mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 5 Aug 2026

474 papers

  1. Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  2. AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative InvestmentLLM agents and tool use → Financial trading and forecasting agents +1
  3. CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic ScienceLLM agents and tool use → Web, search, and research agents
  4. Runtime Action Interference for AI Control of AlphaStar in StarCraft IIDeep reinforcement learning methods → RL for games and combinatorial optimization
  5. Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-TrainingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  6. Rethinking Reverse KL as Adaptive Entropy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  7. Mitigating Rubric Interference in LLM Judges via On-Policy Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  8. Weather- and Location-Aware Agentic Dining Recommendation: Leveraging LLM World Knowledge for Region-Sensitive Contextual ReasoningLLM reasoning → LLM reasoning for recommendation
  9. ComplexityWorld: Benchmarking Vision-Language Models on Verifiable Visual Decision MakingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not EnoughLLM agents and tool use → Agent threats, guardrails and governance
  11. Multi-Branch Policy Optimization for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  12. Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language ModelsMechanistic interpretability → Interpreting biomedical and science models
  13. Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and EditingDiffusion models → Audio, speech and music
  14. WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model WatermarkingLLM safety and security → Watermarking generated content and models
  15. MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient GenerationDiffusion models → Diffusion foundations and sampling
  16. DBLAST: Dependent Block Drafting for Stochastic Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  17. EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM AgentsLLM agents and tool use → Software engineering coding agents +1
  18. Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio EffectsDiffusion models → Audio, speech and music
  19. Robust Context-Aware Detection of Malicious Instructions in TextLLM safety and security → Prompt injection and agent security
  20. IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information GamesDeep reinforcement learning methods → RL with diffusion and flow models
  21. Mood Matters: How Syntactic Sensitivity Undermines Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  22. Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation ModelMultimodal LLMs / vision-language models → Medical vision-language models
  23. C3PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  24. DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal dataLLM agents and tool use → Medical and scientific domain agents
  25. Quantum-Structured World Models (QSWMs) for Predictive Latent DynamicsWorld models → Latent predictive world models
  26. World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot ManipulationVision-language-action models → Tactile, force-aware and humanoid VLA
  27. Positive-Unlabeled Preference Optimization For Chest X-ray Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models +1
  28. Hierarchical Server Architecture for Agentic ScienceLLM agents and tool use → Software engineering coding agents
  29. EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative DecodingMixture-of-experts → Efficient MoE training and inference systems +1
  30. Agentic self-driving microscopy benchmarks support qualification but do not necessarily generalize to unseen tasksLLM agents and tool use → Medical and scientific domain agents
  31. A Paragraph is Worth a Thousand Captions: Rethinking Text Supervision for Vision-Language RetrievalLLM reasoning → Multimodal reasoning +1
  32. An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language GoalsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  33. Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem SolvingLLM reasoning → Mathematical reasoning
  34. PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data SynthesisSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  35. WorldClaw: Agentic 3D Open-World Generation at ScaleLLM agents and tool use → Multimodal and embodied agents
  36. Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement LearningLLM agents and tool use → Agent skill learning and evolution +1
  37. Disentangling 3D Modeling from Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  38. In-Context Forcing: Uncovering Context Effects in Autoregressive Video DiffusionDiffusion models → Video generation
  39. From Trajectories to Evidence: Auditable Experimental Records for Industrial Research AgentsLLM agents and tool use → Agent threats, guardrails and governance
  40. Project2Task: Graph-Guided Project-Level Planning for Autonomous ResearchLLM agents and tool use → Web, search, and research agents
  41. Towards a Risk Assessment of Malicious Skill Files in Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
  42. Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion ModelDiffusion models → Audio, speech and music
  43. When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn AgentsKnowledge distillation → On-policy and self-distillation for LLMs
  44. A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive OptimizationEfficient LLM inference and serving → Token pruning and merging for ViTs
  45. SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search AgentsLLM agents and tool use → Web, search, and research agents
  46. When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box ForecastersLLM agents and tool use → Financial trading and forecasting agents
  47. SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill ReuseLLM agents and tool use → Agent skill learning and evolution
  48. Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  49. OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context ModelingLLM agents and tool use → Software engineering coding agents
  50. Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon ReasoningLLM reasoning → Test-time compute and efficient thinking
  51. Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist DomainsRetrieval-augmented generation → Generation and context integration
  52. OPD-V: Visual On-Policy Self-Distillation with Modality BalanceLLM reasoning → Multimodal reasoning +2
  53. Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  54. Chained Recursive Language Models for Multi-Iteration ReasoningLLM reasoning → Test-time compute and efficient thinking
  55. Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  56. Agent Against Agent: An Agentic System for Automatic Prompt Injection Red TeamingLLM agents and tool use → Agent threats, guardrails and governance +1
  57. Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matchingDiffusion models → Flow matching, time series and science
  58. Hierarchical Graph Memory for LLM Agents with Path-level Localization and RewriteLLM agents and tool use → Agent memory systems
  59. Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous ControlDiffusion models → Diffusion and flow policies for robotics
  60. HelloWorld: Enabling Socially Interactive Characters in Video World ModelsWorld models → Video-generation world models and simulators
  61. Exact Model-Free Policy Iteration for Co-safe LTL PlanningDeep reinforcement learning methods → Interpretable and logic-guided RL
  62. Gradient Immunity: Null-Space Resistance to Malicious Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  63. BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  64. Private Direct Preference Optimization for LLM AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  65. ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI AugmentationLLM agents and tool use → Multimodal and embodied agents
  66. DreamWAM: Beyond RGB Future Prediction for World Action ModelsWorld models → Embodied and robot world models
  67. Protoreasoning in Tiny TransformersLLM reasoning → Prompting and chain-of-thought reasoning
  68. AsymSpec: Efficient Cloud-Edge Speculative Decoding over Asymmetric NetworksEfficient LLM inference and serving → Early exit and edge inference
  69. EvolveNet: Collaborative Harness Evolution for Agent Self-ImprovementLLM agents and tool use → Software engineering coding agents +1
  70. WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World ModelsWorld models → Latent dynamics models and model-based RL +1
  71. SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning RolloutsLLM reasoning → Reinforcement learning for reasoning
  72. Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  73. State2State: Environment-Derived Mid-Training for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  74. Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?LLM reasoning → Prompting and chain-of-thought reasoning
  75. AutoCue: Multimodal LLM-Assisted Externalization of Implicit Inputs as Instructional Visual Cues in Screencast TutorialsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  76. Enhancing Low Back Pain Assessment with Diffusion Models for Lumbar Spine MRI SegmentationDiffusion models → Medical imaging and segmentation
  77. Strengthening Target-Language Features: SAE-Based Steering for Multilingual InferenceMechanistic interpretability → SAE features and their applications
  78. When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  79. STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  80. Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual PerturbationsMultimodal LLMs / vision-language models → Medical vision-language models
  81. A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical CoordinationLLM agents and tool use → Web, search, and research agents +1
  82. MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-offLLM agents and tool use → Agent memory systems
  83. Towards a satellite image manipulation and deepfake localization benchmark datasetDiffusion models → Image generation, text-to-image and editing
  84. Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?LLM agents and tool use → Agent skill learning and evolution
  85. Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown ManifoldsDiffusion models → Diffusion foundations and sampling
  86. When Diffusion Models Forget Who You Are: Identity Preservation in Face Inpainting under Large OcclusionsDiffusion models → Image generation, text-to-image and editing
  87. Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository FirstLLM agents and tool use → Software engineering coding agents
  88. Reference-Based Manipulation: A Framework and Pipeline for Multimodal Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  89. Privileged, but Biased: How PI-Conditioned Teachers Break Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  90. Agentic Reinforcement Learning with Observation-Calibrated Self-DistillationLLM agents and tool use → Reinforcement learning for LLM agents +1
  91. Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  92. Embedding Large Language Models into Flow Controls: An Agentic Framework for Adaptive and Trustworthy Automated CookingLLM agents and tool use → General LLM agent frameworks and benchmarks
  93. Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  94. InsightEmb: Learning Action-Intent Embeddings for Agentic Insight RetrievalLLM agents and tool use → Web, search, and research agents +1
  95. Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMsLLM reasoning → Spatial and embodied reasoning +1
  96. PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded UpdatesRetrieval-augmented generation → Privacy and security of RAG
  97. "Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents
  98. Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory SystemsLLM agents and tool use → Agent memory systems
  99. LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  100. EviGraph: Evidence-Guided Autonomous Research AgentsLLM agents and tool use → Web, search, and research agents
All 474
  1. Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence SettingsLLM reasoning → Prompting and chain-of-thought reasoning
  2. Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal ControlDeep reinforcement learning methods → Safe and constrained RL
  3. When Prompts Become Pixels: Prompt-Region Grounding for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  4. Diagnosing Tool-Selection Reasoning in LLM Agents with Canary ToolsLLM reasoning → Reasoning for agents, planning and code +1
  5. EmpaAva: An Open-source Agentic 3D-Avatar Empathetic Live ChatbotLLM agents and tool use → Multimodal and embodied agents
  6. UniWorld-View: Large-Baseline View Synthesis via Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  7. Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPOLLM reasoning → Reinforcement learning for reasoning
  8. Personalized Federated Sparse Adaptation of Time-Series Foundation ModelsMixture-of-experts → MoE for time series and graphs
  9. Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA PoliciesVision-language-action models → Failure recovery and robustness
  10. Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue ReportsLLM agents and tool use → Software engineering coding agents
  11. Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT BenchmarkLLM reasoning → Reasoning benchmarks and evaluation
  12. An Exploratory Study of Agent Plans for Agentic AI Coding Tools in Open-Source SoftwareLLM agents and tool use → Software engineering coding agents
  13. MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-ForesightWorld models → Embodied and robot world models
  14. Overcoming Statistical Bias in Action-Controllable World ModelsWorld models → Embodied and robot world models
  15. Evaluating Theory of Mind in Reasoning Models: Robustness over ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  16. HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MASLLM agents and tool use → General LLM agent frameworks and benchmarks
  17. Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
  18. Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future DirectionsLLM agents and tool use → Agent threats, guardrails and governance
  19. Masked diffusion enables coherent beat trackingDiffusion models → Audio, speech and music
  20. HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene UnderstandingLLM reasoning → Spatial and embodied reasoning +2
  21. Adaptive Intrusion Detection System using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial InvestigationLLM safety and security → Backdoor and data poisoning attacks
  22. When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  23. Joint UAV Flight and Opportunistic Routing under Reinforcement Learning for Delay-Tolerant NetworksDeep reinforcement learning methods → RL for robot navigation and UAV control
  24. The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. EASy: Towards Efficient LLM-Based Agentic SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech EncodersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  27. PhysMind: From Video to Executable Worlds for Training-Free Physical ReasoningLLM reasoning → Spatial and embodied reasoning
  28. When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM AgentsLLM agents and tool use → Agent memory systems
  29. Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
  30. STRIVE: Probing Reasoning Limits in Graded Plausibility Generation and EvaluationLLM reasoning → Reasoning benchmarks and evaluation
  31. Breadcrumbing Search AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  32. VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI SynthesisDiffusion models → Medical imaging and segmentation
  33. A Model Merging Approach for Continual MLLM UnlearningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  34. Discretization and Statistical Consistency of Functional Flow MatchingDiffusion models → Flow matching, time series and science
  35. FocusMem: Factorizing Content, Readout, and Trust in Latent GUI MemoryLLM agents and tool use → GUI and mobile agents
  36. Retrieve in Time, Correct in FrequencyVision-language-action models → Reasoning and chain-of-thought in VLA
  37. Coupled Continuous-Discrete Generation for Scene Text Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  38. ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient ResistanceLLM reasoning → Clinical and biomedical applications
  39. Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery RobustnessLLM reasoning → Reasoning for agents, planning and code +1
  40. CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume UnderstandingEfficient LLM inference and serving → Visual token pruning in multimodal models
  41. GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAsVision-language-action models → Failure recovery and robustness
  42. CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  43. Emergence of Reputation-Based Cooperation in LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
  44. K-EXAONE 2.0 Technical ReportMixture-of-experts → MoE large language models
  45. GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference PredictionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  46. AFD-Ledger: Deployment Provisioning for Attention--FFN DisaggregationMixture-of-experts → Efficient MoE training and inference systems
  47. DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  48. Not All Redundant Tokens Are Alike: Analyzing Visual Token Pruning through Token RolesMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  49. Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill RetrievalLLM agents and tool use → Agent skill learning and evolution
  50. EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive AlignmentMultimodal LLMs / vision-language models → Medical vision-language models
  51. AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code AdaptationLLM reasoning → Reasoning for agents, planning and code +1
  52. Architectural Implications of Agentic AI WorkflowsLLM agents and tool use → Software engineering coding agents
  53. Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  54. Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  55. When does training on downscaled images yield the same gradients?Diffusion models → Diffusion foundations and sampling
  56. D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
  57. ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image GenerationLLM agents and tool use → Multimodal and embodied agents
  58. Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative InferenceVision-language-action models → Efficient VLA inference and adaptation +1
  59. SPOT: Sparse Probing and Outcome Calibration for On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  60. Social Pressure Breaks Majority Voting in LLM Safety PanelsLLM safety and security → Safety alignment, refusal and guardrails
  61. muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road HazardsWorld models → World models for autonomous driving +1
  62. Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  63. MESH: Memory-Efficient Sinkhorn Optimization for Mixture-of-Experts TrainingMixture-of-experts → Efficient MoE training and inference systems
  64. Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action ModelsWorld models → Embodied and robot world models
  65. Elbow-Based MoE Routing: A Training-Free Inference Time Plugin for Expert SelectionLLM reasoning → Test-time compute and efficient thinking +1
  66. CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual InterventionVision-language-action models → Failure recovery and robustness
  67. Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object DetectionDiffusion models → Image generation, text-to-image and editing
  68. ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-ExaminationLLM reasoning → Multimodal reasoning +1
  69. Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and GenerationWorld models → Video-generation world models and simulators
  70. Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG FrameworkRetrieval-augmented generation → Privacy and security of RAG +1
  71. Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  72. Continuous Improvement and Parallel Autonomous Exploration: An LLM-Agent Framework for Searching Large Solution SpacesLLM agents and tool use → Web, search, and research agents
  73. ATLAS: Adaptive Topological Learning with Abstract Successors for Continual LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  74. Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)LLM agents and tool use → Agent threats, guardrails and governance
  75. Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic EmbeddingsLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. Structured LLM Reasoning for Zero-Shot Human--Robot Coordination Under Hidden GoalsLLM reasoning → Spatial and embodied reasoning
  77. Adaptive Finite-Budget Training for CVaR Risk-Aware Q-LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  78. MIAR: Medical Image Super-Resolution With Autoregressive Modeling
  79. Leakage-Safe Empirical Benchmarking of EEG-Based Machine Learning Pipelines for Dementia Classification
  80. Reading Less While Writing: A Closed-Form Bandwidth Dial for Streaming Multimodal Decoders
  81. Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
  82. Condition aware learning enables robust prediction of oligonucleotide melting behavior across diverse chemistries and assay conditions
  83. Whose Judgments Count? Representation Gaps in Crowdsourced Content Moderation Produce Unequal Protection from Perceived Toxicity
  84. Federated Ensemble Forecasting Under Supply-Chain Market Volatility
  85. Mitigating Spectral Bias in Neural Operators for Underwater Transmission Loss Prediction
  86. DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization
  87. SW-ProxyCE: Zero-Query Adversarial Transfer from Public EEG Encoders to Private Downstream Models
  88. EMAN: Optimization-Driven Capacity Growth through Path Emergence in Multi-Task Learning
  89. Mr.Dec: Daily-Scale Longitudinal Multimodal Modeling for 30-Day Readmission Prediction
  90. Benchmarking Classical and Transformer-Based Models for Document Sensitivity Classification
  91. Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training
  92. One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail
  93. RouteTS: Frequency-Time Routing for Time Series Forecasting
  94. Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans
  95. Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
  96. Distribution-Free Conformal Prediction for Steel Fatigue Strength: Marginal Validity Is Not Enough
  97. MAGIC-SSCIL: Manifold Anchoring and Geometric Incremental Calibration for Semi-Supervised Class Incremental Learning
  98. LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents
  99. Predictive Failure Detection in Network Hardware Using Thermal Imaging and Deep Learning with Sensor Fusion
  100. MiGHT-EHR: A Multi-task Graph Transformer for Heterogeneous Temporal Electronic Health Records
  101. Fixed and Adaptive Topological DeepONets: Functional Measurements on Hausdorff Locally Convex Spaces
  102. Adversarial Causal Intervention Falsification
  103. NTDH: Complex Reasoning for Comprehensive Affective Analysis
  104. Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
  105. Risk-Aware Decision Policies for Agents Under Noisy Perception
  106. Certified Feedforward Tracking for Unknown Nonlinear Systems via Invertible Neural Networks
  107. Latent Fact-Checking: Detecting Misinformation through Activation Engineering
  108. GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers
  109. KV-Skill: Forging Expertise in the Model's Native Language
  110. Matrix Zonotopic Attention: A Context-Adaptive Value Projection for Set Transformers
  111. A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets
  112. Recursive Synthesis for Long-Horizon Terminal Tasks
  113. Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling
  114. A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Lojasiewicz condition
  115. Stochasticity Is Not the Hard Part: Reduction and Complexity in Instructional Sequencing over Prerequisite DAGs
  116. Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
  117. Example-Guided Prompting for Document-Level Text Simplification
  118. SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications
  119. Discrete energy as an exact label-free training objective for finite-element surrogates
  120. The ethics of artificial intelligence in the life sciences: Universality, cultural diversity and an architecture of care
  121. Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes
  122. Invisible Shortcuts: Why Vision Encoders Know Your Camera
  123. Why the Third Axis Is Freedom
  124. Can Open-Weight LLMs Produce Kernel-Verified Coq Proofs? A Pilot Study
  125. Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples
  126. Negotiating Risk Boundaries in AI for Policing Through Mixed-Stakeholder Deliberation
  127. Spectral Distillation: From Nonlinear Dynamics to Linear State-Space Models
  128. Evaluating and Improving Pedagogical Fit in LLM-Based AI Tutors with the Pedagogical Suitability Index
  129. Adapting Vision Foundation Models with Cascaded Semantics
  130. Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordination
  131. Velocity- and Regime-Aware Detection of Intraday Options Market Manipulation, with Explainable Attribution
  132. Counterfactual Analysis via Large Language Models
  133. The interface of intonation and lexical tone: Boundary phenomena in Mandarin varieties
  134. CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction
  135. DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting
  136. LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection
  137. Evidence Lock Before Commitment: A Frozen Interface Degrades LLM-as-Judge Evaluation
  138. Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application
  139. Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks
  140. Physics-Based Molecular Fingerprints from Spectral Graph Theory Provide Efficient Geometry-Aware Measures of Chemical Similarity
  141. Context Matters: Support Set Selection and Failure Detection for In-Context Medical Image Segmentation
  142. Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening
  143. QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding
  144. Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG
  145. Failing Gracefully: Mitigating Impact of Inevitable Robot Failures
  146. Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
  147. OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality
  148. IMMENSE: Inductive Multi-perspective User Classification in Social Networks
  149. Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI
  150. Posture and Sustainment Optimization Under Adversarial Uncertainty
  151. Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning
  152. Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning
  153. LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs
  154. A Unified Causal Inference Framework for the Desirability of Outcome Ranking Paradigm in Benefit-Risk Evaluation
  155. Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
  156. One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization
  157. Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
  158. PPDL: LLM-Based Flows as Probabilistic Programs
  159. Coherence-Oriented Dream Scene Visualisation
  160. Analysis of Numerical Localisation in LLM Translations
  161. Quality Diversity for Reliable Data Driven Time-Use Optimization
  162. TriQua: Reconciling Granularity and Context in Factuality Evaluation
  163. NeuroAdaptTrainer: A Fiji/ImageJ Plugin for YOLO-Based Neuron Segmentation, InteractiveCorrection and Transfer Learning
  164. Small Foundation Models of Human Cognition and Behaviour
  165. PD-GS: Phoneme-Driven 3DGS for Audio-Driven Talking Heads
  166. VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances
  167. StyleComposer: Training-Free Multi-Reference Style Composition
  168. Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation
  169. MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction
  170. Otter: A Time-Aware, History-Conditioned Human Chess AI
  171. Abstract Event Causal Rules: Induction and Application
  172. From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction
  173. ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study
  174. CoCo-IR: Contextual Composed Image Retrieval
  175. Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training
  176. Objects as Audio-Visual Modal Sound Fields
  177. SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
  178. The Loss Does Not See the Basis, but Adam Does
  179. Predicting Brain Morphometry with MT-GNN: Mesh Evolution in Continuous Time with Graph-Based Metric Tensor Embeddings
  180. SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
  181. IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers
  182. DASyR-LLM: Domain-Aware Symbolic Regression with LLMs for Kinetic Model Discovery
  183. Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
  184. Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift
  185. Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth
  186. CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
  187. BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning
  188. ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
  189. HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes
  190. Lesion Detection in CT with Frozen Self-Distilled Features: SALT, a Spatially Adaptive Label-Guided Temperature
  191. Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?
  192. MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning
  193. Item Response Theory for AI Safety
  194. Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
  195. Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
  196. MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
  197. German parties shifted towards intuition-based rhetoric after the far right's parliamentary breakthrough
  198. Bag-of-Visual-Words for Spatial Mapping of Lung Adenocarcinoma Growth Patterns
  199. VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detection
  200. Beyond Reprojection Error: Camera Calibration with 3D Targets
  201. Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
  202. Hardware Design and Security in the Era of Chiplets and LLMs
  203. RepairFormer: Automated Repair of Structured Inputs Using Transformers
  204. MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres
  205. The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
  206. OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing
  207. SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUs
  208. From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking
  209. Language Models Generalize to Human-like Word Order Preferences
  210. Comparing SGLD and a fixed-noise predictor-corrector adaptation in canonical joint energy-based models on CIFAR-10
  211. Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
  212. Algorithm-Driven SVARs: Navigating the Wilderness of Big Data
  213. Link prediction on multi-relational graphs from an influence propagation perspective
  214. Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems
  215. Stochastic Emulation using Generalized Stratified Sampling for Performance-Based Risk Optimization of Structures
  216. DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
  217. Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes
  218. ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
  219. Promptable Animal Pose Tracking Across Species
  220. SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models
  221. ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing
  222. Towards Valid B-Rep Generation: Training-Free Wireframe Anomaly Detection and Repair
  223. UG-UMRE: Uncertainty-Guided Modality Augmentation and Distributional Calibration for Unified Multimodal Relation Extraction
  224. A General Sufficient Condition for Rewriting Horn-ALCHI Atomic Queries into GQL
  225. A geometry-based deep equilibrium model for image restoration under multiplicative Gamma noise
  226. CheMLFlow: An Open-Source Platform for Cheminformatics and Materials Informatics Applications
  227. Reading Between the Frames of Multimodal Drivelology
  228. SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery
  229. Optimal Training-Time Scaling in Gradual Adaptation
  230. Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
  231. A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI
  232. An active-learning framework for real-time depth perception from monocular vision streams
  233. Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation
  234. Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classification
  235. When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
  236. Variational Bounds for Perceptron Learning from Structured Data
  237. Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision
  238. Preverbal Uninflected and Underived Roots in Mapudungun. Wuno and Its Implications
  239. Persistent Object Narratives for Token-Efficient Video Language Models
  240. Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen
  241. The Neural Echo: A Signal Processing Perspective for Understanding Neural Networks
  242. Nonparametric Goodness-of-fit Testing under Covariate Shift
  243. Do Language Models Know Their Slang? Queer Slang Understanding in User-Generated Content
  244. RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection
  245. Robust Control under Stationary Ambiguity
  246. ContextWeave: A Real-World Workflow Benchmark
  247. Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator
  248. Rethinking Pixel Mean Flows via Interval Denoiser
  249. StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning
  250. Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading
  251. A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy
  252. MGSB: Manifold Gated Signature Branch Pressure-Domain Baseline Architecture for Two-Phase Pipeline Flows Under Distributional Shift
  253. Multi-Modal, Multi-Temporal Geospatial Foundation Models Improve Global Above-Ground Biomass Estimation
  254. On the Effectiveness of Adaptation Strategies for VLM-Based Federated Learning in Remote Sensing
  255. Reachability in 3-VAS
  256. RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
  257. Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations
  258. IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
  259. NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
  260. Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
  261. FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening
  262. Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling
  263. Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection
  264. Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction
  265. Simile Understanding in Text-to-Image Models: An Evaluation Framework
  266. Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
  267. A GitOps-Driven Annotation Catalog for Fully Automatic Railway Operations
  268. Multi-View Face and Gesture Animation with Dynamic Gaussians
  269. YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
  270. What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend
  271. A 6G Integrated Sensing and Communication Framework for Railway Intrusion Detection and Collision Prediction
  272. Benchmarking Deep Learning Models for Dense Event Classification of Offshore Wind Infrastructure in Sentinel-1 Time Series
  273. A Multi-Sensor Dataset for Monitoring the Operational Environment of Rail Vehicles
  274. IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)
  275. Design Choices That Matter: A Functional ANOVA Analysis for Remote Sensing Multi-Label Classification
  276. Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
  277. The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
  278. MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs
  279. Kathleen Writes: Autoregressive Generation and Data Scaling Without Attention
  280. Diverse and Plausible Algorithmic Recourse via Tractable Recourse Distributions
  281. SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding
  282. Differential 6-DOF Pose Estimation with Provable First-Order Immunity to Camera Calibration Errors
  283. Differentiating Through Dual Prices: End-to-End Policy Learning Under Capacity Constraints
  284. Automatic Statistical Test for Rationally Expressible Algorithms by Selective Inference, with Applications to Feature Selection
  285. Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning
  286. CSGen: A Multi-Domain Curvilinear Structure Generation Model via Hierarchical Multimodal Diffusion
  287. DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
  288. Active Learning Guided Design Space Refinement for Scalable Multi-Objective Bayesian Optimization in Materials Discovery
  289. YOLO-PVC: 2D-to-3D Consolidation of Slice-wise Detections for Volumetric Liver Tumor Localization in MRI
  290. AI Literacy for Legal Translation: Developing Digital Resilience
  291. A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
  292. Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition
  293. DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generation
  294. Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination
  295. An entropic explanation of insistence on sameness in autism
  296. Why Ranking Anomaly Detection Algorithms Isn't as Reliable as You May Think
  297. The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals
  298. On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations
  299. TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition
  300. COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation
  301. Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
  302. MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
  303. ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields
  304. Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study
  305. The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
  306. Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching
  307. What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
  308. OutLangSplat: 3D Language Gaussian Splatting for UAV Outdoor Scenes
  309. ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detection
  310. Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling
  311. Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery
  312. EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks
  313. Learning Compression Rules for Network Traffic
  314. EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation
  315. RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care
  316. Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs
  317. Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs
  318. REZE: Recognition-Based Zero-Shot Extraction for Video Temporal Grounding
  319. AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation
  320. DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
  321. Local Violation Certification for Linear Predict-Then-Optimize Pipelines
  322. Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecasting
  323. The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity
  324. CLEARMIND: Closed-Form Laplacian Embeddings of Arakelov-Green Resistance for Morphological Intrinsic Neuronal Distances
  325. Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning
  326. Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting
  327. TwinIR: Coordinated Invisible Dual-Point Attacks on Online HD Map Construction
  328. A Counterexample to Fourier Alignment in Single-Neuron Modular Addition
  329. Robustness Emerges Early in Training Dynamics, but Is Not Preserved
  330. Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks
  331. ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation
  332. OmniRouting: A Semantic-Coupled Multimodal Benchmark for Constraint-Aware Spatial Reasoning in PCB Routing
  333. MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages
  334. The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
  335. An adaptive split-combine Gaussian mixture filter for nonlinear and multimodal state estimation
  336. UBLLIE: Unified Backlight and Low-Light Image Enhancement
  337. Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes
  338. Thinking with Anchors: Grounded and Efficient Document Reasoning
  339. Foreseeing the Invisible: Amodal Reconstruction of Leaf Fossil Images
  340. Generative Optimization for Incentivized Advertising with Global Level Constraints
  341. Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation
  342. Training-Free Hashing-Based Attention via Binary Principal Components
  343. Approximate Multi-Objective Search Under Rulebooks
  344. NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap
  345. When Proxy Prediction Becomes Equation Reconstruction: Diagnostics and Residual Learning for Factor-Derived Proxy Supervision
  346. EdgeLM: Edge Demonstrations for Language Models' Table Understanding
  347. NeuroPB: Scaling Neural Decoding with Pretrained Behavioral Representations
  348. Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
  349. Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics
  350. NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
  351. Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features
  352. Towards Trustworthy Hypergraph Neural Networks under Label Noise
  353. FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation
  354. EvtGraph: Event-Adaptive Compression for Sparse Temporal Graph Learning in Multimodal Time Series
  355. Manipulation-Proof Oblivious Audits against Deceptive Model Providers
  356. NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
  357. The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale
  358. HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models
  359. iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data
  360. Introspecting Alignment Shifts Beyond Behaviors Implanted Through Fine-Tuning
  361. Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO
  362. COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
  363. Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation
  364. Right Reset: Chunking by Prefix Removal
  365. An Analysis and Implementation of Seam Carving for Content-Aware Image Resizing
  366. Real-time probabilistic tsunami forecasting via generative AI
  367. Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits
  368. DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning
  369. Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
  370. Achieving First-Order Statistical Improvements in Data-Driven Optimization: From No-Free-Lunch to Amplified Decision Perturbation
  371. ArborEnum: Decision Tree Rashomon Sets over Continuous Features
  372. MIDAS: Multi-LLM Iterative Data-Adaptive Summarization
  373. CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
  374. Searching for Sound-Meaning Collisions: Graph-Based Affordance Retrieval and Multi-Evaluator Ranking for Pun Translation at CLEF 2026 JOKER Task 2