confidence Is Not a Property of the Answer
  107. Which Decisions Low-Bit Quantization Breaks, and How to Predict Them
  108. Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization
  109. Wasserstein Mahalanobis Distances for Recovering Latent Geometry
  110. Newton-Schulz Retraction-Based Inference Enables Hidden Quantum Markov Models to Outperform Classical HMMs
  111. TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade
  112. Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions
  113. Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance
  114. Density-Functional Excited-State Gradients and Nonadiabatic Couplings on a Consumer GPU from a Contraction-DAG
  115. KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planning
  116. Online Security Learning in Cooperative Multi-Agent Systems under Hidden Byzantine Attacks
  117. CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
  118. Target-Weighted Neyman Allocation: Experimental Design for Heterogeneous Treatment Effects under Population Shift
  119. Unmasking Removal-Budget Confounding: A Matched Operating-Point Evaluation Framework for Adaptive Data Cleaning
  120. Measuring the Cross-Lingual Comprehension Gap: How the language of the evidence shapes what language models understand
  121. Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
  122. ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
  123. InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion
  124. Beyond Attention: Signed Integrated Gradients Attribution in a BiomeGPT-Style Microbiome Transformer
  125. Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics
  126. Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning
  127. Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition
  128. ED-CSP: Crystal Structure Prediction from Electron Diffraction
  129. FedTransKD-IDS: Robust Federated Transfer Learning with Knowledge Distillation for Intrusion Detection in IoT
  130. SNI-GNN: SmartNIC-Assisted Full-Graph GNN Training with In-Network Embedding Prediction
  131. Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
  132. Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeria
  133. An Optimal Agnostic PAC Algorithm
  134. The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
  135. Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
  136. CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
  137. Challenges in Evaluating Explanation Methods for Static and Evolving Data
  138. Scalable estimation of VARMA models
  139. Optimal Rates for Learning with Monotone Adversaries
  140. Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
  141. Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents
  142. Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
  143. UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression
  144. QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction
  145. FastKron: Efficient Quantization with Kronecker-Factored Hessians
  146. Learning Latent Memory States from Longitudinal Athlete Monitoring Data
  147. Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data
  148. The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
  149. TLNM: Externally Validated Tooth Detection, Numbering and Segmentation from Smartphone Photographs Using Mask R-CNN
  150. Improving the Realism of Synthetic Clinical Benchmarks Under Utility Constraints
  151. OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations
  152. Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
  153. RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
  154. MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
  155. Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
  156. Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
  157. Timestep-Conditioned Transformers for Global Weather Forecasting
  158. Depth-Guided Video Object Counting in Crowded Scenes
  159. From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks
  160. Muon on the Stiefel Manifold Admits an Exact Closed-Form Update
  161. Continual Learning in Transition
  162. Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
  163. CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection
  164. What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
  165. Handling Missing Data in Probabilistic Regression Trees
  166. HOPE: Hand-Object Pressure Estimation from Monocular Videos
  167. EvReflection: Event-Driven Micro-Dynamics for Reflection Removal
  168. MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
  169. On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities
  170. Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation
  171. Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions
  172. Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
  173. Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset
  174. BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Models
  175. Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
  176. Reducing belief in conspiracy theories as they unfold using large language models
  177. CogVis: Must Open-Vocabulary Change Detection Perceive the Scene Anew for Every Query?
  178. FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
  179. Learning visual representations for compositional analysis of artworks and photographs
  180. Decolonizing Linguistic Policies in Automated Speech Recognition: A Framework for Cross-Culturally Competent Speech AI
  181. SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models
  182. LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm
  183. Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation
  184. Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts
  185. Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
  186. Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction
  187. Mind the Gaps: Mixture-of-Minds for Human Simulation
  188. From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems
  189. Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers
  190. Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations
  191. Signal or Spurious Cue? A Randomized Audit of Survey-Country Metadata in LLM Social Inference
  192. Dense-Cast: A lightweight ensemble of deep learning architectures for precipitation nowcasting
  193. Training-Free Token-Level Steering for LLM Personalized Co-Writing
  194. Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture
  195. Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
  196. DARAD: Dual Adapters and Ranking-Aware Distillation for Continual Remote Sensing Image-Text Retrieval
  197. ML-for-ML
  198. LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs
  199. Integrating Implicit and Explicit Relational Biases through Graph-Based Multiple Instance Learning: A Case Study in Skin Lesion Diagnosis
  200. Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
  201. PaCoNet: Deep Data Extraction for Parallel Coordinates
  202. FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India
  203. EpiBench: Can LLMs Understand Epitopes for Antibody Drug Discovery?
  204. ProDVI: Programmatic Dynamics Priors for Value Network Initialization
  205. HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards
  206. Wan-Animate-2: Pushing the Application Boundaries of Character Animation
  207. Do Tabular Foundation Models Agree with Themselves?
  208. Hybrid Machine Learning Framework for Herd-Level Cattle Growth Pattern and Weight Gain Forecasting in Grazing-Based Production Systems
  209. A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk
  210. Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies
  211. Universal Concept Disruption for SAM3 Image Segmentation
  212. THBKG: A Temporal Biomedical Knowledge Graph for Decision-Aligned Clinical Advancement Prediction
  213. Temporal Bridges for Spatial Resolution: Enhancing Climate Data Super-Resolution with Bidirectional Alignment
  214. How Far Do Simple Transformations Translate Across Text Embedding Models?
  215. Multi-Year Geospatial Reasoning using Interannually-Consistent Historical Predictions as a Free Input Modality
  216. TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions
  217. Topology-Aware Neighborhood Learning for Source-Free Cross-Scene Hyperspectral Image Classification
  218. Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models
  219. Stability of Ranking-dependent Pair-wise Comparison Patterns in the Analytic Hierarchy Process
  220. Operating Multi-Node Full Fine-Tuning on NVIDIA B300: A Field Report on Telemetry-Based Triage, Negative Results, and Operational Hardening
  221. MirrorNet: Can Medical Image Anonymization Really Protect Patient Identity?
  222. Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data
  223. BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells
  224. Floating Radiance Networks
  225. Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press
  226. CourseGraph: Finding overlaps and differences in Computer Science courses across universities
  227. CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal
  228. GSBF: Gaussian Splatting for Environment-Aware Beamforming
  229. ECG-LENS: Lead-Aware Clinical Context Enriched ECG Report Generation and Evaluation
  230. Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features
  231. The em-dash em-beds in Congress: A population-level rise in em-dash frequency in U.S. congressional press releases at the dawn of the large-language-model era, 2021-2025
  232. Beyond Feature Importance: A Comparative Analysis of Pattern Detection Methods in Cluster Interpretation
  233. To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
  234. D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation
  235. MACRO: Markov Chain Routing of Transformer Layers
  236. Improving Interoperability among Defence and National Security Ontologies: Analysis and Evaluation Tasks
  237. Evidential Rule Learning for Interpretable Classification with Abstention
  238. Shape-Aware Oriented Bounding Box (OBB) to Horizontal Bounding Box (HBB) Conversion
  239. MameLoshnLM: Yiddish Language Model and Evaluation Benchmark
  240. DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection
  241. Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation
  242. Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement
  243. Accurate Localization of Road Traffic Objects on the Road Plane Using Surveillance Camera Imagery
  244. A neural operator view on U-Nets for inverse imaging problems
  245. Controllable Clothing: Precise Labels and Generation for Virtual Try-On with Latent Diffusion Models
  246. MoCA: Implicit Social Context Analysis
  247. Decomposed Entailment for Factuality Checking and Hallucination Detection
  248. Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation
  249. M3R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
  250. Bayesian adaptively-weighted ensembles for few-shot abdominal segmentation
  251. Cautious Context Steering for Language Model Personalization
  252. STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models
  253. Hierarchical Latent Prediction for Language Models
  254. Ordered Diffusion for 3D Human Registration
  255. Predicting Task Difficulty Without Rollouts
  256. Fuzzy network jump models for soft dynamic clustering of graph-structured data
  257. VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation
  258. Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding
  259. When Do Prompt-Side Agent Playbooks Transfer? Accuracy, Cost, and Runtime Shift in Agent Deployment
  260. SR-JEPA: Learning Predictive Latent State in 3D Scenes
  261. Neuro-Symbolic Closed-Loop Control of Laser Powder Bed Fusion with an In-Loop Ontology
  262. HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection
  263. Accelerating nanodrug development in continuous flow systems using informed prediction models based on low-cost surrogate nanoparticles
  264. How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs
  265. GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
  266. UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on
  267. Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines
  268. ConceptADapt: Concept-guided Adaptive Feature Reconstruction with Dynamic Attention for Few-Shot Industrial Anomaly Detection
  269. Multivariate Time Series Forecasting needs Cross Variable Loss
  270. Once a Response, Always a Response: Detecting LLM-generated Text via Latent Prompt Restoration
  271. LiteKD-Net: Lightweight Knowledge-Distilled Network for Mobile Image Denoising
  272. ABC: Numerical Data Collection under Local Differential Privacy without Prior Knowledge
  273. Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams
  274. LILAC: An Idempotent Neural Speech Codec
  275. Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation
  276. Sparse PPMI Graph Averaging for Random Indexing Embeddings
  277. Iterative Hybrid Discrete-Continuous Viewpoint Planning for UAV Photogrammetry
  278. BlockPython: A Process-Aware Agent-Supported Platform for the Transition from Block-Based to Python Programming
  279. RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation
  280. Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing Objectives
  281. Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
  282. G2ARD-GS: Geometry-Guided Anchor-Regularized Gaussian Splatting Distillation
  283. SEAM: Global consistency beyond local accuracy in scientific machine learning
  284. TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding
  285. A Low-Power Wearable Respiratory Sensor for Non-Invasive Stress Monitoring
  286. SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment
  287. Provably Efficient Self-Calibrating Quantum Fault Tolerance
  288. Grounded Well-Condition Anomaly Detection on the Volve Field: Constructed Labels, a Baseline, and a Dual-Head Model
  289. Nonvisual Classification of Ground-Condition by Artificial Proprioception in an Amoeba-Inspired Autonomous Walking Robot
  290. DistMedVL: Distributional Vision-Language Alignment for Uncertainty-Aware Medical Image Segmentation
  291. A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition
  292. URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation
  293. When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering
  294. SafeDivertor: Faithful Divertor Heat Flux Reconstruction from Macroscopic Plasma State Signals via Time-Frequency Prior Exploitation
  295. Potential Matching Optimal Transport: Continuous Normalizing Flows for Exact p-Wasserstein Dynamics
  296. Dual-Attention and Adversarial Transfer Networks for Sim-to-Real Cross-Orientation Wireless Sensing
  297. Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
  298. Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
  299. Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
  300. Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation
  301. RASP-QAOA: Resource-Aware Per-Instance Selection for Exact QAOA Simulation
  302. Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying
  303. Human-Like Anaphor Resolution in Large Language Models
  304. SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation
  305. Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
  306. Measuring and Detecting Harmful AI Sycophancy
  307. ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation
  308. FOCUS: Decoupling Expert Personas in LLMs to Enhance Domain Expert Capabilities
  309. LC-Implicit-QAOA: Active-Workspace-Capped Exact Objective-and-Gradient Evaluation for Training over Bounded QUBO Light Cones
  310. GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification
  311. Structured Dimension-Matched Joint Variational Transdimensional Inference
  312. Enhancing Anomaly Resilience in Research Networks: A Large-Scale Forecasting Benchmark for Dynamic Security Baselining
  313. Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflows
  314. How Much Reconstruction Does Quantum Machine Learning Need? Late Fusion of Independently Trained Quantum Subcircuits
  315. Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations
  316. The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions
  317. Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation
  318. A Multi-Layer System for Ultra-High-Resolution Static 360-Degree Telepresence
  319. CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images
  320. EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal
  321. Turing's First Imitation Game: Design Concepts and a Human-Approximates-Machine Reading
  322. Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks
  323. Vibe Compiler: A Research-Logic Synthesis Tool That Runs without Prompt Engineering -Toward Enhancing Metacognition for Sustaining Agency in the Age of Generative AI-
  324. Equation-Free Period-Aware Forecast-Error Contraction for Estimating Negative Largest Lyapunov Exponents from Short Trajectory Ensembles
  325. Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness
  326. An Inertial Block Proximal Linearized Method with Adaptive Momentum for Nonconvex and Nonsmooth Optimization
  327. Innovation-Residual Auditing of Autonomous Analysis Agents: Localization, Detection Limits, Error Control, and Identifiability
  328. CDSeg: A Renderable Gaussian Carrier for Image-to-3D Label Transfer