mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 9 Apr 2026

491 papers

  1. Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for CodeWorld models → World models for language agents +1
  2. VineLM: Trie-Based Fine-Grained Control for Agentic WorkflowsLLM agents and tool use → Software engineering coding agents
  3. MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning CorrectionLLM reasoning → Clinical and biomedical applications
  4. From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical DatasetLLM agents and tool use → Medical and scientific domain agents
  5. Graph Query Generation with Constraint-guided Large Language AgentsLLM agents and tool use → Web, search, and research agents
  6. B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  7. On Tackling Complex Tasks with Reward Machines and Signal Temporal LogicsDeep reinforcement learning methods → Interpretable and logic-guided RL
  8. Functional Emotions or Situational Contexts? A Discriminating Test from the Mythos Preview System CardMechanistic interpretability → Activation steering methods
  9. SMART: When is it Actually Worth Expanding a Speculative Tree?Efficient LLM inference and serving → Speculative decoding
  10. LOLGORITHM: Funny Comment Generation Agent For Short VideosLLM agents and tool use → Multimodal and embodied agents
  11. HiFloat4 Format for Language Model Pre-training on Ascend NPUsMixture-of-experts → Efficient MoE training and inference systems
  12. Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  13. Building Better Environments for Autonomous Cyber DefenceDeep reinforcement learning methods → Adversarial robustness and RL in finance
  14. eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video StreamingDeep reinforcement learning methods → RL for energy, networks and operations
  15. MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial ObservabilityLLM reasoning → Clinical and biomedical applications
  16. Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal LocomotionWorld models → Embodied and robot world models
  17. SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting GenerationDiffusion models → 3D, point cloud and scene generation
  18. Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm ConstraintsLLM safety and security → Watermarking generated content and models
  19. Cards Against LLMs: Benchmarking Humor Alignment in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  20. Communicate-Predict-Act: Evaluating Social Intelligence of AgentsLLM agents and tool use → Social simulation and multi-agent debate
  21. Task-Aware Bimanual Affordance Prediction via VLM-Guided Semantic-Geometric ReasoningLLM reasoning → Spatial and embodied reasoning
  22. Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?LLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  23. LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End DrivingWorld models → World models for autonomous driving +1
  24. What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment ReconstructionDiffusion models → 3D, point cloud and scene generation
  25. Model Space Reasoning as Search in Feedback Space for Planning Domain GenerationLLM reasoning → Reasoning for agents, planning and code
  26. Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor DecompositionLLM agents and tool use → General LLM agent frameworks and benchmarks
  27. Skip-Connected Policy Optimization for Implicit AdvantageLLM reasoning → Reinforcement learning for reasoning
  28. RAMP: Hybrid DRL for Online Learning of Numeric Action ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
  29. GenPHRI: Agentic Generative Simulation for Physical Human-Robot InteractionLLM agents and tool use → Multimodal and embodied agents
  30. InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models AdaptationDiffusion models → Video generation
  31. 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  32. EXAONE 4.5 Technical ReportMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  33. Retrieval Augmented Classification for Confidential DocumentsRetrieval-augmented generation → Privacy and security of RAG
  34. Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case StudyLLM agents and tool use → Social simulation and multi-agent debate
  35. StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  36. SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical SupportLLM agents and tool use → Agent skill learning and evolution +1
  37. MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water EnvironmentsLLM reasoning → Multimodal reasoning +1
  38. When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion ModelsDiffusion models → Video generation
  39. Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  40. Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-ExpertsMixture-of-experts → Multimodal MoE models
  41. OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual TasksLLM reasoning → Multimodal reasoning +1
  42. ParseBench: A Document Parsing Benchmark for AI AgentsLLM agents and tool use → Web, search, and research agents
  43. RewardFlow: Generate Images by Optimizing What You RewardDiffusion models → Diffusion and flow policies for robotics +1
  44. Fail2Drive: Benchmarking Closed-Loop Driving GeneralizationEnd-to-end autonomous driving → End-to-end system architecture
  45. Self-Improving 4D Perception via Self-DistillationKnowledge distillation → Detection and dense prediction distillation
  46. Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  47. What Drives Representation Steering? A Mechanistic Case Study on Steering RefusalLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  48. MolmoWeb: Open Visual Web Agent and Open Data for the Open WebLLM agents and tool use → Web, search, and research agents
  49. FrameCrafter: Novel View Synthesis as Video CompletionDiffusion models → 3D, point cloud and scene generation
  50. PIArena: A Platform for Prompt Injection EvaluationLLM safety and security → Prompt injection and agent security
  51. SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural InstructionsLLM reasoning → Reinforcement learning for reasoning
  52. Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy OptimizationLLM reasoning → Spatial and embodied reasoning +1
  53. TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational SynthesisLLM reasoning → Reinforcement learning for reasoning +1
  54. From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse AnalysisLLM agents and tool use → Social simulation and multi-agent debate
  55. CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and ReasoningLLM reasoning → Chain-of-thought reasoning for driving
  56. Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  57. KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent EvaluationLLM agents and tool use → GUI and mobile agents
  58. KV Cache Offloading for Context-Intensive TasksEfficient LLM inference and serving → KV cache optimization
  59. Synthetic Data for any Differentiable TargetSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
  60. Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply ChainLLM agents and tool use → Agent threats, guardrails and governance
  61. Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-AuditingLLM reasoning → Reasoning for agents, planning and code +1
  62. Phantasia: Context-Adaptive Backdoors in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  63. Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel ProverLLM agents and tool use → Educational agents and math problem solving
  64. SkillClaw: Let Skills Evolve Collectively with Agentic EvolverLLM agents and tool use → Agent skill learning and evolution
  65. Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  66. Scaling-Aware Data Selection for End-to-End Autonomous Driving SystemsEnd-to-end autonomous driving → End-to-end system architecture
  67. Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled TrainingDiffusion models → Flow matching, time series and science
  68. InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal UnderstandingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  69. Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
  70. DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR ConditioningDiffusion models → Diffusion for compression and wireless
  71. ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit InjectionLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  72. Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public DataLLM reasoning → Clinical and biomedical applications
  73. Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified FlowDiffusion models → Medical imaging and segmentation
  74. HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in HistopathologyDiffusion models → Medical imaging and segmentation
  75. Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future DirectionsRetrieval-augmented generation → Privacy and security of RAG
  76. DMax: Aggressive Parallel Decoding for dLLMsDiffusion models → Discrete and text diffusion +1
  77. SeLaR: Selective Latent Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  78. Towards Identification and Intervention of Safety-Critical Parameters in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  79. Can Vision Language Models Judge Action Quality? An Empirical EvaluationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  80. VCAO: Verifier-Centered Agentic Orchestration for Strategic OS Vulnerability DiscoveryLLM agents and tool use → Agent threats, guardrails and governance
  81. When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math ReasoningLLM reasoning → Reasoning for agents, planning and code
  82. An Illusion of Unlearning? Assessing Machine Unlearning Through Internal RepresentationsLLM safety and security → Machine unlearning
  83. Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving ModelsLLM reasoning → Chain-of-thought reasoning for driving +2
  84. Self-Debias: Self-correcting for Debiasing Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  85. oslash Source Models Leak What They Shouldn't nrightarrow: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial OptimizationLLM safety and security → Machine unlearning
  86. HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied NavigationLLM reasoning → Spatial and embodied reasoning
  87. Grounding Clinical AI Competency in Human Cognition Through the Clinical World Model and Skill-Mix FrameworkWorld models → Medical and surgical world models
  88. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness EngineeringLLM agents and tool use → General LLM agent frameworks and benchmarks
  89. MemCoT: Test-Time Scaling through Memory-Driven Chain-of-ThoughtLLM reasoning → Reasoning for agents, planning and code
  90. EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction SynthesisLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  91. Vision-Language Foundation Models for Comprehensive Automated Pavement Condition AssessmentMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  92. MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement LearningLLM reasoning → Clinical and biomedical applications +2
  93. Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph GenerationDiffusion models → Flow matching, time series and science
  94. Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward ModelingLLM agents and tool use → Reinforcement learning for LLM agents +1
  95. Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  96. Activation Steering for Aligned Open-ended Generation without Sacrificing CoherenceLLM safety and security → Safety alignment, refusal and guardrails +1
  97. ViVa: A Video-Generative Value Model for Robot Reinforcement LearningVision-language-action models → Reinforcement learning and post-training +1
  98. Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf FormulaDeep reinforcement learning methods → RL theory and sample complexity
  99. Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A BenchmarkLLM reasoning → Chain-of-thought reasoning for driving
  100. Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts InferenceMixture-of-experts → Efficient MoE training and inference systems
All 491
  1. Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic SearchLLM reasoning → Knowledge- and tool-augmented reasoning +1
  2. LegoDiffusion: Micro-Serving Text-to-Image Diffusion WorkflowsDiffusion models → Diffusion foundations and sampling
  3. Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video GeneratorDiffusion models → Video generation
  4. Small Vision-Language Models are Smart Compressors for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  5. Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?LLM safety and security → Machine unlearning
  6. OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  7. Test-Oriented Programming: rethinking coding for the GenAI eraLLM reasoning → Reasoning for agents, planning and code
  8. DiffVC: A Non-autoregressive Framework Based on Diffusion Model for Video CaptioningDiffusion models → Video generation
  9. From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI OutputRetrieval-augmented generation → Hallucination detection in RAG
  10. AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  11. Multimodal Latent Reasoning via Predictive EmbeddingsLLM reasoning → Multimodal reasoning +1
  12. ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language ModelsLLM agents and tool use → Agent memory systems
  13. ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video CaptioningMultimodal LLMs / vision-language models → Video understanding with MLLMs
  14. Guiding a Diffusion Model by Swapping Its TokensDiffusion models → Diffusion foundations and sampling
  15. Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  16. Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  17. PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head GenerationDiffusion models → Robustness, privacy and adversarial aspects
  18. PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPCDeep reinforcement learning methods → RL theory and sample complexity
  19. Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous VehiclesEnd-to-end autonomous driving → Large language models for driving
  20. Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  21. Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  22. Preference Redirection via Attention Concentration: An Attack on Computer Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  23. Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMsLLM reasoning → Audio-language model reasoning
  24. HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA
  25. MotionScape: A Motion-Stratified UAV Video Benchmark for World Modeling and Future Video GenerationWorld models → World models for navigation
  26. LogAct: Enabling Agentic Reliability via Shared LogsLLM agents and tool use → Software engineering coding agents
  27. Predicting the Benefit of Retrieval Augmentation in Open-Domain Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  28. A Decomposition Perspective to Long-context Reasoning for LLMsLLM reasoning → Test-time compute and efficient thinking
  29. How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban AirspaceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  30. Lighting-grounded Video Generation with Renderer-based Agent ReasoningDiffusion models → Video generation
  31. Rethinking Data Mixing from the Perspective of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  32. Is your algorithm unlearning or untraining?LLM safety and security → Machine unlearning
  33. TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement LearningLLM agents and tool use → Multimodal and embodied agents
  34. WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World ModelsWorld models → World models for navigation +2
  35. Rethinking Residual Errors in Compensation-based LLM QuantizationLLM reasoning → Test-time compute and efficient thinking
  36. Incremental Residual Reinforcement Learning Toward Real-World Learning for Social NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  37. On-Policy Distillation of Language Models for Autonomous Vehicle Motion PlanningEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
  38. Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned DistributionsEfficient LLM inference and serving → Serving systems and request scheduling
  39. Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search SystemsLLM agents and tool use → GUI and mobile agents
  40. EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning ToolsLLM agents and tool use → Web, search, and research agents
  41. SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive ThinkingLLM reasoning → Test-time compute and efficient thinking
  42. Mitigating Entangled Steering in Large Vision-Language Models for Hallucination ReductionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  43. Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement LearningLLM agents and tool use → Software engineering coding agents
  45. Visual Perceptual to Conceptual First-Order Rule Learning NetworksLLM reasoning → Multimodal reasoning
  46. Linear Representations of Hierarchical Concepts in Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  47. An Agentic Evaluation Architecture for Historical Bias Detection in Educational TextbooksLLM agents and tool use → Social simulation and multi-agent debate
  48. FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent DecodingDiffusion models → Robustness, privacy and adversarial aspects
  49. Learning over Forward-Invariant Policy Classes: Reinforcement Learning without Safety ConcernsDeep reinforcement learning methods → Safe and constrained RL
  50. Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph MemoryLLM agents and tool use → Agent memory systems
  51. Networking-Aware Energy Efficiency in Agentic AI Inference: A SurveyLLM agents and tool use → Agentic AI for wireless networks
  52. ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuningLLM reasoning → LLM reasoning for recommendation
  53. We Need Strong Preconditions For Using Simulations In PolicyLLM agents and tool use → Social simulation and multi-agent debate
  54. Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation AblationLLM safety and security → Jailbreaking
  55. Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element InjectionLLM agents and tool use → Agent threats, guardrails and governance +2
  56. Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth TransformersLLM reasoning → Reasoning benchmarks and evaluation
  57. Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal GroundingLLM agents and tool use → Multimodal and embodied agents
  58. Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge ModelLLM agents and tool use → Tool learning and function calling
  59. AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse AttentionEfficient LLM inference and serving → KV cache optimization
  60. AgriChain Visually Grounded Expert Verified Reasoning for Interpretable Agricultural Vision Language ModelsLLM reasoning → Clinical and biomedical applications +1
  61. HAWK: Head Importance-Aware Visual Token Pruning in Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  62. Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  63. TEMPER: Testing Emotional Perturbation in Quantitative ReasoningLLM reasoning → Audio-language model reasoning
  64. Lightweight LLM Agent Memory with Small Language ModelsLLM agents and tool use → Agent memory systems
  65. SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  66. ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE AgentsLLM agents and tool use → Software engineering coding agents
  67. Automotive Engineering-Centric Agentic AI Workflow FrameworkLLM agents and tool use → Multimodal and embodied agents
  68. Structured Distillation of Web Agent Capabilities Enables GeneralizationLLM agents and tool use → Web, search, and research agents
  69. RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMsLLM agents and tool use → Multimodal and embodied agents
  70. DailyArt: Discovering Articulation from Single Static Images via Latent DynamicsWorld models → Embodied and robot world models
  71. The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-TrainingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  72. Symbiotic-MoE: Unlocking the Synergy between Generation and UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  73. The Cartesian Cut in Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  74. CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization VLLM agents and tool use → Reinforcement learning for LLM agents
  75. TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak DefenseLLM safety and security → Jailbreaking
  76. Towards Knowledgeable Deep Research: Framework and BenchmarkLLM agents and tool use → Web, search, and research agents
  77. Breaking the KV Cache Bottleneck: Fan Duality Model Achieves O(1) Decode Memory with Superior Associative RecallEfficient LLM inference and serving → KV cache optimization
  78. CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual DynamicsWorld models → World models for language agents
  79. Tree-of-Evidence: Efficient "System 2" Search for Faithful Multimodal GroundingMultimodal LLMs / vision-language models → Medical vision-language models
  80. Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class SystemLLM agents and tool use → Web, search, and research agents
  81. Reset-Free Reinforcement Learning for Real-World Agile Driving: An Empirical StudyEnd-to-end autonomous driving → Reinforcement learning for driving +1
  82. From Debate to Decision: Conformal Social Choice for Safe Multi-Agent DeliberationLLM reasoning → Reasoning for agents, planning and code +1
  83. Intelligent Three Level Learning Architecture for Autonomous UAV Swarms in Search and Rescue
  84. Interval Certifications for Multilayered Perceptrons via Lattice Traversal
  85. Imperfect Visual Verification for Code Edition : A Case Study on TikZ
  86. Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers
  87. A Relative-Computability Theory of Self-Improving Agents
  88. BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision
  89. Soro: A Lightweight Foundation Model and Chatbot for Tajik
  90. OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis
  91. Enhancing LLM Medical Coding with Structured External Knowledge
  92. Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models
  93. Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?
  94. Evaluating Large Language Models in a Complex Hidden Role Game
  95. Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems
  96. Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation
  97. Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection
  98. PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL
  99. Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding
  100. Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings
  101. Multi-Label Phase Diagram Prediction in Complex Alloys via Physics-Informed Graph Attention Networks
  102. GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
  103. Improving DNS Exfiltration Detection via Transformer Pretraining
  104. ExecTune: Effective Steering of Black-Box LLMs with Guide Models
  105. STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
  106. Unsupervised Local Plasticity in a Multi-Frequency VisNet Hierarchy
  107. Data-Driven Automated Identification of Optimal Feature-Representative Images in Infrared Thermography Using Statistical and Morphological Metrics
  108. SenBen: Sensitive Scene Graphs for Explainable Content Moderation
  109. Loom: A Scalable Analytical Neural Computer Architecture
  110. R2G: A Multi-View Circuit Graph Benchmark Suite from RTL to GDSII
  111. Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis
  112. Smartwatch-Based Sitting Time Estimation in Real-World Office Settings
  113. Policy-Aware Design of Large-Scale Factorial Experiments
  114. Scrapyard AI
  115. Alleviating Community Fear in Disasters via Multi-Agent Actor-Critic Reinforcement Learning
  116. p1: Better Prompt Optimization with Fewer Prompts
  117. Tracing the Chain: Deep Learning for Stepping-Stone Intrusion Detection
  118. MeshOn: Intersection-Free Mesh-to-Mesh Composition
  119. Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation
  120. MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
  121. PSIRNet: Deep Learning-based Free-breathing Rapid Acquisition Late Enhancement Imaging
  122. Adaptive Simulation Experiment for LLM Policy Optimization
  123. CERBERUS: A Three-Headed Decoder for Vertical Cloud Profiles
  124. Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
  125. Weak Adversarial Neural Pushforward Method for the Wigner Transport Equation
  126. InstrAct: Towards Action-Centric Understanding in Instructional Videos
  127. State Space Models are Effective Sign Language Learners: Exploiting Phonological Compositionality for Vocabulary-Scale Recognition
  128. Artifacts as Memory Beyond the Agent Boundary
  129. Accurate and Reliable Uncertainty Estimates for Deterministic Predictions Extensions to Under and Overpredictions
  130. IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing
  131. LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
  132. Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control
  133. A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
  134. AniGen: Unified S3 Fields for Animatable 3D Asset Generation
  135. Active Learning for Generalizable Detonation Performance Prediction of Energetic Materials
  136. Deterministic Adam-Inspired Methods with Accelerated Convergence Rate
  137. LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification
  138. RansomTrack: A Hybrid Behavioral Analysis Framework for Ransomware Detection
  139. Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning
  140. AI Driven Soccer Analysis Using Computer Vision
  141. Demystifying the Silence of Correctness Bugs in PyTorch Compiler
  142. Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring
  143. Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup
  144. Parameterized Complexity Of Representing Models Of MSO Formulas
  145. Efficient RL Training for LLMs with Experience Replay
  146. RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data
  147. QoS-QoE Translation with Large Language Model
  148. Unified Multimodal Uncertain Inference
  149. EvoLen: Evolution-Guided Tokenization for DNA Language Model
  150. EfficientSign: An Attention-Enhanced Lightweight Architecture for Indian Sign Language Recognition
  151. An Algorithm for Fast Assembling Large-Scale Defect-Free Atom Arrays
  152. Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States
  153. PRAGMA: Revolut Foundation Model
  154. High-dimensional inference for the γ-ray sky with differentiable programming
  155. Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
  156. On Semiotic-Grounded Interpretive Evaluation of Generative Art
  157. VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
  158. LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design
  159. Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
  160. WildDet3D: Scaling Promptable 3D Detection in the Wild
  161. Spectral-transport stability and benign overfitting for minimum norm interpolation
  162. Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing
  163. From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
  164. ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
  165. ETCH-X: Robustify Expressive Body Fitting to Clothed Humans with Composable Datasets
  166. GaussiAnimate: Rig Animatable Categories with Level of Dynamics
  167. SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
  168. E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation
  169. Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
  170. AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
  171. Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
  172. PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
  173. FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
  174. Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
  175. ClawBench: Can AI Agents Complete Everyday Online Tasks?
  176. UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
  177. Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
  178. When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations
  179. What do Language Models Learn and When? The Implicit Curriculum Hypothesis
  180. Visually-grounded Humanoid Agents
  181. Differentially Private Language Generation and Identification in the Limit
  182. Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
  183. Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
  184. sciwrite-lint: Verification Infrastructure for the Age of Science Vibe-Writing
  185. What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric
  186. The Impact of Dimensionality on the Stability of Node Embeddings
  187. Formalizing building-up constructions of self-dual codes through isotropic lines in Lean
  188. AI generates well-liked but templatic empathic responses
  189. LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation
  190. Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance
  191. Persistence-Augmented Neural Networks
  192. OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
  193. A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
  194. Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains
  195. AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages
  196. Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond
  197. HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment
  198. Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules
  199. Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM
  200. On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
  201. Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
  202. Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI
  203. What a Comfortable World: Ergonomic Principles Guided Apartment Layout Generation
  204. BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields
  205. SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
  206. Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
  207. Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks
  208. ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
  209. TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
  210. A GAN and LLM-Driven Data Augmentation Framework for Dynamic Linguistic Pattern Modeling in Chinese Sarcasm Detection
  211. SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
  212. SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization
  213. MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
  214. Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
  215. Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation
  216. ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
  217. Human-AI Collaboration Reconfigures Group Regulation from Socially Shared to Hybrid Co-Regulation
  218. EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment
  219. Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
  220. Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers
  221. Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
  222. Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization
  223. GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis
  224. U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
  225. CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models
  226. CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild
  227. Distributed Multi-Layer Editing for Rule-Level Knowledge in Large Language Models
  228. Revisiting Radar Perception With Spectral Point Clouds
  229. QARIMA: A Quantum Approach To Classical Time Series Analysis
  230. ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
  231. Floating or Suggesting Ideas? A Large-Scale Contrastive Analysis of Metaphorical and Literal Verb-Object Constructions
  232. Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
  233. Neural-Symbolic Knowledge Tracing: Injecting Educational Knowledge into Deep Learning for Responsible Learner Modelling
  234. DBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detection
  235. Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
  236. HyperMem: Hypergraph Memory for Long-Term Conversations
  237. From Phenomenological Fitting to Endogenous Deduction: A Paradigm Leap via Meta-Principle Physics Architecture
  238. Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges
  239. SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection
  240. OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
  241. Introducing Echo Networks for Computational Neuroevolution
  242. Approximation of the Basset force in the Maxey-Riley-Gatignol equations via universal differential equations
  243. Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
  244. AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
  245. Long-Term Embeddings for Balanced Personalization
  246. On the Global Photometric Alignment for Low-Level Vision
  247. OceanMAE: A Foundation Model for Ocean Remote Sensing
  248. T-Gated Adapter: A Lightweight Temporal Adapter for Vision-Language Medical Segmentation
  249. Shift- and stretch-invariant non-negative matrix factorization with an application to brain tissue delineation in emission tomography data
  250. Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection
  251. Training Data Size Sensitivity in Unsupervised Rhyme Recognition
  252. A Direct Approach for Handling Contextual Bandits with Latent State Dynamics
  253. Clickbait detection: quick inference with maximum impact
  254. Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
  255. Bag of Bags: Adaptive Visual Vocabularies for Genizah Join Image Retrieval
  256. Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs
  257. LLM-Based Data Generation and Clinical Skills Evaluation for Low-Resource French OSCEs
  258. PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction
  259. Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization
  260. A unifying view of contrastive learning, importance sampling, and bridge sampling for energy-based models
  261. Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
  262. TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems
  263. EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition
  264. Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection
  265. Coordinate-Based Dual-Constrained Autoregressive Motion Generation
  266. DeepForestSound: a multi-species automatic detector for passive acoustic monitoring in African tropical forests, a case study in Kibale National Park
  267. AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
  268. Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
  269. DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather
  270. Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels
  271. Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning
  272. EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience
  273. From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants
  274. Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with a Proof-of-Concept Evaluation on Embodied Agents
  275. Automating aggregation strategy selection in federated learning
  276. Efficient Provably Secure Linguistic Steganography via Range Coding
  277. Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images
  278. 3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience
  279. LINE: LLM-based Iterative Neuron Explanations for Vision Models
  280. Rotation Equivariant Convolutions in Deformable Registration of Brain MRI
  281. IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
  282. "Why This Avoidance Maneuver?" Contrastive Explanations in Human-Supervised Maritime Autonomous Navigation
  283. From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse
  284. Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI
  285. SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Driving
  286. Evaluating Counterfactual Explanation Methods on Incomplete Inputs
  287. The ecosystem of machine learning competitions: Platforms, participants, and their impact on AI development
  288. PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
  289. Benchmarking Deep Learning for Future Liver Remnant Segmentation in Colorectal Liver Metastasis
  290. Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
  291. SAT: Selective Aggregation Transformer for Image Super-Resolution
  292. SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
  293. Show Me the Infographic I Imagine: Intent-Aware Infographic Retrieval for Authoring Support
  294. DP-DeGauss: Dynamic Probabilistic Gaussian Decomposition for Egocentric 4D Scene Reconstruction
  295. Object-Centric Stereo Ranging for Autonomous Driving: From Dense Disparity to Census-Based Template Matching
  296. Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention
  297. AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
  298. DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
  299. Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction
  300. ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
  301. MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
  302. Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification
  303. Fraud Detection System for Banking Transactions
  304. Investigation of Automated Design of Quantum Circuits for Imaginary Time Evolution Methods Using Deep Reinforcement Learning
  305. Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
  306. A Systematic Framework for Tabular Data Disentanglement
  307. HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy
  308. Shortcut Learning in Glomerular AI: Adversarial Penalties Hurt, Entropy Helps
  309. Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting
  310. Sinkhorn doubly stochastic attention rank decay analysis
  311. Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolation
  312. Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation
  313. Unified Precision-Guaranteed Stopping Rules for Contextual Learning
  314. ParkSense: Where Should a Delivery Driver Park? Leveraging Idle AV Compute and Vision-Language Models
  315. Capture-Quiet Decomposition: A Verification Theorem for Chess Endgame Tablebases
  316. Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency
  317. PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation
  318. Non-variational supervised quantum kernel methods: a review
  319. DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
  320. TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
  321. Data Selection for Multi-turn Dialogue Instruction Tuning
  322. Sampling-Aware 3D Spatial Analysis in Multiplexed Imaging
  323. Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
  324. Contextualising (Im)plausible Events Triggers Figurative Language
  325. Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
  326. ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
  327. MemReader: From Passive to Active Extraction for Long-Term Agent Memory
  328. PyVRP^+: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems
  329. Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems
  330. Hidden Biases in Conditioning Autoregressive Models
  331. QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
  332. Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
  333. SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
  334. Why Are We Lonely? Leveraging LLMs to Measure and Understand Loneliness in Caregivers and Non-caregivers
  335. Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
  336. LPM 1.0: Video-based Character Performance Model
  337. More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
  338. Automatic Generation of Executable BPMN Models from Medical Guidelines
  339. Agentivism: a learning theory for the age of artificial intelligence
  340. Intensity Dot Product Graphs
  341. PolicyLong: Towards On-Policy Context Extension
  342. GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning
  343. The Weaponization of Computer Vision: Tracing Military-Surveillance Ties through Conference Sponsorship
  344. Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems
  345. Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes
  346. Image-Guided Geometric Stylization of 3D Meshes
  347. PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context
  348. Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
  349. Toward Generalizable Graph Learning for 3D Engineering AI: Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction
  350. MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
  351. Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models
  352. The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives
  353. ACIArena: Toward Unified Evaluation for Agent Cascading Injection
  354. RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
  355. ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions
  356. Sensitivity-Positional Co-Localization in GQA Transformers
  357. Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
  358. Generative optimal transport via forward-backward HJB matching
  359. WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects
  360. An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations
  361. MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models
  362. Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models
  363. Sparse ε insensitive zone bounded asymmetric elastic net support vector machines for pattern classification
  364. Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
  365. Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU)
  366. The Condition-Number Principle for Prototype Clustering
  367. MSCT: Differential Cross-Modal Attention for Deepfake Detection
  368. Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification
  369. Efficient Dataset Selection for Continual Adaptation of Generative Recommenders
  370. SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
  371. Emotion Concepts and their Function in a Large Language Model
  372. GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting
  373. Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
  374. Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
  375. Needle in a Haystack: One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology
  376. Detecting HIV-Related Stigma in Clinical Narratives Using Large Language Models
  377. Mathematical analysis of one-layer neural network with fixed biases, a new activation function and other observations
  378. IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models
  379. AITH: A Post-Quantum Continuous Delegation Protocol for Human-AI Trust Establishment
  380. Joint Task Offloading, Inference Optimization and UAV Trajectory Planning for Generative AI Empowered Intelligent Transportation Digital Twin
  381. Tensor-based computation of the Koopman generator via operator logarithm
  382. Towards Counterfactual Explanation and Assertion Inference for CPS Debugging
  383. FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction
  384. Weight Group-wise Post-Training Quantization for Medical Foundation Model
  385. On the Unique Recovery of Transport Maps and Vector Fields from Finite Measure-Valued Data
  386. LLM-Guided Dynamic Action Spaces for Synthesizable Molecular Optimization
  387. An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
  388. Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation
  389. Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach
  390. SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
  391. Parameter-Free Non-Ergodic Extragradient Algorithms for Solving Monotone Variational Inequalities