mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 25 May 2026

516 papers

  1. Agentic Kernel Optimization: Generating State-of-the-Art GPU Kernels Without Hand-Written CUDALLM agents and tool use → Software engineering coding agents +1
  2. Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and ServicesLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. NEXUS: Structured Runtime Safety for Tool-Using LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  4. "AI Watermarking": Bridging Policy Discourse and Technical CapabilitiesLLM safety and security → Watermarking generated content and models
  5. Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought AgentsLLM reasoning → Multimodal reasoning
  6. Diffusion Image Generation with Explicit Modeling of Data Manifold GeometryDiffusion models → Diffusion foundations and sampling
  7. From Data to Insights: Exploring Program-of-Thoughts Prompting for Chart SummarizationLLM reasoning → Multimodal reasoning
  8. NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect ClassificationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  9. Advancing Creative Physical Intelligence in Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage RankingRetrieval-augmented generation → Agentic RAG, agents and memory +1
  11. VisualNeedle: Benchmarking Active Visual Search in Information-Dense ScenesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. When Does LeJEPA Learn a World Model?World models → Latent predictive world models
  13. BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular CarcinomaMixture-of-experts → Medical and biomedical MoE
  14. Cultural Value Alignment Via Latent Activation Steering in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  15. Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized RepresentationsLLM reasoning → Hallucination detection and mitigation
  16. Balancing Plasticity and Stability with Fast and Slow Successor FeaturesDeep reinforcement learning methods → Deep RL algorithms and representations
  17. In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent PerspectiveRetrieval-augmented generation → Generation and context integration
  18. RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning AgentsLLM reasoning → Knowledge- and tool-augmented reasoning
  19. MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic InterpretabilityLLM agents and tool use → Reinforcement learning for LLM agents +2
  20. ScientistOne: Towards Human-Level Autonomous Research via Chain-of-EvidenceLLM agents and tool use → Web, search, and research agents
  21. Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  22. Curriculum Learning for Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  23. Experiments in Agentic AI for ScienceLLM agents and tool use → Web, search, and research agents
  24. Sandlock: Confining AI Agent Code with Unprivileged Linux PrimitivesLLM agents and tool use → Agent threats, guardrails and governance
  25. CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer DetectionMultimodal LLMs / vision-language models → Medical vision-language models
  26. CroCo: Cross-Lingual Contrastive Preference Tuning on Self-GenerationsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  27. Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential TuningMultimodal LLMs / vision-language models → Medical vision-language models
  28. Stateful Inference for Low-Latency Multi-Agent Tool CallingLLM agents and tool use → Software engineering coding agents
  29. Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal ScreeningMultimodal LLMs / vision-language models → Medical vision-language models
  30. Scaling World-Model Reinforcement Learning Through Diffusion Policy OptimizationWorld models → Latent dynamics models and model-based RL +2
  31. SPEAR: Code-Augmented Agentic Prompt OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  33. Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video DiffusionDiffusion models → Video generation +1
  34. Personalizing Embodied Multimodal Large Language Model Agents over Long-term User InteractionsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  35. The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels WorksKnowledge distillation → Knowledge distillation for LLMs
  36. Sentinel: Embodied Cooperative Spatial Reasoning and PlanningLLM reasoning → Spatial and embodied reasoning
  37. Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal VideosLLM reasoning → Audio-language model reasoning
  38. AgentSociety: Incentivizing Agentic Social IntelligenceLLM agents and tool use → Social simulation and multi-agent debate
  39. CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the FlyLLM agents and tool use → Agent threats, guardrails and governance
  40. SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?LLM agents and tool use → Software engineering coding agents
  41. AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT CalculationsLLM agents and tool use → Medical and scientific domain agents
  42. ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron HierarchyLLM agents and tool use → General LLM agent frameworks and benchmarks
  43. ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time SamplingLLM reasoning → Test-time compute and efficient thinking
  44. MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent ResearchLLM agents and tool use → GUI and mobile agents
  45. AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and BeyondEnd-to-end autonomous driving → Generative simulation for driving
  46. From Model Scaling to System Scaling: Scaling the Harness in Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  47. Squeezing Capacity from Multimodal Large Language Models for Subject-driven GenerationMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  48. Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  49. Reinforcing Few-step Generators via Reward-Tilted Distribution MatchingDiffusion models → Diffusion and flow policies for robotics +1
  50. Looped Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  51. On-Policy Adversarial Flow Distillation for Autoregressive Video GenerationKnowledge distillation → On-policy and self-distillation for LLMs
  52. Forgetting in Language Models: Capacity, Optimization, and Self-Generated ReplaySynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  53. DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific ThinkingLLM reasoning → Spatial and embodied reasoning
  54. Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital WorldLLM agents and tool use → GUI and mobile agents
  55. VeriTrace: Evolving Mental Models for Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  56. Automated Benchmark Auditing for AI Agents and Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  58. Paris 2.0: A Decentralized Diffusion Model for Video GenerationDiffusion models → Video generation
  59. DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  60. Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool UseLLM reasoning → Test-time compute and efficient thinking
  61. CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI ScientistsLLM agents and tool use → Medical and scientific domain agents
  62. Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of ServiceRetrieval-augmented generation → Legal and financial RAG
  63. STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language ModelsLLM reasoning → Multimodal reasoning
  64. AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow ModelsDiffusion models → Diffusion and flow policies for robotics +1
  65. Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  66. MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  67. Causal methods for LLM development and evaluationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  68. AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  69. LLaVA-OneVision-2: Towards Next-Generation Perceptual IntelligenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  70. Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-TuningLLM reasoning → Reasoning benchmarks and evaluation
  71. PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical FlowchartsLLM agents and tool use → Medical and scientific domain agents
  72. Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic AudioLLM safety and security → Watermarking generated content and models
  73. LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  74. Continual Speaker Identity Unlearning with Minimal InterferenceLLM safety and security → Machine unlearning
  75. PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight ExtractionLLM reasoning → Reasoning for agents, planning and code +1
  76. Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program OptimizationLLM reasoning → Test-time compute and efficient thinking
  77. VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal UnderstandingMixture-of-experts → Multimodal MoE models
  78. Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  79. How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?Diffusion models → Inverse problems and image restoration
  80. Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?LLM agents and tool use → Social simulation and multi-agent debate
  81. Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  82. Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement LearningLLM agents and tool use → Social simulation and multi-agent debate
  83. Joint Optimization of Training and Inference in Federated Edge Learning via Constrained Multi-Objective Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  84. AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  85. Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action ModelsVision-language-action models → Safety and adversarial attacks +1
  86. DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  87. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model EvaluationWorld models → Video-generation world models and simulators
  88. Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory RepresentationLLM agents and tool use → Agent memory systems
  89. When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  90. Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and MetacognitionLLM reasoning → Reasoning benchmarks and evaluation
  91. MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured PruningLLM reasoning → Multimodal reasoning +1
  92. When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving SkillsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  93. OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic ManipulationWorld models → Embodied and robot world models +1
  94. [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive AggregationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  95. Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  96. On Reliability of Membership Inference Vulnerability EvaluationLLM safety and security → Membership inference attacks
  97. Rethinking VLM Representation for VLA InitializationLLM reasoning → Spatial and embodied reasoning +2
  98. Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  99. SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase RobustnessLLM safety and security → Watermarking generated content and models
  100. Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
All 516
  1. Concept Unlearning via Cross-Attention Activation Projection for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  2. AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
  3. Towards Anatomically Plausible Human Image Generation via Synthetic Localized PreferencesLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  4. Multi-Agent Coordination Adaptation via Structure-Guided OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Selective Latent Thinking: Adaptive Compression of LLM Reasoning ChainsLLM reasoning → Test-time compute and efficient thinking
  6. Latent Representation Alignment for Offline Goal-Conditioned Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  7. The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes ImpossibleDeep reinforcement learning methods → RL training of language and agent models
  8. Learning to Search and Searching to Learn for Generalization in PlanningDeep reinforcement learning methods → Deep RL algorithms and representations
  9. An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAGRetrieval-augmented generation → Privacy and security of RAG
  10. AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment CorruptionsLLM agents and tool use → Agent threats, guardrails and governance
  11. Neural Router: Semantic Content Matching for Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  12. How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling LawsMixture-of-experts → MoE large language models
  13. HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and ControlDiffusion models → Diffusion and flow policies for robotics
  14. Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion ModelsDiffusion models → Flow matching, time series and science
  15. DRM: Diffusion-based Reward Model With Step-wise GuidanceDiffusion models → Diffusion and flow policies for robotics +1
  16. When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical SystemsLLM agents and tool use → Agent threats, guardrails and governance
  17. G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor NavigationLLM reasoning → Spatial and embodied reasoning
  18. Iterate Until Retrieved: Factual Nugget Optimization for Discoverable Continual Corrections in Agentic RAGRetrieval-augmented generation → Agentic RAG, agents and memory +1
  19. Reinforcement Learning from Denoising FeedbackDiffusion models → Diffusion and flow policies for robotics +1
  20. When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference ShiftLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  21. CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  22. Back to Parsimonious Latents: Learning Task-Centric World Models from Visual FoundationsWorld models → Latent predictive world models
  23. DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +1
  24. Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External DiscrepancyLLM reasoning → Prompting and chain-of-thought reasoning
  25. Extreme Region Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  26. Geometric Flow Matching for Molecular Conformation Generation via Manifold DecompositionDiffusion models → Flow matching, time series and science
  27. PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code GenerationSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  28. AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor EvolutionLLM reasoning → Multimodal reasoning +1
  29. Uncertainty Reasoning with Large Language Models for Explainable Disease DiagnosisLLM reasoning → Clinical and biomedical applications
  30. RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating MechanismMixture-of-experts → MoE large language models
  31. BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training DataLLM reasoning → Prompting and chain-of-thought reasoning
  32. Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon AgentsLLM agents and tool use → Agent memory systems
  33. StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMsLLM reasoning → Reasoning for agents, planning and code +1
  34. From Denoising to Decision Making: A Survey on Diffusion Model-Enabled Deep Reinforcement Learning for Wireless NetworksDiffusion models → Diffusion for compression and wireless
  35. SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language ModelsMechanistic interpretability → SAE features and their applications +1
  36. ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMsLLM reasoning → Spatial and embodied reasoning +1
  37. CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing AgentsLLM reasoning → Reinforcement learning for reasoning +1
  38. The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  39. Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and TheoryDiffusion models → Flow matching, time series and science
  40. Credit Assignment with Resets in Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning
  41. WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion ModelsDiffusion models → Audio, speech and music
  42. Full-4D: Generating Full-Scope 4D Scenes from a Single-View VideoDiffusion models → 3D, point cloud and scene generation
  43. RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic RelevanceLLM reasoning → Knowledge- and tool-augmented reasoning +1
  44. Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-WikiLLM reasoning → Knowledge- and tool-augmented reasoning +2
  45. MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  46. EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +1
  47. IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  48. BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM TrainingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  49. Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video DiffusionDiffusion models → 3D, point cloud and scene generation
  50. GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram GenerationDeep reinforcement learning methods → RL with diffusion and flow models
  51. Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  52. Enhancing Single-Image Facial Demorphing using Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  53. A Multi-Agent LLM Framework for Rating the Quality of Surgical FeedbackLLM agents and tool use → Medical and scientific domain agents
  54. Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual ReasoningLLM reasoning → Multimodal reasoning
  55. Security of OpenClaw Agents: Fundamentals, Attacks, and CountermeasuresLLM agents and tool use → Agent threats, guardrails and governance
  56. CODESKILL: Learning Self-Evolving Skills for Coding AgentsLLM agents and tool use → Agent skill learning and evolution +1
  57. Binding Visual Features Point by PointMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  58. SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  59. A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  60. HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text ProtocolLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper ReviewersLLM safety and security → Prompt injection and agent security
  62. How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  63. Decision-Making with Lightweight Confidence-Aware Language Model for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  64. Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MASLLM agents and tool use → Agent threats, guardrails and governance
  65. GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem SolvingLLM reasoning → Spatial and embodied reasoning
  66. StateRAG: Typed State Contracts for Complex Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  67. CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy DistillationDiffusion models → Image generation, text-to-image and editing +1
  68. Adversarial Orthogonal Disentanglement for LVLM Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  69. Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric ReasoningLLM reasoning → Multimodal reasoning +1
  70. Context-CoT: Enhancing Context Learning via High-Quality Reasoning SynthesisLLM reasoning → Prompting and chain-of-thought reasoning
  71. Toward Native Multimodal Modeling: A RoadmapWorld models → World models for language agents
  72. MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  73. CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent FailuresLLM agents and tool use → Software engineering coding agents
  74. Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State EvolutionWorld models → Video-generation world models and simulators
  75. UWM-JEPA: Predictive World Models That Imagine in Belief SpaceWorld models → Latent predictive world models
  76. Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual StreamsLLM agents and tool use → Tool learning and function calling
  77. Spectral origin of the topological gap exponent d + η: mechanism, kernel, decomposition, and scope
  78. Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety
  79. Language as a Material Interface for Creative LLM Interaction
  80. Household Movement Detection in Mixed-Format Occupancy Data Using LLM-Based Entity Resolution
  81. The Hard Decision Layer: Evidence for Committed Inference in Transformers
  82. Benchmarking Large Language Models on Multi-Sensor Physical Hazard Assessment
  83. AI-Model Network: Concept, Current State and Future
  84. SurfDesign: Effective Protein Design on Molecular Surfaces
  85. STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms
  86. Considerations for an Integrated Detector Design at FCC-ee: A Human-AI Exploration
  87. Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems
  88. The Montparnasse Algorithm for RNA Design
  89. Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes
  90. Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning
  91. Phantom Transitions in Language Model Fine-Tuning: A Density-Matrix Analysis
  92. Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing
  93. SPIN: Decentralized Swarm Control via Tensorized Policy Coordination
  94. Selecting New Measurement Locations to Diversify Traffic-Pattern Coverage: A Real-World Evaluation for Total Traffic Volume Estimation
  95. Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override
  96. Which Anatomy Matters Under Limited Labels? A Data-Efficient Anatomy-Aware Benchmark for Cardiac Pathology Prediction
  97. Segmentation-Guided Spatial Indexing for Generalizable and Explainable Deepfake Detection
  98. Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation
  99. Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why
  100. Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit
  101. D2Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation
  102. Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures
  103. Metric-Aware PCA as a Linear Instance of Geometric Deep Learning
  104. MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition
  105. Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study
  106. Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing
  107. Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
  108. Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
  109. Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery
  110. Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
  111. Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
  112. Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery
  113. Unified Panoramic Geometry Estimation via Multi-View Foundation Models
  114. Automatic Layer Selection for Hallucination Detection
  115. Fast Convergence of Policy Regret in Learning Stochastic Optimal Control
  116. Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows
  117. Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention
  118. Personalized Generative Models for Contextual Debiasing
  119. When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
  120. The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology
  121. A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning
  122. QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
  123. Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning
  124. JobBench: Aligning Agent Work With Human Will
  125. RadarSim: Simulating Single-Chip Radar via Multimodal Neural Fields
  126. Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage
  127. Semigroup Consistency as a Diagnostic for Learned Physics Simulators
  128. OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
  129. Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
  130. MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding
  131. E3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control
  132. Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks
  133. Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieval-Augmented Generation and Large Language Models
  134. Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
  135. Sleep-stage efficient classification using a lightweight self-supervised model
  136. Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks
  137. Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects
  138. A multifractal-based masked auto-encoder: an application to medical images
  139. Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering
  140. Two-Parameter Flows for Learning Population Dynamics of Physical Systems
  141. MPMMine: Better Benchmarks for Constraint Acquisition
  142. VesselSim: learning 3D blood vessel segmentation without expert annotations
  143. Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation
  144. Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
  145. Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis
  146. Prospective evaluation of multimodal respiratory failure prediction: Do chest X-rays improve performance beyond EHR signals?
  147. Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
  148. Unified Neural Scaling Laws
  149. LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
  150. Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
  151. Can LLMs Introspect? A Reality Check
  152. RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation
  153. DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation
  154. Minimal surfaces, Knots, and Neural Networks
  155. Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
  156. From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms
  157. Workflow Closure Is Not Scientific Closure in Auto-Research Systems
  158. On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series
  159. Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
  160. Co-folding model guided by structural proteomics
  161. Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series
  162. HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals
  163. Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training
  164. GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
  165. What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction
  166. BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
  167. RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
  168. PitchBench: Measuring Pitch Hearing in Audio-Language Models
  169. InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
  170. A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration
  171. When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
  172. LearnedCache: eBPF-Integrated Perceptron-Based Eviction Policies for the Linux Page Cache
  173. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
  174. Helix4D: Complex 4D Mesh Generation
  175. EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
  176. Global Structure-from-Motion Meets Feedforward Reconstruction
  177. InstructSAM: Segment Any Instance with Any Instructions
  178. Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models
  179. Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
  180. Pixel-Level Pavement Distress Assessment Using Instance Segmentation
  181. Goal-driven Bayesian Optimal Experimental Design for Robust Decision-Making Under Model Uncertainty
  182. GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization
  183. Channel-wise Vector Quantization
  184. StakeBench: Evaluating Language Understanding Grounded in Market Commitment
  185. Active Query Synthesis for Preference Learning
  186. WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification
  187. Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
  188. Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding
  189. Look Both Ways Before You Cross: Lifting Cross Fields From 2D Visual Priors
  190. Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning
  191. Accelerating Bayesian inverse design in computational fluid dynamics using neural operators
  192. Retrying vs Resampling in AI Control
  193. When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
  194. Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
  195. L2IR: Revealing Latent Intent in Graph Fraud Detection
  196. CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities
  197. Length Generalization with Log-Depth Recurrent Units
  198. Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
  199. A Multimodal 3D Foundation Model for Light Sheet Fluorescence Microscopy Enables Few-Shot Segmentation, Classification, and Deblurring
  200. Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversational Filipino and English Speech
  201. MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control
  202. Towards 3D heart mesh generation using contactless radar imaging and physics-informed neural network
  203. AI-Assisted Systematization for Evaluating GenAI Systems
  204. Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance
  205. Deployment-complete benchmarking
  206. Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models
  207. What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
  208. Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables
  209. SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation
  210. F-RNG: Feed-Forward Relightable Neural Gaussians
  211. Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
  212. Triplet-Block Diffusion RWKV
  213. Context-driven Missing-Modality Learning for Robust Medical Diagnosis with Image-Tabular Data
  214. Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training
  215. RAPTOR+: A Visually Grounded Vision-Language Framework to Improve Clinical Trust and Auditability in Automated Cancer Referral Processing
  216. QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
  217. Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
  218. A Pedestrian-Vehicle Interaction Benchmark and Annotation Framework for Unstructured Scenes via Uncalibrated Cameras
  219. EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory
  220. STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy
  221. LRDDv3: High-Resolution Long-Range Drone Detection Dataset with Range Information and Thermal Data
  222. From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
  223. Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation
  224. Quantitative Evaluation of the Severity of Posttraumatic Stress Disorder through Transfer Learning from Specific Phobia Data
  225. Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3
  226. Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
  227. Does Continued Pretraining on a Learner Corpus Improve Automated Essay Scoring on English Proficiency Tests? Evidence from EFCAMDAT
  228. Curve Skeletonization in Continuous domain for Meshes and Point Clouds
  229. Accelerated Spatio-Temporal Gaussian Rendering via Kinematic and Semantic Priors
  230. Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
  231. Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
  232. Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Learning
  233. D2-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals
  234. SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution
  235. Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express
  236. Merge-Bench: Resolve Merge Conflicts with Large Language Models
  237. Optimal and Order-optimal Gated Priority-based Greedy Policies for Two-layer Multi-item Order Fulfillment
  238. Conformalised imprecise inference for robust extrapolation under limited data
  239. The Quantization Benefits of Residual-Free Transformers
  240. A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation
  241. The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams
  242. UNATE: UNsupervised ATomic Embedding for crystal structures property prediction
  243. MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images
  244. SAM3-Assisted Training of Lightweight YOLO Models for Precision Pig Farming
  245. Minimax Limits of k-Fold Cross-Validation via Majority
  246. High-Dimensional Robust Change-Point Detection via Angular Kernel Statistics
  247. From Accounting to Coordination: A Virtual Water-Aware Electricity-Computation-Water Nexus Framework for Data Center Dispatch
  248. TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
  249. Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams
  250. On the Limits of Model Merging for Multilinguality in Pre-Training
  251. CTI2TTP: Evidence-Grounded TTP Extraction from Cyber Threat Intelligence via Diverge-then-Converge Verification
  252. Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation
  253. Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
  254. Branched Signature Kernel Solvers for ODEs with rough Single-Trajectory signals
  255. Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa
  256. Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network
  257. Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution
  258. Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing
  259. Data-driven Head Motion Generation through Natural Gaze-Head Coordination
  260. An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?
  261. Event-to-Video Reconstruction using Spatio-Temporal and Frequency-Enhanced Deep Neural Networks
  262. ATV-Net: Adaptive Triple-View Network with Dynamic Feature Fusion
  263. PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution
  264. When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Interaction Logs
  265. On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
  266. NPSolver: Neural Poisson Solver with Iterative Physics Supervision
  267. Double Triangle Annotation: A Scalable Human-in-the-Loop Framework for High-Precision Historical Document Annotation
  268. OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
  269. DRFusion: Drift-Resilient Temporally Consistent Infrared-Visible Video Fusion
  270. Efficient Benchmarking Is Just Feature Selection and Multiple Regression
  271. MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training
  272. SAFE-Diff: Scale-Aware Attention and Feature-Dispersive Diffusion with Uncertainty Estimation for Contrast-Enhanced Breast MRI Synthesis
  273. Benchmarking Pathology Foundation Models for Spatial Domain Understanding
  274. StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios
  275. Broadband Hyperspectral 3D Imaging using Dispersed Structured Light
  276. SplitAvatar: One-shot Head Avatar with Autoregressive Gaussian Splitting
  277. Invariant-Based Weight Sharing for Message Passing
  278. DeGRe: Dense-supervised Generative Reranking for Recommendation
  279. Agent-Centric Social Trajectory Prediction: A Free Energy Principle Perspective
  280. SFR-Net: Learning Scale-Frustum Representations for Ultra-Wide Area Remote Sensing Image Segmentation
  281. A Deep Dive into Axiomatic Design -- Part I: Problem Formulation
  282. Stein-Encoder: A White-Box Supervised Encoder via Stein Identities in Multi-Modal Studies
  283. Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
  284. DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation
  285. TriDP-PTM: a three-stage distortion-perception tradeoff guides the pre-training model for radar cardiac sensing
  286. FLOATBench: A Dataset and Benchmark for Floating Offshore Wind Turbine Tower Fatigue
  287. Machine Learning Multiscale Interactions
  288. CMAP: Cross-Modal Adaptive Prompting for Multi-Domain Task-Incremental Learning
  289. Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker
  290. PowLU: An Activation Function for Stable Pre-Training of LLMs
  291. Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selection
  292. From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
  293. Testing the Deliteralization Hypothesis in Human and Machine Translation
  294. Profiling-Driven Adaptive Distributed Transformer Inference on Embedded Edge Deployment
  295. Simulating Human Memory with Language Models
  296. PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
  297. Llamion Technical Report
  298. Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training
  299. Referential Security as a New Paradigm for AI Evaluations
  300. Meta-Engineering Harnesses for AI-Native Software Production: A Contract-Driven Adversarial Verification Architecture with Early Deployment Report
  301. Posture Clip: Sit properly or I wont let you work
  302. Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
  303. Closed-Form Node Classification with Exact Graph Unlearning
  304. StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration
  305. AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
  306. ARMA-C3: A Contrastive ARMA Convolutional Framework for Unsupervised and Semi-supervised Classification
  307. Event-based Batting Impact Estimation
  308. A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays
  309. Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception
  310. StrTransformer: Source-Wise Structured Transformers for Unsupervised Blind Source Recovery
  311. Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines
  312. 3D Magnetic Field Reconstruction and Mapping with Physics-Informed Neural Networks
  313. Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents
  314. Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
  315. StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
  316. Analogies between Transformer Layers and Power Method
  317. Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
  318. UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognition
  319. Towards the Connection between Activation Sparsity and Flat Minima
  320. Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
  321. Decoding Stimulus Reconstruction-Based Auditory Attention Robustly in Unbalanced EEG Datasets
  322. Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models
  323. Generalized Evidential Deep Learning: From a Bayesian Perspective
  324. SurfSurg6D: Geometry Consistent Dense Correspondence for Textureless Surgical Instrument Pose Estimation
  325. Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
  326. How Far Has AI Come in Liver Fibrosis Staging? A Large-Scale Real-World Dataset and Benchmark
  327. Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
  328. Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
  329. Artifact Correction for Echo-Planar Imaging at Low-Field and Ultra-Low-Field MRI
  330. Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation
  331. Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction
  332. Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
  333. From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation
  334. ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
  335. Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking
  336. Rao-Blackwellized Score Matching on Manifolds
  337. CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
  338. Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
  339. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
  340. Keep the Proof State Live: Snapshotting for Efficient Tactic Search in Lean 4
  341. PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting
  342. ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation
  343. Learning Permutation from Structure Without Supervision
  344. SiST-GNN: Simultaneous Spatial-Temporal Message Passing for Dynamic Graph Representation Learning
  345. TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
  346. ADMFormer: An Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attention for Traffic Forecasting
  347. TopoAlign: Topology-Aware Visual Representation Alignment
  348. A Multimodal Framework for Dementia Detection via Linguistic and Acoustic Representation Learning
  349. Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking
  350. A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions
  351. Location Prior Generation via Multi-Source Urban Data Fusion for Low-Altitude Air Mobility
  352. DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading
  353. From DPPs to k-DPPs: identifiability analysis via spectral decomposition
  354. Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
  355. Cross-Stage Attention Multi-Expert Network for Radiologist-Inspired Breast Ultrasound Diagnosis
  356. What Gets Cited: Competitive GEO in AI Answer Engines
  357. Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation
  358. Generative AI impacts on intra-urban inequality and skill premium in Beijing
  359. Metric--Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
  360. A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis
  361. Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
  362. RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation
  363. SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
  364. ATWL: A Formal Language for Representing, Comparing, and Reusing Visual Analytics Workflows
  365. Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation
  366. TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification
  367. JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates
  368. A Lightweight Hybrid Transformer-CRF Architecture for Multi-Type Bangla Medical Entity Recognition
  369. MetaphorVU: Towards Metaphorical Video Understanding
  370. Mean-Shift PCA by Knockoff Mean
  371. From Simulation to Enaction: Post-trained language models recognize and react to their own generations
  372. AI Content Moderation in Therapy Conversations
  373. Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks
  374. A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography
  375. Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random
  376. Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
  377. Learning View-Dependent Splatting Kernels
  378. SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
  379. Capture-Calibrate-Coach: A Graph-Based Framework for Knowledge Monitoring Estimation and Adaptive Feedback
  380. Generating 3D models from sketches of human faces using a combined approach of Convolutional Neural Networks, Procedural Modeling, and Contour Mapping
  381. Autoregression-Free Neural Operators for Time-Dependent PDEs
  382. MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model
  383. Towards Active Real-to-Twin Inspection: A New Paradigm for Zero-Shot Anomaly Detection
  384. Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems
  385. Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation
  386. Towards end-to-end LLM-based censoring-aware survival analysis
  387. Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultrasound Plane Quality Control
  388. EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization
  389. Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
  390. A Context Augmented Multi-Play Multi-Armed Bandit Algorithm for Fast Channel Allocation in Opportunistic Spectrum Access
  391. ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks
  392. Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance
  393. Learning manifold diffusion semigroups from graph transition matrices
  394. AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora
  395. Not only where, But when: Temporal Scheduling for RLVR
  396. KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition
  397. Physics-Aware 3D Gaussian Editing for Driving Scene Generation
  398. MARVEL: Universal Murray's Law-informed Vessel Tree Segmentation and Topology Estimation
  399. Learning to Route Languages for Multilingual Policy Optimization
  400. AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing
  401. Towards Reliable Fetal Ultrasound Interpretation with Multi-Agent Collaboration
  402. PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problems
  403. Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
  404. Parameter-Efficient CT Reconstruction via Deep Graph Laplacian Regularization
  405. ERNIE-Image Technical Report
  406. Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
  407. Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Rendering
  408. A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models
  409. Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence
  410. DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
  411. Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation
  412. P1SCO: Social Dimensions from a Perspectivist Lens
  413. Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
  414. Recursive Class Connectivity Classification (R3C) Applied to Binary Image Segmentation for Improved Infant Fingerprint Enhancement
  415. Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations
  416. When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers