mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 1 Sep 2026

564 papers

  1. Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal ResearchLLM agents and tool use → Social simulation and multi-agent debate
  2. Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. Don't Just Look, Intervene: Perturbation Based Region Labeling for VQA ImagesLLM reasoning → Multimodal reasoning +1
  4. Synthetic Leprosy Image Generation Using Mask-Conditioned Latent Diffusion and Transfer Learning from Large Chronic Wound DatasetsDiffusion models → Medical imaging and segmentation
  5. Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance PredictionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent CollaborationLLM agents and tool use → Agent threats, guardrails and governance
  7. Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic EraLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  9. Diffusion models for eye-gaze trajectory generation using position and velocity representationsDiffusion models → Video generation
  10. Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display ImagesKnowledge distillation → Detection and dense prediction distillation
  11. Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning NetworkKnowledge distillation → Federated, robust and private distillation
  12. On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following RerankersLLM reasoning → Prompting and chain-of-thought reasoning +1
  13. OR-Transformer: Scaling Real-Time Decision-Making to 1,000 ItemsDeep reinforcement learning methods → RL for energy, networks and operations
  14. Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using AgentsLLM safety and security → Prompt injection and agent security
  15. Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy MarketsLLM agents and tool use → Financial trading and forecasting agents
  16. MERGED: Multimodal Entity Resolution via Generated Expert Reasoning DistillationLLM reasoning → Multimodal reasoning
  17. Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation MethodsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  18. GAPS: Dimension-Level Gates for Conditional Activation SteeringMechanistic interpretability → Activation steering methods
  19. Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying EvidenceLLM agents and tool use → Web, search, and research agents
  20. ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent ResearchLLM agents and tool use → Web, search, and research agents
  21. Thinking effort aligns between humans and reasoning models in abductive reasoningLLM reasoning → Reasoning benchmarks and evaluation
  22. ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding RetrievalRetrieval-augmented generation → RAG for code +1
  23. Belief-Calibrated Optimization: An Explicit World Model for Agentic OptimizationWorld models → World models for language agents +1
  24. Agent Memory Is a Surface for Endogenous Authorization LaunderingLLM agents and tool use → Agent threats, guardrails and governance
  25. Scaling Inference Prefill with High-Radix Photonic InterconnectsMixture-of-experts → Efficient MoE training and inference systems
  26. Induction and Inquiry via Probabilistic Reasoning over Language and CodeLLM reasoning → Reasoning benchmarks and evaluation
  27. Reinforcement learning to choose optimizersDeep reinforcement learning methods → Deep RL algorithms and representations
  28. Designing Versatile Samples for Learned Trajectory ScoringEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  29. KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic NavigationLLM agents and tool use → Web, search, and research agents
  30. Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G NetworksLLM agents and tool use → Agentic AI for wireless networks
  31. MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  32. Curriculum-Guided Reinforcement Learning for Energy-Efficient UAV-ISAC in Post-Disaster Search-and-Rescue OperationsDeep reinforcement learning methods → RL for robot navigation and UAV control
  33. AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via α-Corrected Binary Cross Entropy and Factorized Latent SupervisionMultimodal LLMs / vision-language models → Medical vision-language models
  34. A Study of Conditional Diffusion Models for Open-Loop Control under Dry Friction and StictionDiffusion models → Diffusion and flow policies for robotics
  35. CAT-Flow: Curvature-Adaptive sTeps for Flow MatchingDiffusion models → Flow matching, time series and science
  36. Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool PrimitivesLLM agents and tool use → Tool learning and function calling
  37. Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS ModelsLLM safety and security → Membership inference attacks +1
  38. Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model StudyLLM agents and tool use → Agent threats, guardrails and governance
  39. FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-MakingMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  40. Reinforcement Learning and Rule-Based Peer-to-Peer Pricing in Residential PV-BES CommunitiesDeep reinforcement learning methods → RL for energy, networks and operations
  41. Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software EngineeringLLM agents and tool use → Agent threats, guardrails and governance
  42. Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  43. Efficient SWE Agent Benchmarking via Trajectory-Aware EvaluationLLM agents and tool use → Software engineering coding agents
  44. CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?LLM reasoning → Reasoning for agents, planning and code +1
  45. The Rise of Verbal Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  46. SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image GenerationLLM reasoning → Multimodal reasoning
  47. Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM TeachersMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  48. H3-World: Turning Language Understanding into World ControlWorld models → Video-generation world models and simulators
  49. Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectoriesLLM agents and tool use → Web, search, and research agents
  50. NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  51. Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive DiagnosisMechanistic interpretability → Sparse autoencoder training and evaluation
  52. Knowledge Distillation During Mid-Training Favors Reasoning over Factual RecallLLM reasoning → Prompting and chain-of-thought reasoning +1
  53. When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce EvaluationLLM agents and tool use → Financial trading and forecasting agents
  54. DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
  55. TempCloze: Can Video-LLMs Identify the Missing Middle?LLM reasoning → Multimodal reasoning
  56. LatentPress: Context Compression Beyond Text and VisionEfficient LLM inference and serving → Prompt and context compression
  57. GlossoGen: Emergent Language in Complex Multi-Agent LLM InteractionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Harness-of-Harness: Multi-Day Autonomous Software Development with Continual ImprovementLLM agents and tool use → Software engineering coding agents
  59. Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their ObserversLLM agents and tool use → Agent memory systems
  60. When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  61. Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution SpeedsOffline RL and imitation learning from data → Robot manipulation imitation learning
  62. Diffusion as a Training Curriculum for Timestep-Free Iterative ReasoningDiffusion models → Discrete and text diffusion
  63. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?LLM agents and tool use → Software engineering coding agents
  64. Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept ErasureDiffusion models → Robustness, privacy and adversarial aspects
  65. TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient ExecutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Provably Safe Sim-to-Real TransferDeep reinforcement learning methods → Safe and constrained RL
  67. EdiTikZ: Scientific Figure Editing from Revision TrajectoriesMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  68. Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and SearchingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  69. InSight: A Benchmark for Agentic Claim Verification in Interactive VisualizationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  70. IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective SignalsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  71. Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QAMechanistic interpretability → Interpreting biomedical and science models
  72. EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM SystemsLLM agents and tool use → Software engineering coding agents
  73. SMELT: Scaling Laws for Compute-Matched MoE Looped TransformersMixture-of-experts → Expert routing strategies
  74. mzCache: On-Device LLM Memory Management under MultitaskingEfficient LLM inference and serving → Serving systems and request scheduling
  75. VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking ModelsRetrieval-augmented generation → Privacy and security of RAG
  76. Exploring Sparse Autoencoders in Text-Based Causal Confounding AdjustmentMechanistic interpretability → SAE features and their applications
  77. Reliability Challenges in Diffusion Vision-Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  78. Explore Before Committing: Hypothesis-Guided Search for Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  79. EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA AgentsVision-language-action models → Failure recovery and robustness
  80. TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion ModelsDiffusion models → Audio, speech and music
  81. Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model AgentsLLM agents and tool use → Agent memory systems
  82. What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels RevealLLM agents and tool use → Software engineering coding agents
  83. One Prompt Is Enough: Watermark Laundering Through Foundation Image ModelsLLM safety and security → Watermarking generated content and models
  84. Ready to Speak: Aligning LLMs for TTS-Friendly Text GenerationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  85. Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  86. Post-Training Science for Supervised Fine-TuningMixture-of-experts → Mixture of LoRA experts
  87. Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and ShufflingEfficient LLM inference and serving → Token pruning and merging for ViTs
  88. S2Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  89. H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  90. REFACTOR-VLA: Unsupervised Library Learning of Typed Motor ProgramsWorld models → Embodied and robot world models +1
  91. Compressing AI Traffic: Standardized Neural Network Coding of Visual-Token Representations in Split Vision-Language InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  92. PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in InsuranceDeep reinforcement learning methods → RL training of language and agent models
  93. Reveree: Diagnosing LLM Reverse-Engineering AgentsLLM agents and tool use → Agent threats, guardrails and governance
  94. Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent DebateLLM agents and tool use → Agent threats, guardrails and governance +1
  95. Classic AI Scaffolding for LLM Social AgentsLLM agents and tool use → Social simulation and multi-agent debate
  96. CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  97. On the Design Fundamentals of Pixel Text Representation LearningEfficient LLM inference and serving → Visual token pruning in multimodal models
  98. P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image EnhancementDiffusion models → Inverse problems and image restoration
  99. Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMsLLM reasoning → Test-time compute and efficient thinking
  100. ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived DialoguesLLM reasoning → Clinical and biomedical applications +1
All 564
  1. Beyond Magnitude: Contrastive Routing for Modular Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  2. Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  3. Text-guided flow matching enables sample-efficient crystal structure generationDiffusion models → Flow matching, time series and science
  4. OUTLETS: Output-Length Prediction from Speculative Decoding BackbonesEfficient LLM inference and serving → Speculative decoding
  5. World Model-Guided Reinforcement Learning via Counterfactual User Engagement SimulationWorld models → Latent dynamics models and model-based RL
  6. Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPCDeep reinforcement learning methods → RL for autonomous driving and traffic
  7. Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  8. ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  9. WorldBench: Culturally Grounded Benchmark for Multilingual AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. Lagged Coupling: Internal Representations Become Readable Before They Become CausalMechanistic interpretability → Circuits and mechanistic analysis
  11. HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial ObfuscationLLM safety and security → Prompt injection and agent security
  12. AgentFactory: Towards Automated Agentic System Design and OptimizationLLM agents and tool use → Software engineering coding agents
  13. From Truncation to Commitment: Persistent Context in Uniform Discrete DiffusionDiffusion models → Discrete and text diffusion
  14. Data-Driven Persona-Conditioned Agents for A/B Test SimulationLLM agents and tool use → Social simulation and multi-agent debate
  15. Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent TreesLLM agents and tool use → Agent threats, guardrails and governance
  16. PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path CompositionMixture-of-experts → Efficient MoE training and inference systems
  17. AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMsLLM safety and security → Backdoor and data poisoning attacks
  18. SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  19. AInfer-PD: Communication-Safe In-Place Prefill-Decode Multiplexing for Distributed MoE RolloutsMixture-of-experts → MoE in reinforcement learning and robotics
  20. Disclosure-Gated User Simulation for Companion-Agent EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  21. ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image TranslationDiffusion models → Inverse problems and image restoration
  22. CoBRA: Learning Tool-Use Boundaries via Counterfactual MarginsLLM agents and tool use → Tool learning and function calling
  23. Conditional Flow Matching for Cross-Field MRI HarmonisationDiffusion models → Medical imaging and segmentation
  24. ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory HardwareDiffusion models → Diffusion foundations and sampling
  25. Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-CallingLLM agents and tool use → Tool learning and function calling
  26. From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  27. DualStake: Dual-Path Confidence Calibration in Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  28. Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPOLLM reasoning → Test-time compute and efficient thinking +1
  29. VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  30. Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAsVision-language-action models → Efficient VLA inference and adaptation
  31. CacheBridge: Efficient Cross-Model KV Cache TransferEfficient LLM inference and serving → KV cache optimization
  32. Denoising Diffusion Generative Models Secretly Calculate AttentionsDiffusion models → Diffusion foundations and sampling
  33. Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  34. Beyond the Clock: Measuring the Value of Adaptive RevisionLLM agents and tool use → General LLM agent frameworks and benchmarks
  35. Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization AsymmetryDiffusion models → Robustness, privacy and adversarial aspects +1
  36. The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual EvidenceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  38. Conditional Flow Matching for ML-Based Inverse Design ProblemsDiffusion models → Flow matching, time series and science
  39. Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  40. Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing ProblemsLLM agents and tool use → Reinforcement learning for LLM agents
  41. LLM Inference on IMC-NoC Architecture with Balanced Dataflow and Fine-Grained ParallelismEfficient LLM inference and serving → Serving systems and request scheduling
  42. Towards Generalizable Visually Grounded Exploration of Household DevicesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  43. Dense Process Supervision for Search Agents via Fact Utility EstimationDeep reinforcement learning methods → RL training of language and agent models
  44. Visual Attention Faithfulness in Vision-Language Models is HeterogeneousMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  46. ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image RestorationDiffusion models → Inverse problems and image restoration
  47. Advanced Pixel Diffusion Model with Guided Sparse Global RefinementDiffusion models → Diffusion foundations and sampling
  48. Agentic programs: an emerging form of scientific software in computational materials scienceLLM agents and tool use → Medical and scientific domain agents
  49. Instella-MoE Technical ReportMixture-of-experts → MoE large language models
  50. RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  51. Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral DomainMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  52. Solaris: Towards Interfaces That Are Generated, Not CodedWorld models → World model security and GUI agents
  53. Non-Prehensile Throwing: A Reinforcement Learning PerspectiveDeep reinforcement learning methods → RL for robot locomotion and manipulation
  54. Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural ArchitecturesLLM reasoning → Multimodal reasoning
  55. Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History TextbooksRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  56. S^3martCirc: Self-supervised Smart Circuit DiscoveryMechanistic interpretability → Circuits and mechanistic analysis
  57. ContextPipe: Database-Inspired Context Assembly for Long-Horizon AgentsLLM agents and tool use → Agent memory systems
  58. Text Capability Loss in Vision-Language Adaptation: An Attention-Sink DiagnosisLLM reasoning → Multimodal reasoning +1
  59. Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMsLLM reasoning → Test-time compute and efficient thinking
  60. Agentic Empirical Asset Pricing: Methodological FoundationsLLM agents and tool use → Financial trading and forecasting agents
  61. A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving PoliciesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  62. ChatDev 2.0: A No-Code Multi-Agent Platform for Developing EverythingLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. EarthLD: Towards Unified Open-World Landslide Understanding via Vision-Language Guided Diffusion ModelsDiffusion models → Inverse problems and image restoration
  64. Controllable Image Captioning with Prompt-Conditioned Scene RewardsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  65. Patterning in Practice: Debiasing Reward Models with SusceptibilitiesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  66. SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  67. Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?LLM agents and tool use → Social simulation and multi-agent debate
  68. HarmoCore: Functional Latent Diffusion for Sparse Reconstruction of Oscillatory Wave FieldsDiffusion models → Inverse problems and image restoration
  69. From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM RerankersMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  70. Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structuresLLM reasoning → Multimodal reasoning +1
  71. Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical ReasoningLLM reasoning → Spatial and embodied reasoning +1
  72. Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary SearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  73. You Cannot Photograph the Same Street Twice: Reliability Limits in Vision-Language Measurement of Urban ChangeMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  74. It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  75. ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge GraphsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  76. Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference TimeLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  77. Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMsLLM agents and tool use → Software engineering coding agents
  78. DSG: Dynamic 3D Scene Graph Construction for Embodied Agents in Changing Indoor EnvironmentsLLM agents and tool use → Multimodal and embodied agents
  79. Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental ReconstructionWorld models → Video-generation world models and simulators
  80. Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM UnlearningLLM safety and security → Machine unlearning
  81. NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced ManufacturingLLM reasoning → Reasoning for agents, planning and code
  82. SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  83. A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLossMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  84. CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RANLLM reasoning → Reasoning for agents, planning and code
  85. Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMsMixture-of-experts → MoE large language models
  86. WiseSpec: Requirements-Driven Agents for Code GenerationLLM agents and tool use → Software engineering coding agents
  87. Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge ConflictMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  88. Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  89. Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  90. Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop ApplicationsLLM agents and tool use → GUI and mobile agents
  91. Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  92. ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  93. Independent Reinforcement Learning in Discounted Markov GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  94. Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
  95. Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null
  96. QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models
  97. CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion
  98. ToCo-Mesh: Topology-Consistent Dynamic Mesh Reconstruction via Adaptive Tessellation and Surface-Aligned 2DGS
  99. SALSA: Semi-Autonomous Literature Summarization Assistant
  100. Replicating the Geometry of Emotion Representations in a Base Open-Weights Model
  101. An Implant-to-Wearable IR-UWB Transmitter-Receiver Architecture and Layered Protocol for High-Density Brain-Computer Interfaces
  102. Prediction of Nonlinear Oscillations in a Jumping Quarter-Car Model Using Reservoir Computing
  103. Evaluating Personal Information Output from Conversational Interactions in Generative AI Systems
  104. Reliability-Aware Hybrid-K Ensemble Selection for Cervical Cytology Classification: Integrating Discrimination, Calibration, and Selective Prediction
  105. Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validation
  106. Situation Awareness for Intelligent Data Distribution in Connected Vehicles
  107. FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions
  108. Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis
  109. Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
  110. Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising
  111. Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation
  112. Refining Heuristic-Based Bitcoin Address Clustering with Graph Neural Networks
  113. Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
  114. Learning with Volterra Neural Networks: A System Theoretic Perspective
  115. CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing
  116. Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?
  117. Automated Maize Ear Phenotyping Using 3D Reconstructions
  118. Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
  119. The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction
  120. Accurate in space, unreliable in time: how LLMs represent national cultural change
  121. TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views
  122. OutageDiT: A Generative Foundation Model for Power Outage Forecasting and Scenario Simulation
  123. SignMatch: Matching Dictionary Signs to Continuous Sign Language Video
  124. RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume Correlation
  125. Latent unified smooth Hamiltonians for excited state chemistry
  126. The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
  127. SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval
  128. Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
  129. Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation
  130. Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
  131. Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern
  132. Candidate Generation and Definition-Guided Verification for Sentence-Level Depression Symptom Recognition
  133. Interpretable Symptom Vectors for Depression in a Large Language Model
  134. AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking
  135. SliceBridge: Context-Consistent Repair of Corrupted Slice Intervals in T1-Weighted MRI
  136. Kirin: Animal Motion Generation from In-the-Wild Video
  137. Zeta-Lite: A Concurrent, Branchable In-Browser SQL Database for Agentic Memory
  138. Video2Reaction: Training Foundation Video Models to Predict Audience Reaction
  139. When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium Selection
  140. TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding
  141. Integrated Laser Scanning and Image-Based Topology Optimization Techniques for Detection and Quantification of Visible and Subsurface Structural Defects
  142. SPD: Single Pass Decoding for Generative Reranking
  143. Consistency as Regularization for Unsupervised Shadow Removal
  144. D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data
  145. Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks
  146. How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?
  147. DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation
  148. Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization
  149. Efficient Passive Acoustic Monitoring of Killer Whales Using a Two-Stage Detection and Ecotype Classification Cascade
  150. VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages
  151. CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer
  152. Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation
  153. Robust Bayesian Inference for Unnormalized Models with Mixed-Domain Data
  154. Allocate Before You Embed: Adaptive Visual Input Allocation for Video Embeddings
  155. Dictionary-Guided Mutation Operators for Automated HDL Repair
  156. Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks
  157. Toward Explainable and Policy-Aware AI for Carbon Credit Price Prediction: A Research Framework for Emerging Carbon Markets
  158. Pooling and Drift in Delayed Bandits
  159. Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics
  160. SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness
  161. Evidential Deep Learning for Multi-Modal Anti-UAV Detection
  162. When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Logic
  163. ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
  164. UAV Thermal Imagery for Inert Ordnance Screening: Multi Campaign Dataset Development,Object Detection, and Practical Recommendations
  165. SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition
  166. HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
  167. RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis
  168. From Visual Cues to Spoken Narration: Rethinking Audio Description
  169. Generative Diffusion Surrogates with Analytical Variance Schedule
  170. Tri-Band Channel Measurement-Enabled Multi-Layer Digital Twin for Terahertz Wireless Data Centers
  171. Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oracle
  172. Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA
  173. Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
  174. FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers
  175. A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
  176. Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling
  177. CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction
  178. Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports
  179. Private Computation Space: Experience with Trusted Multi-Cluster Federated Learning for Agriculture
  180. Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
  181. Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation
  182. Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
  183. UI-VISA: U-Net Initialized Vascular Image Segmentation Architecture
  184. Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation
  185. Mechanism Design for Alignment and Control
  186. StudentSim: Training LLM-based Student Simulators
  187. Designing Proactive Thought Partners for Writing
  188. The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
  189. A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios
  190. Simultaneous Pointwise Majorization for Mixed Tail Processes with Applications in Gaussian Chaos and Ergodic Diffusions
  191. Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics
  192. Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
  193. From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
  194. From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
  195. A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains
  196. Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
  197. BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net
  198. Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
  199. What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
  200. Linear Reusable Neural Bases Architecture for Network Compression
  201. SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue
  202. Variable Selection for Feature-Based Newsvendor
  203. Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
  204. Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
  205. Sierpi'nski--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation
  206. EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
  207. Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data
  208. A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation Data
  209. Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation
  210. Optimizing Byzantine Node Placement in Decentralized Federated Learning
  211. Rethinking Learnability in Offline Data-driven Optimization
  212. Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
  213. CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling
  214. RadMatch: Auditable Radiology Report Evaluation via Finding-Level Matching
  215. AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval
  216. Edge-Girth as a Structural Edge Feature for Graph Neural Networks
  217. Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation
  218. Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search
  219. Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
  220. Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications
  221. Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading
  222. CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection
  223. MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition
  224. From Rollouts to Recipes: Self-Contained Post-Training for LLMs
  225. Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks
  226. On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
  227. Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations
  228. Contribution-Aware Bandwidth Allocation for Multimodal Split Learning
  229. Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity
  230. Scale-based Approach for Active Wildfire Segmentation on Satellite Imagery
  231. Multimodal RGB-Infrared Combination for UAV-Based Wildfire Segmentation: A Comparative Study on FLAME3
  232. When Tokenization is Secretly Output Supervision
  233. Polish ModernBERT: The Long and Short of Polish Language Understanding
  234. Behaviorally Effective LoRA Writes Are Sparse and Structured
  235. Diffusion Based Unpaired Data Learning for Inverse Problems
  236. How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation
  237. Accurate Reconstruction of Gas Turbine Blade Geometry Using 3D/2D Rigid Registration and CT View Optimization
  238. PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction
  239. Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
  240. Exact Risk-Complexity Laws for Projective Boundaries in Scenario Optimization and Distribution-Free Certification
  241. Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR
  242. SymFold: Synergizing Evolutionary and Structural Priors for Accurate Protein Inverse Folding
  243. CHARM: Character Hallucination for Multicultural Role Play Benchmark
  244. Scalable Rao-Blackwellized Online Planning for High-Dimensional POMDPs
  245. Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades
  246. ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence
  247. Probing Factual Knowledge Transfer with Training Data Interventions
  248. LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting
  249. Bandits in Prod: Hyperparameter Optimization at Inference Time
  250. Automated Event Log Generation from Unstructured Text Using Finetuned LLMs
  251. Matched Queries for Curvature and Density at Branching Junctions
  252. MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval
  253. A Composable Evaluation System for Reproducible Omni-Modal Foundation Model Evaluation
  254. One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context
  255. GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation
  256. CMRVision: A Foundation Model for Cardiac MR Image Analysis
  257. MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering
  258. Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning
  259. Agentic Multimodal Models for Environmental Hyperspectral Unmixing
  260. Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems
  261. HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
  262. Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models
  263. Seeing the World and the Self from Egocentric Video
  264. The Constitutional Coverage Trilemma in AI Governance
  265. From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
  266. Position: Privacy Is a Claim, Not a Property of Synthetic Data
  267. Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data
  268. Dual Process Motion Planning
  269. Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations
  270. MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation
  271. From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs
  272. MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence
  273. Multi-Head Self Attention is a Parameter Identification Mechanism
  274. Prompt-Robust Language Models: Which Training Strategies Work?
  275. Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey
  276. Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges
  277. Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening
  278. Towards AI-Assisted Clinical Trial Matching: Practical Considerations, Multicenter Evaluation, and Real-World Deployment
  279. FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue
  280. CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs
  281. Births are difficult to predict even with rich survey and full-population register data
  282. Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
  283. LLMPEDIA: Browsing, Verifying, and Comparing the Parametric Encyclopedic Knowledge of LLMs
  284. Monocular Depth Estimation from a Single Image: Progress and Opportunities
  285. Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
  286. Nonparametric inference for density-dependent McKean--Vlasov diffusions
  287. Superposed Latent Autoencoder
  288. Subword Segmental BabyLMs: Learning to Tokenise for Sample-Efficient Pretraining
  289. Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement
  290. StainPresetNet: Stain Preset Network for Fast Multi-to-Multi Stain Normalization
  291. Revisiting Face Recognition for Monozygotic Twins: The Celeb Twins Test Set
  292. Does task decomposition improve automatic NLG evaluation?
  293. Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning
  294. Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
  295. Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras
  296. When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting
  297. DNC-IMM: Early Lane-Change Intention Recognition via Neural Calibration Based on Driving Context Information
  298. EDRAC: Benchmarking Arabic Dialect Reading Comprehension
  299. Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget
  300. Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation
  301. When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP
  302. Neural Symbollic Regression Using Deep Learning and Sparse Modelling
  303. IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion
  304. Modelpedia: A Catalog of Model Findings for the Meta-Science of AI
  305. StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions
  306. Post-hoc Alignment of LLM-judges to Human Judgment Distribution
  307. Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
  308. Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models
  309. Space Generative AI with Solar Energy Harvesting
  310. Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment
  311. User Representation via Cross Multi-source Behavior Pre-training for Mobile Games
  312. SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations
  313. QILP-0: Constructing Observational Declarative Twins of Quantum Circuits
  314. ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives
  315. Causal Evidentiary Governance for High-Risk Machine Learning Systems
  316. MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset
  317. The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow
  318. On Synthesis of Metric Interval Temporal Logics
  319. Web Price Extraction: State of the Art and an Adaptive Browserless Implementation
  320. Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set
  321. PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation
  322. Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech
  323. A Network Science Perspective on Evaluating Deep Graph Generative Models
  324. Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints
  325. Figures as Programs: Recursive Generation of Editable Scientific Figures
  326. Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
  327. Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
  328. Does This Moment Justify the Recommendation? Counterfactual Behavior-Grounded Evidence Retrieval for Personalized Video Recommendation
  329. CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Image
  330. EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting
  331. On the Human and Computer Alignment of Attribute-Based Music Matches
  332. Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realism Constraints
  333. Prior-Guided Implicit Neural Representations for Single-Subject Diffusion MRI Super-Resolution
  334. The zbMATH Open Knowledge Graph: Tracing Centuries of Mathematical Research
  335. Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance
  336. Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA
  337. PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian
  338. PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance
  339. CERF: Communication-Efficient and Retraining-Free Collaborative Perception
  340. Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches
  341. A Dataset for Modeling Iterative Problem-Solving
  342. Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
  343. On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios
  344. VerNav: Verifier-First Low-Latency Vision-and-Language Navigation
  345. RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation
  346. A multicenter benchmark and clinically structured metric for coronary CTA report generation
  347. When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting
  348. In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?
  349. HELIOS: From midnight to noon, continuous outdoor urban scene relighting
  350. Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization
  351. Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting
  352. Poisson-Gamma Dynamical Systems with Time-varying Transition Dynamics
  353. CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training
  354. iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy
  355. FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study
  356. Sharp Mixed Spectral Barron Regularity of Coulombic Many-Electron Wave Functions
  357. Stochastic Optimization of Tree Tensor Networks
  358. MemoryWalker: Stop Training Agents on Contexts They Never Saw
  359. Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
  360. Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
  361. ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
  362. A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
  363. An Intelligent Decision Support System for Emotion Monitoring using Microscopic Fixational Dynamics
  364. Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
  365. Residual Kalman Dynamics for Event-Based UAV Forecasting
  366. Probabilistic Model Checking of Autoregressive Neural Sequence Models
  367. Replacing Training with Memory: Listwise Selection for Text-to-SQL
  368. TWIX: a Two-Stage Approach for End-To-End Named Entity Recognition and Relation Extraction
  369. FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
  370. HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
  371. Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents
  372. AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation
  373. Can Scene Text Recognition Read Rare Compositions?
  374. RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing
  375. Ctrl-F-Resist. Practices, Challenges, and Technical Needs of Civil Society Organizations Monitoring the Far-Right Online
  376. Towards a Reliable and Practical Eval Pipeline
  377. TEIDAN: A Multilingual Multiparty Dialogue Corpus
  378. No Pixel Left Behind: Filling Gaps in Anime Colorization
  379. SFAD: Speculative Factuality-Aware Decoding
  380. MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries
  381. Subspace Levenberg Marquardt Algorithms in Training Neural Networks
  382. StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
  383. When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection
  384. VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM
  385. Semi-Supervised Classification with Informative Missing Labels in Weibull Mixture Models
  386. Deep Skew-t Mixture Models
  387. Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models
  388. Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation
  389. A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
  390. Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning
  391. Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding
  392. How Do Language Models Choose Between Context and Memory?
  393. Measuring Optimal Transport in Transformer Depth
  394. Can Large Language Models Forecast What Researchers Study Next?
  395. Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation
  396. Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection
  397. Online Self-Weighted Fine-Tuning
  398. Design and Implementation of a Kalman Filter-Infused Algorithm for Tilt Estimation
  399. SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification
  400. Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models
  401. MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes
  402. Efficient and Robust Absolute Pose Estimation via Gravity-Prior-Driven Transformation Decoupling and Pose Refinement
  403. Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption
  404. Differentially Private Paired Table-Image Multimodal Synthesis
  405. A Certificate-Producing Cascade for Equational Implication: The SAIR EQT2 Stage 2 Solver
  406. FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation
  407. Value Over Language Model: Detecting Original Contribution in Writing
  408. MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks
  409. Verdict Instability of OOD Scores under Reference Resampling
  410. A Study of Hidden-State Optimization Order in Predictive Coding Networks
  411. Visual Framing for News Stance Detection via Image Generation
  412. DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection
  413. Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs
  414. Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets
  415. Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models
  416. Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning
  417. SciTrue: Reliable Scientific Claim Validation with Frontier and Open Language Models at the NTCIR SciClaimEval Task
  418. EEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction
  419. DK-GBMKKM: Dynamic Kernel-Space Granular-Ball Multiple Kernel k-Means Clustering
  420. DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation
  421. Disciplined Bilevel Programming
  422. REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows
  423. TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data
  424. Beyond Landmark Extraction: A Framework for Robust Geometric Feature Construction in Structured Image Classification
  425. Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity
  426. Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
  427. Inverse Rendering for Modeling with Line Primitives
  428. Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
  429. An efficient EM algorithm for both element-wise and structural missingness in matrix-variate normal mixture models
  430. BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management
  431. Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics
  432. Investigating Assistant Bias in LLM User Simulators Using a Role Vector
  433. Topological Steering
  434. BrainDiff: Longitudinal Report Generation for Multimodal Brain MRI
  435. Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking
  436. Real-Time Neuromorphic Spectrum Intelligence Simulator
  437. Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing
  438. Enoki: Efficient Multi-Level Hallucination Detection
  439. Predicting Program Exit Code with LLMs and Programming Language Semantics
  440. Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
  441. GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning
  442. Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random
  443. A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI
  444. VoiceLongMemEval: Do Assistants Remember How You Sounded?
  445. EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection
  446. Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
  447. Potential-Guided Particle Steering for Negation-Constrained Dexterous Grasping
  448. Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing
  449. EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
  450. Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers
  451. GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting
  452. DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement
  453. Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
  454. GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
  455. Soft-Argmax for the Projective Plane via the Veronese Embedding
  456. The Safeguard Worked. Is the LLM System Safer?
  457. Learning Task-Specific Antibody Representations via Function-Aware Masking
  458. The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
  459. When the Algorithm Becomes the Brand Crisis: A Sociotechnical Theory of Distributed Responsibility and Accountable Transparency
  460. CoVer: Conflict-Aware Claim Verification
  461. VATO: A Vortex-Force-Aware Transformer Operator for Unsteady Separated Aerofoil Flows
  462. RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
  463. ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits
  464. Wave Function Backpropagation with Explicit Temporal-Interval Dynamics