mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 30 Jul 2026

522 papers

  1. GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM InferenceEfficient LLM inference and serving → Diffusion LLM and MoE inference
  2. MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease AssessmentsRetrieval-augmented generation → Medical and biomedical RAG
  3. Looking Again: Measuring Sycophancy in the Reasoning Chains of Multimodal Models Under PressureLLM reasoning → Multimodal reasoning
  4. Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster AssistanceMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model CascadeWorld models → Embodied and robot world models
  6. Discrete Diffusion Language Models Are Training-Free Multi-Label ClassifiersDiffusion models → Discrete and text diffusion
  7. SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  8. NeuroPilot: An Agent-Driven Smart Pipeline for Processing, Quality Control, and Managing NeuroimagesLLM agents and tool use → Medical and scientific domain agents
  9. Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic CommerceLLM agents and tool use → Financial trading and forecasting agents
  10. Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production ScaleLLM agents and tool use → Software engineering coding agents
  11. SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  12. Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated MeshDiffusion models → Video generation
  13. Fragility of Value under Imperfect AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  14. Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL RepairLLM agents and tool use → Software engineering coding agents
  15. Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?LLM agents and tool use → Software engineering coding agents
  16. Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular RegressionDiffusion models → Diffusion foundations and sampling
  17. Hypergradient-based Bilevel Reinforcement Learning with Improved Sample ComplexityLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  18. DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMsEfficient LLM inference and serving → Serving systems and request scheduling
  19. CyberNeuro: A Privacy-Preserving Agentic Workbench for Cohort-Scale Neuroimage and Clinical Data AnalysisLLM agents and tool use → Medical and scientific domain agents
  20. When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent NetworksLLM safety and security → Federated unlearning and poisoning
  21. Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber OperationsLLM agents and tool use → Agent threats, guardrails and governance
  22. Building a Process-Modeling Tool using Agentic AI: An Experience Report on PM4Py-UCMLLM agents and tool use → Software engineering coding agents
  23. Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution LayerLLM agents and tool use → Software engineering coding agents
  24. WaiT for the Signal: Simple Frequency-Aware Flow-MatchingDiffusion models → Flow matching, time series and science
  25. SCMA: Structure-Conditioned and Metal-Aware Flow Matching for CT Metal Artifact ReductionDiffusion models → Medical imaging and segmentation
  26. Mirror LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  27. MMFGU: Multimodal Federated Graph UnlearningLLM safety and security → Graph unlearning
  28. Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  29. WitCert: Sound Runtime Risk Observability and Gating for KV-Cache QuantizationEfficient LLM inference and serving → KV cache quantization
  30. Flow Matching with Missing DataDiffusion models → Flow matching, time series and science
  31. Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical ShiftMultimodal LLMs / vision-language models → Medical vision-language models
  32. SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool AcquisitionLLM agents and tool use → Web, search, and research agents +1
  33. Safety, or Just Capability? A Validity Audit of Agent-Safety BenchmarksLLM safety and security → Safety alignment, refusal and guardrails
  34. ReToken: One Token to Improve Vision-Language Models for Visual RetrievalMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  35. PhiZero: A World Model Built Around Physical LanguageWorld models → Video-generation world models and simulators
  36. Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion TransformersDiffusion models → Video generation +1
  37. OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward ModelsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  38. Inducing language models to assert their own consciousness restores human beliefs and valuesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  39. FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich ManipulationDiffusion models → Diffusion and flow policies for robotics
  40. Beacon: Knowing When and How to Perform Agentic Visual ReasoningLLM reasoning → Multimodal reasoning +2
  41. Change2Task: From Repository Changes to Executable Coding Agent Tasks and EnvironmentsLLM agents and tool use → Software engineering coding agents
  42. VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy DistillationKnowledge distillation → Multimodal distillation
  43. β-OPSD: Deriving with Policy Optimization, Training with Self-DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  44. DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented GenerationLLM reasoning → Multimodal reasoning +1
  45. Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7BLLM reasoning → Test-time compute and efficient thinking
  46. Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute TradeoffsLLM reasoning → Reasoning for agents, planning and code +1
  47. Finding Change in Satellite Archives from Text: How to Combine Before-and-After Images EfficientlyState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  48. Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning EngineeringSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  49. MIND: Multimodal Intent-Driven Network via Diffusion Transformers for Medical Image FusionDiffusion models → Medical imaging and segmentation
  50. X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted MatchingDiffusion models → Diffusion and flow policies for robotics +1
  51. ORCA-bench: How Ready Are Language Model Agents for Oncall?LLM agents and tool use → Software engineering coding agents
  52. MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  53. Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache TransplantationEfficient LLM inference and serving → Efficient reasoning and agent inference
  54. Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  55. A report-grounded vision-language foundation model for colonoscopy from 280000 routine reportsMultimodal LLMs / vision-language models → Medical vision-language models
  56. Can Vision-Language Models Reason about AI Edits in Images?LLM reasoning → Multimodal reasoning +1
  57. VisualRouter: Query-Grounded Visual Sampling for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  58. Cybersecurity Detection Classification with Reasoning-enabled Language ModelsLLM reasoning → Reasoning for agents, planning and code
  59. SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time ComputeLLM reasoning → Reinforcement learning for reasoning +1
  60. Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  61. ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QAMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  62. AgentRadio: Passive Awareness for Long-Horizon Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
  63. QQWorld: Quantile-Quantile Matching for World Model RegularizationWorld models → Latent predictive world models
  64. QuantWAMs: Calibrating at the Right Granularity for World Action ModelsWorld models → Embodied and robot world models
  65. Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy TreesLLM agents and tool use → GUI and mobile agents
  66. GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  67. TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile PredictionWorld models → Embodied and robot world models
  68. Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPsDeep reinforcement learning methods → RL theory and sample complexity
  69. HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation DetectionLLM reasoning → Multimodal reasoning
  70. LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence LedgerLLM reasoning → Multimodal reasoning +1
  71. How Benchmarks Mis-Score Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  72. ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its ShadowWorld models → Embodied and robot world models
  73. Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  74. Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal ReasonersKnowledge distillation → Multimodal distillation
  75. Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace AgentsLLM agents and tool use → Financial trading and forecasting agents
  76. PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?Multimodal LLMs / vision-language models → Medical vision-language models
  77. One Human, N Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated ConfidenceLLM agents and tool use → Agent threats, guardrails and governance
  78. Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts RoutingMixture-of-experts → Expert routing strategies
  79. Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3World models → World models for language agents
  80. MSCM-net: A hyperspectral image classiffcation method based on multi-scale convolution and MambaState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  81. MemHarness: Memory Is Reconstructed, Not ReplayedLLM agents and tool use → Agent memory systems
  82. Agentic Method for Deterministic Validation of Legacy Code MigrationLLM agents and tool use → Software engineering coding agents
  83. Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +2
  84. EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPEWorld models → Embodied and robot world models
  85. EMBL AI Librarian: Life-Sciences Knowledge Layer for AI AgentsLLM agents and tool use → Web, search, and research agents
  86. Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI AgentsLLM agents and tool use → GUI and mobile agents
  87. Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and EvaluationWorld models → World model security and GUI agents +1
  88. FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image VerificationLLM reasoning → Multimodal reasoning +2
  89. Scaling Vision-Language Models Is Not Enough to Mitigate BiasMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  90. Vibe-FDTR: An agent-oriented framework for reproducible frequency-domain thermoreflectance data analysisLLM agents and tool use → Medical and scientific domain agents
  91. Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic ExecutionLLM agents and tool use → Agent memory systems
  92. Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content ModerationLLM safety and security → Safety alignment, refusal and guardrails
  93. AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic ApproachLLM agents and tool use → General LLM agent frameworks and benchmarks
  94. Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  95. Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  96. RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal ReasoningLLM reasoning → Reasoning for agents, planning and code
  97. OPLD: On-Policy Latent Distillation for Multimodal ReasoningLLM reasoning → Multimodal reasoning
  98. SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache TransferEfficient LLM inference and serving → KV cache optimization
  99. Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  100. Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction GameLLM reasoning → Reasoning for agents, planning and code +1
All 522
  1. LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  2. Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor ModelsLLM reasoning → Reasoning benchmarks and evaluation
  3. FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  4. MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information BottleneckLLM agents and tool use → Agent threats, guardrails and governance
  5. From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  6. LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  7. Group-Reflective Self-Distillation for Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  8. Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at ScaleLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. SemPIC: Learning Semantic Position-Independent KV CachesLLM agents and tool use → Software engineering coding agents +1
  10. BladeYOLO: Wind Turbine Blade Defect Detection with Limited Annotations and Weak-Saliency AwarenessState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  11. Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video DiffusionDiffusion models → Video generation +1
  12. SKILL-KD: Contrastive Skill Distillation for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  13. ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial HarnessLLM agents and tool use → Web, search, and research agents
  15. VISA: A Structured Description Protocol for Agent-Based Simulation Models Towards Machine ReproducibilityLLM agents and tool use → Software engineering coding agents
  16. Contrastive Reinforced Policy Optimization via Privileged Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  17. Flux-OPD: On-Policy Distillation with Evolving ContextsKnowledge distillation → On-policy and self-distillation for LLMs
  18. RepBench: Compiling Benchmarks into Capability Representations for Large Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  19. Share the Judge, Learn the Deferral: Where Specialization Helps LLM EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. TAPO: Transition-Aware Policy Optimization for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  21. Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement UnlearningLLM safety and security → Machine unlearning
  22. FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image RetrievalLLM reasoning → Multimodal reasoning +1
  23. Sigma-Mem: An Online Reliability Memory for LLM-based Multi-Agent SystemsLLM agents and tool use → Agent memory systems
  24. LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM InferenceEfficient LLM inference and serving → Visual token pruning in multimodal models
  25. Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State EntanglementLLM safety and security → Federated unlearning and poisoning
  27. From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  28. The Geometry of Flow-Matching Uncertainty: A Cost-free Uncertainty Proxy and Its Application in Flow-based VLA Failure DetectionDiffusion models → Flow matching, time series and science
  29. Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent TrainingLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. ODEWorld: A Continuous Predictive Architecture via Physical-Time FlowWorld models → Latent predictive world models
  31. Memory Decoder at Scale: A Pretrained, Parametric Long-Term MemoryLLM reasoning → Test-time compute and efficient thinking
  32. One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  33. Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV ControlLLM reasoning → Reinforcement learning for reasoning
  34. A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  35. Class-Aware Reinforcement Learning for Counterfactual Explanation GenerationDeep reinforcement learning methods → Interpretable and logic-guided RL
  36. Unifying Adversarially Robust Model Experts in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  37. Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT ReasoningLLM reasoning → Reinforcement learning for reasoning
  38. RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic AgentsVision-language-action models → Failure recovery and robustness
  39. ARES: Adaptive Reasoning-Effort Steering for PPA- and Cost-Aware RTL Optimization with LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  40. Orca: Neural Operators for Causal Reasoning in Continuous TimeLLM reasoning → Causal reasoning in LLMs
  41. FinanceHarness: Autonomous Financial Deep Research FrameworkLLM agents and tool use → Financial trading and forecasting agents
  42. FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion InferenceDiffusion models → Diffusion foundations and sampling
  43. Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin CalibrationLLM safety and security → Machine unlearning
  44. MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent MemoryLLM agents and tool use → Agent memory systems
  45. Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQALLM reasoning → Multimodal reasoning +1
  46. Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object CorrectionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  47. SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark AttackState-space sequence models (S4, Mamba) → Mamba for image restoration
  48. FDDWAN: A Frequency-Decoupled Diffusion Network for Watermarking AttackLLM safety and security → Watermarking generated content and models
  49. MemeBench: What LVLMs Miss When Interpreting Culture-Dependent MemesMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  50. LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff PromptsLLM reasoning → Reinforcement learning for reasoning
  51. Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG AggregationLLM reasoning → Reasoning benchmarks and evaluation
  52. RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA PolicyVision-language-action models → Efficient VLA inference and adaptation +2
  53. ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent MemoryLLM agents and tool use → Agent memory systems
  54. Hierarchical Latent Reasoning for LLM-based RecommendationLLM reasoning → LLM reasoning for recommendation
  55. Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning CapabilitiesLLM reasoning → Multimodal reasoning +1
  56. Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual TeachersKnowledge distillation → Federated, robust and private distillation
  57. A Sparse Glimpse of the Whole: Train-Free Self-Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  58. VeriSkill: A Self-Evolution Framework for Program Verification SkillsLLM agents and tool use → Agent skill learning and evolution
  59. Baikal: Structured Search for Deep Research over Data LakesLLM agents and tool use → Web, search, and research agents
  60. SpatialCLI: Learning to Reason With Spatial Tools, Then Without ThemLLM reasoning → Spatial and embodied reasoning +2
  61. Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMsLLM reasoning → Multimodal reasoning +2
  62. RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG GenerationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
  63. GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM InferenceEfficient LLM inference and serving → KV cache quantization
  64. Recall Before You Rank: Similarity-Guided Top-K Reuse for Efficient Long-Context AttentionEfficient LLM inference and serving → KV cache optimization
  65. Rehearse: Stepping Back from the Confidence Cliff in Self-Improving AutoresearchSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  66. JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw PuzzlesLLM reasoning → Spatial and embodied reasoning
  67. Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal AnswersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  68. Harness-G: A Graph-Structured Harness for Search AgentsDeep reinforcement learning methods → RL training of language and agent models
  69. MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  70. HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic ExecutionLLM agents and tool use → Agent threats, guardrails and governance
  71. ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  72. Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL FinetuningLLM reasoning → Reinforcement learning for reasoning
  73. Back from the Future: Key-Value Cache Management by Counter-Causal SurpriseEfficient LLM inference and serving → KV cache optimization
  74. World Action Planner: Generalizable Decision-Making with Action-Conditioned World ModelsWorld models → Embodied and robot world models
  75. A Systems Engineering Framework for Vision-Language-Enabled UAV Triage and Disaster ResponseMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  76. Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese HistoriesLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA AdaptersLLM reasoning → Reasoning for agents, planning and code +2
  78. Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case StudyMixture-of-experts → MoE for recommender systems
  79. Policy Gradient Steering: Interventions from Behavioral ObjectivesMechanistic interpretability → Activation steering methods +1
  80. Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical ReasoningLLM agents and tool use → Medical and scientific domain agents
  81. DeepResearch Agent SystemLLM agents and tool use → Web, search, and research agents
  82. Evaluating Agentic Bioinformatics through Function, Evidence, and ValidationLLM agents and tool use → Medical and scientific domain agents
  83. Cross-Embodiment Transfer via Behavior-Aligned RepresentationsOffline RL and imitation learning from data → Robot manipulation imitation learning
  84. ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI PredictionDiffusion models → Medical imaging and segmentation
  85. Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition
  86. Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes
  87. Viveka-Insight: a cross-lingual concept graph and citation-grounded retrieval resource over the complete works of Swami Vivekananda in English and Bengali
  88. SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption
  89. Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detection
  90. Queries Knew More Than We Thought: Uncovering Latent Knowledge in Segmentation Models
  91. Speaker or Language? Explaining Variance in Charismatic Prosody Across Luxembourgish and French
  92. Speaker-Specific and Language-Dependent Temporal Organization in Bilingual Political Speech
  93. Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
  94. Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
  95. Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings
  96. iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration
  97. The Edge-based Contiguous p-median Problem with Connections to Logistics Districting
  98. Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator
  99. An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop
  100. LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology
  101. GRAIN: Molecules Are Not the Right Granularity -- Active-Ingredient Modeling for Safe Medication Recommendation
  102. Untrainable elements determine what physical learning remembers
  103. Logographic Character Visual Pretraining via Semantic-based Contrastive Learning
  104. Rethinking Total Absorption Gamma Spectroscopy Deconvolution: Supervised Machine Learning vs Response-Matrix Methods
  105. DODA: A Database of Datasets for Aesthetics Research
  106. SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization
  107. DS@GT ARC at MEDIQA-CORE-Task-1 2026: Trimodal Model Fusion with Task-Specific Gates for Brain Tumor Subtype Classification
  108. TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models
  109. Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design
  110. Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth
  111. Human-LLM Collaborative Inductive Coding for Conceptualizing K-12 Educator AI Use
  112. To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
  113. LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data
  114. RareSense: Rarity-Aware Similarity Search for Anomaly Retrieval in Transactional Data
  115. Learning to Predict Performance-induced Emotion Differences in Classical Piano Music
  116. Physics-Aligned Self-Supervised Learning for Scientific Imaging
  117. TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text
  118. The Debiased Score Test: Hunt-and-test for Semiparametric Hypotheses
  119. A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging
  120. Fast Rates for Swap-Agnostic Learning of Proper Losses
  121. Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds
  122. An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks
  123. Seeing the Forest for the Trees: The Gaussian Process Limit of BART
  124. Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications
  125. FocusGS: Spatial Delta Layers for Local Repair and Deterministic Editing of Trained 3D Gaussian Assets
  126. Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions
  127. Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing
  128. Bayesian Mediation Analysis for Individualized Treatment Rules
  129. Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
  130. Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation
  131. Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments?
  132. EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses
  133. Stratified Negation in RDF Rules: A Correct Approach (Extended Version)
  134. Self-Supervised Skill Optimization
  135. Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation
  136. Do Medical Foundation Models Generalize on the African Brain?
  137. Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning
  138. The Morphological Core of Dungan: A Two-Dialect Finite-State Model and a Multi-Genre Evaluation
  139. Feature Interaction Modeling for Neural Operators
  140. TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning
  141. ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding
  142. DragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End Testing
  143. A user's guide to PINNs in geometric analysis: lessons from the asymptotic Plateau problem
  144. Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs
  145. Simulative Anomaly Detection using 2D Tomography
  146. Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning
  147. SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM
  148. Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent
  149. Reflected UAS: Corrected Deterministic Stability and Direct CTMC Drift Calculation
  150. Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions
  151. Optical Flow Sensor: A Direction-Selective Bionic Retina Design
  152. Library Reachability in LSR-Synth: How Anti-Memorization Design Changes the Measurement of Symbolic Discovery
  153. Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation
  154. Learning to Trace Seiberg Dualities
  155. ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine
  156. PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
  157. AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
  158. AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
  159. KAISEN: Reproducible Subgroup Fairness Auditing for Clinical Risk Models
  160. MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
  161. PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks
  162. ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation
  163. Algorithms for Structured Elections under Thiele Voting Rules
  164. Doubly Robust Functional Representation Learning for Longitudinal Causal Inference with Irregular Histories
  165. APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems
  166. ScaFE: Data-Efficient Scar Classification with LLM-Generated Clinical Feature Programs
  167. Graph Neural Network Force Fields for Spin Dynamics in Metallic Magnets
  168. MarkushGlyph and OCSRGlyph: Improved Chemical Structure Recognition
  169. AI systems and the reproduction of (standard) language ideologies in World Englishes
  170. What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
  171. Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
  172. Selective Credibility-Limited Belief Update
  173. Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
  174. Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding
  175. Creative Transformation in Literary Texts: Modelling Change Across Representational Levels
  176. RefCaptioner: Multi-Reference Image-Grounded Video Captioning
  177. Generative AI and linguistic diversity in academic writing and publishing: Perspectives from World Englishes
  178. InfoOps Bench: A live information operations safety benchmark
  179. TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
  180. The Role of Causality in Algorithmic Recourse
  181. Beyond Sentiment: Structured Information Extraction from Financial News
  182. SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination
  183. AuricularWorld: Hierarchical Action-Guided World Modeling for Fine-Grained Auricular Structure Segmentation from CT Scans
  184. Towards Real-Time PixOOD: Efficient Anomaly Segmentation for Autonomous Vehicles
  185. A Fuzzy Rule-based Neuro-Symbolic Approach for Pipe Severity Prediction in Sewer Networks
  186. Improving Mental Health Screening and Early Risk Detection in Spanish
  187. Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation
  188. LeanCSP: A Framework for Certifying Constraint Reformulation and Solving in Lean
  189. Graph Neural Multilevel Preconditioners for Iterative Solvers
  190. Machines that know they are aging: a framework for hardware-aware autonomous intelligence
  191. Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation
  192. Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory
  193. Metaphor Tracer: A Theory-Informed Analysis of Hidden States
  194. A foundation model of numerical intelligence with cross-disciplinary generalization
  195. Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification
  196. Negative controls reveal volume-driven confounding in radiomics and imaging foundation model features
  197. QAdapt: A Noise-Adaptive Neural Pre-Decoding Framework for Quantum Error Correction
  198. When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
  199. WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
  200. Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
  201. Can Large Language Models Execute Parent Orders?
  202. On-Policy and Off-Policy Learning for Large Action Spaces
  203. Large scale cross-regional remote sensing flood monitoring framework for operative mapping and impact analysis
  204. Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer
  205. Explaining Image Similarity with Automatically Extracted Concept Activation Vectors
  206. When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
  207. Correlation between prosody and pragmatics: A case study of the discourse marker h=al=a `now' in Persian
  208. Teffic-Audio: Tell Fact from Fiction
  209. LLMs struggle to simulate human belief updates in controlled environments
  210. Reflected diffusion, no-flux continuity equations and confined Lagrangian flows in bounded domains
  211. Learning to Persuade Privately Informed Receivers
  212. Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata
  213. Same Branches, Different Trees: A Bifurcation Connectedness Metric for Coronary Artery Segmentation and FFR-CT Decision Agreement
  214. Measuring Distortion in the Empty Regions of Dimensionality Reduction Scatterplots with the Gap Index
  215. Non-partitioned e-detectors for nonparametric sequential change detection
  216. AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction
  217. Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
  218. ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
  219. Fully Inductive Cardinality Estimation
  220. From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis
  221. A Distributed Acoustic Sensing Dataset for Vessel Detection and Localization in Submarine Cable Protection
  222. Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
  223. HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks
  224. MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
  225. Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
  226. CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
  227. Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captions
  228. (Towards) Scalable Reliable Automated Evaluation with Large Language Models
  229. MORFES: A Benchmark for Productive Inflectional Competence in Modern Greek
  230. LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
  231. CoMem: Reusing Transformer Depth across Queries with Persistent Intermediate Residuals
  232. TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting
  233. TopoFormer: Topology Meets Attention for Graph Learning
  234. Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing
  235. Uncertainty quantification for trustworthy deep learning: Methods and measures
  236. Space2Ground 2.0: A Multi-Source Dataset and Framework for Agricultural Monitoring through Fusion of Street-Level and Satellite Imagery
  237. Agentic Metaverse Services: A New As-a-Service Paradigm
  238. AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge
  239. CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising
  240. Weather Emulators at the Frontier of Heat Extremes Predictability
  241. Causal Discovery with Inverted Self-attention for Multivariate Time Series
  242. UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis
  243. Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data
  244. The MADRS Pipeline: Supporting Depression Assessment in Clinical Trials
  245. Think with Extra-Image: A Farmland Segmentation Agent Driven by Spatio-Temporal Information Gain
  246. Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
  247. Multi-channel Uplift Policy Learning
  248. Integrating AI into Requirements Quality Learning in Software Engineering Education: A TPACK-Guided Empirical Study
  249. Search Strategies for Optimal Classification and Regression Trees
  250. S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image
  251. A Mathematical Framework for Topological Causal Data Analysis
  252. What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study
  253. ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate
  254. Asymmetric Communication: Large Language Models and Language Games
  255. Convolutional Neural Shading for High-Quality 3D Reconstruction from Multi-View Images
  256. Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification
  257. Face and Voice Cross-modal Association with Learning Convex Feature Embedding
  258. ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
  259. Towards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imaging
  260. Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
  261. Challenges in annotations by humans and LLMs: A case study of evaluative language
  262. BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprints
  263. Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training
  264. mmRadarTwin: A Measurement-Calibrated Signal-Level Digital Twin Platform for Indoor mmWave Radar
  265. PCAP-LM: An LLM-Native Text Representation for TLS Bulk Traffic Analysis
  266. An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale
  267. Meteosat Third Generation imagery improves CNN-based SSI retrieval
  268. PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses
  269. Diversifying Personalized Research Ideation against AI-Induced Homogenization
  270. Distilling Answer Set Programming Theories from Large Language Models
  271. GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
  272. On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems
  273. Chem World: A Large-Scale Benchmark and Physics-Informed Framework for Trustworthy Chemical Property Prediction
  274. Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
  275. GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios
  276. Stimulus-Evoked Network Dynamics in Human Cortical Organoids: From a Graph-Computational Framework to Repeated-Stimulation Depression
  277. Landmark shape spaces with induced metrics
  278. IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD
  279. TSOG: A Format For Temporally And Spatially Ordered Gaussians
  280. A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes
  281. TongueReenact: Geometry-Anchored Tongue Synthesis for Face Reenactment
  282. Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers
  283. Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework
  284. Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
  285. MUL-T: Decoding Spatial Cellular Architecture in Multiplexed Tissue Images
  286. Scaling, Lock-In, and Proxy Compliance: A Political Economy of Responsible AI
  287. ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compression
  288. Building a User Foundation Model for the Open Web
  289. Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures
  290. MMLDSum-LLM: Multimodal Long-Document Summarization with Visual-Alignment and Keyword-Aware
  291. Deep learning-based hierarchical insect classification using camera trap imagery
  292. The Noise Premium in Adversarial Training for Kernel Regression
  293. SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
  294. Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
  295. It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
  296. ViP-Rig: Visual-Prompted Controllable Rigging
  297. Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
  298. Now You Have My Healthy Attention: A U-DiT for Brain-MRI Inpainting
  299. FootprintNet: State-Transition-Guided Dynamic Footprint Learning for Multi-temporal Remote Sensing Change Detection
  300. MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation
  301. What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models
  302. Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
  303. SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions
  304. AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization
  305. Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
  306. Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting
  307. Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation
  308. Shapes from Examples: Foundations of Shape Learning in Recursive SHACL
  309. Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting
  310. ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
  311. S-CEReBrO: Breaking the Memory Barrier in Continuous EEG Monitoring
  312. IFHierBench: Hierarchical Instruction Following for Large Language Models
  313. Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances
  314. Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations
  315. One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting
  316. CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration
  317. MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos
  318. Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators
  319. DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection
  320. An Empirical Study of Coordination Mode as the First-Class Citizen in From-Scratch Multi-Agent Coding
  321. Search as Computation Allocation
  322. Learning to Understand Body Language from Flight through Robust 3D Avatar Placing
  323. Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs
  324. ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection
  325. EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits
  326. Benchmarking Foundation and Large Language Models for Few-Shot Medical Image Segmentation
  327. Simplifying Neural Networks During Training
  328. Beyond Feeling Better: Capability-Sustaining Emotional Dialogue as a Longitudinal Research Paradigm
  329. Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design Findings
  330. AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification
  331. Nanoparticle Networks for Neuromorphic Computing
  332. VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection
  333. Virtual Process Dossier: A Process-Aware Data Catalogue
  334. SAFViT: Spatial Attention Fusion Gating for Vision Transformer-Based Nucleus Segmentation and Classification
  335. Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding
  336. Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction
  337. STEREODISCO: Discovering Stereotypicality in LLMs
  338. Deep Learning for Accelerated Long-Horizon Forecasting of Multicomponent Multiphase Microstructure Evolution in High-Entropy Alloys
  339. Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
  340. Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
  341. Learning-Augmented and Randomized Algorithms for Line Aggregation with Delays
  342. LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA
  343. Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches
  344. Can AI Follow In Einstein's Footsteps?
  345. Annotating Topical Legal Insights from Case Proceedings
  346. Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
  347. SpecCal: Ambiguity-Aware Candidate Calibration for Infrared Spectrum-Based Molecular Structure Reconstruction
  348. Fractional Parabolic Partial Differential Equations in Anisotropic Spectral Barron Spaces: Regularity and Neural Approximation
  349. CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography
  350. RIPPLE: Generating Multi-Channel Phase, Not Recovering It
  351. Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold
  352. VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition
  353. Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
  354. Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
  355. Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation
  356. DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis
  357. DAS-PMVC: A Framework for Partial Multi-View Clustering via Dual Alignment and Structure Enhancement
  358. Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
  359. EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder
  360. Articulated Object Reconstruction from Rest-State Observation
  361. A Structured Knowledge Infrastructure for Domain-Specific Data Asset Discovery
  362. ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation
  363. Three-Photon Bayesian Imaging of Ortho-Positronium
  364. Measuring Alignment With Reader Highlights Net of Position and Length
  365. Towards joint scaling laws with optimal batch size schedules
  366. PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation
  367. Error Analysis of Neural-Network-Based Engression
  368. New Synchronous Computation Dynamics for Hopfield Networks
  369. VESTIGE: A Knowledge-Guided Masking Strategy for Corruption-Aware Fine-Tuning of Genomic Transformers, Validated on Ancient DNA Reconstruction
  370. NMINE: Normalized Mutual Information Neural Estimation
  371. MECA: A Mechanism-Centered Agent for Constructing Well-Specified and Valuable Mathematical Conjectures
  372. Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration
  373. LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference
  374. Guiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling
  375. LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents
  376. Evaluating and Pricing Advertisements in AI-Generated Responses
  377. Event-Structured Physics-Informed Neural Networks for Differentiable Critical Clearing Boundaries
  378. Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
  379. Stop Shipping AI Agents on Faith: Capability Is Not Production Readiness
  380. ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring
  381. FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
  382. Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective
  383. Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement
  384. Looped Transformers with Source-Centered State Evolution
  385. Checkpoint Selection and Evaluation in EEG Emotion Recognition
  386. From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models
  387. Held-out evidence resolves follow-up measurement decisions in biological screens
  388. Robust Wavelength Selection for Partial Least Squares Sugar Content Estimation Using Combinatorial Bayesian Optimization
  389. HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
  390. 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
  391. First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selection
  392. SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization
  393. BlindPSNR: A No-Reference Fidelity Predictor for Low-Light Image Enhancement
  394. Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation
  395. Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning
  396. MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging
  397. Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures
  398. MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing
  399. CORE: In-Context Reconstruction for Unified Tabular Anomaly Detection
  400. DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
  401. AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure
  402. Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting
  403. Scalable Graph Coreset Selection via Greedy Sampling
  404. Wiring diagram extraction and gluing: a case study in classifying figure skating jumps using 3D dataset
  405. MeshFM: 2D Features Are All You Need for 3D Shape Understanding
  406. Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs
  407. Is Solving Better Than Evaluating GenAI Solutions?
  408. ZMIS-SAM: Segment Anything Model Enhanced with Wavelet Transform for Zooplankton Microscopy Image Instance Segmentation
  409. MUGEN: A Unified Framework for Efficient Motion Understanding and Generation
  410. From Minds to Models: The Intersection of Psychology and LLM Behaviours
  411. What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering
  412. Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding
  413. Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA
  414. A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography
  415. Strategies for Milestone-driven Start-ups in Multi-activity Settings
  416. Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings
  417. Skill Training with Corruption and Reconstruction Loop
  418. AI and Its Impact on Creativity and Diversity: An Empirical Study of LLM-Generated Product Ideas
  419. AI Literacy: An Exercise in Power-Knowledge
  420. Memory Efficient Tabular Foundation Models
  421. Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory
  422. Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games