mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 19 Jun 2026

342 papers

  1. Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerfLLM agents and tool use → Software engineering coding agents +1
  2. An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use CaseLLM agents and tool use → Web, search, and research agents
  3. Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid ArchitecturesVision-language-action models → VLA for autonomous driving
  4. Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Prediction in Social Media SimulationLLM agents and tool use → Social simulation and multi-agent debate
  5. DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech SynthesisDiffusion models → Audio, speech and music
  6. Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAGRetrieval-augmented generation → Multimodal RAG
  7. CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  8. Depth-Entropy Guided Sampling for Training-Free LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  9. What Context Does a Coding Agent Actually Need to Act?LLM agents and tool use → Software engineering coding agents
  10. Aligning Sentence Embeddings to Human Concepts via Sparse AutoencodersRetrieval-augmented generation → Generation and context integration +1
  11. LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph RetrievalLLM agents and tool use → Web, search, and research agents
  12. When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  13. Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error CorrectionRetrieval-augmented generation → Conversational and speech RAG
  14. When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  15. Discretizing Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  16. What Do Lorentz-Equivariant Jet Taggers Learn?Mechanistic interpretability → Circuits and mechanistic analysis
  17. CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive TasksLLM agents and tool use → Web, search, and research agents
  18. Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon PlanningWorld models → Latent predictive world models
  19. Motion-Aware Reinforcement Learning For Object LocalizationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. Adversarial Domain Prompt Tuning and Generation for Single Domain GeneralizationDiffusion models → Image generation, text-to-image and editing
  22. HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and ReasoningLLM reasoning → Multimodal reasoning
  23. Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  24. Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  25. PrivacyAlign: Contextual Privacy Alignment for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  26. When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought DistillationLLM reasoning → Test-time compute and efficient thinking
  27. Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World ModelsWorld models → Embodied and robot world models +1
  28. Improving Text-to-Music Generation with Human Preference RewardsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  29. Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM SystemsLLM agents and tool use → Medical and scientific domain agents
  30. ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld TasksLLM agents and tool use → GUI and mobile agents
  31. EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic MemoryLLM agents and tool use → Web, search, and research agents
  32. Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  33. HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache RetrievalEfficient LLM inference and serving → KV cache optimization
  34. CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-TrainingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  35. Counsel: A Meta-Evaluation Dataset for Agentic TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  36. A DVDrive Approach for doScenes Instructed Driving ChallengeEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  37. CulMind: Benchmarking Multimodal Understanding and Reasoning in Chinese Cultural HeritageLLM reasoning → Multimodal reasoning +1
  38. The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  39. CurvSegFlow: Time-Conditioned Flow Matching for Robust Segmentation of Curvilinear Structures in Noisy Biomedical ImagesDiffusion models → Medical imaging and segmentation
  40. T-MOR: Learning Motion-Aware Skeleton Representations for Human Action RecognitionMultimodal LLMs / vision-language models → Video understanding with MLLMs
  41. ATLAS: Agentic Taxonomy of Large-Scale Software EcosystemsLLM agents and tool use → Software engineering coding agents
  42. FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  43. The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake DetectionLLM reasoning → Chain-of-thought reasoning for driving
  44. Robot Critics that Sweat the Small StuffMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  45. Composing Verifiable Conceptual Models via Building Blocks: Towards Design-Time Verification of Agentic AI WorkflowsLLM agents and tool use → Software engineering coding agents
  46. Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B ModelRetrieval-augmented generation → Agentic RAG, agents and memory +1
  47. AI Alignment From Social Choice PerspectivesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  48. Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous ControlDeep reinforcement learning methods → RL with diffusion and flow models
  49. A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  50. Towards Pedagogically Aligned LLM Tutors for Math Mistake RemediationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  51. UniviewVLA: A Unified Multiview Vision-Language-Action Model with World ModelingWorld models → Embodied and robot world models +1
  52. Balancing Performance and Diversity in GRPO Autoregressive Text-to-Image Post-TrainingLLM reasoning → Reinforcement learning for reasoning
  53. Decoupling the Declarative from the Procedural in Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  54. Semi-Supervised Vision-Language-Action ModelVision-language-action models → Generalist VLA models and benchmarks
  55. Post-Training Speech Enhancement Language Models with Perceptual RewardsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  56. CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. Fast-TurboQuant: A Multiplier-Free Online Vector Quantization ApproachEfficient LLM inference and serving → KV cache quantization
  58. AutoRAS: Learning Robust Agentic Systems with Primitive RepresentationsLLM reasoning → Reasoning for agents, planning and code +1
  59. Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical StudyMixture-of-experts → Efficient MoE training and inference systems
  60. MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions for Fine-Grained Vision-Language LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  61. 2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI ModelsDiffusion models → Medical imaging and segmentation
  62. Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM AgentsLLM agents and tool use → Tool learning and function calling
  63. SwarmX: Agentic Scheduling for Low-Latency Agentic SystemsLLM agents and tool use → Software engineering coding agents
  64. Calibration Is Not Control: Why LLM-Agent Oversight Needs InterventionLLM agents and tool use → Software engineering coding agents
  65. BIT-Nav: Brain-Inspired Trajectory Memory for Embodied NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  66. Long-Distance Real-World Navigation of the Legged-Wheeled Robot Go2-W Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  67. VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  68. NAC: Neural Action Codec for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  69. A Reward-Petri-Net Interpretation of Temporal Behavior TreesDeep reinforcement learning methods → Interpretable and logic-guided RL
  70. DataClaw0: Agentic Tailoring Multimodal Data from Raw StreamsLLM agents and tool use → Multimodal and embodied agents
  71. Social World Model for Lifelong Social IntelligenceWorld models → World models for language agents
  72. A Test-time Actor-Critic Approach to News Images GenerationDeep reinforcement learning methods → RL with diffusion and flow models
  73. NASDAQ: Normalized Observation Space Dynamics-Augmented Q-LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  74. Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage MaximizationDeep reinforcement learning methods → Deep RL algorithms and representations
  75. ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  76. Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned TransportDiffusion models → Flow matching, time series and science
  77. Sakana Fugu Technical ReportLLM agents and tool use → General LLM agent frameworks and benchmarks
  78. Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts ApproachMixture-of-experts → Multimodal MoE models
  79. Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse AutoencodersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  80. MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  81. Inverting the Bellman Equation: From Q-Values to World ModelsWorld models → Latent dynamics models and model-based RL +1
  82. BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous DrivingWorld models → World models for autonomous driving +1
  83. Trip+: Benchmarking Agents in Personalized Interactive Travel PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  84. Dementia-Agents: A Multi-Modal Multi-Agent System for Dementia Staging and PhenotypingLLM agents and tool use → Medical and scientific domain agents
  85. OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
  86. Who Checks the Citations? Benchmarking Legal Hallucination DetectionLLM agents and tool use → Medical and scientific domain agents
  87. AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?LLM safety and security → Safety alignment, refusal and guardrails
  88. ChronoLock: Protecting Videos from Unauthorized Text-to-Video PersonalizationDiffusion models → Video generation
  89. AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized AgentsLLM agents and tool use → Agent memory systems
  90. Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  91. Horizon Adaptive Offline Policy Learning via Value StitchingOffline RL and imitation learning from data → Offline RL algorithms
  92. AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  93. A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health ScreeningLLM reasoning → Clinical and biomedical applications +1
  94. MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography DiagnosisLLM reasoning → Clinical and biomedical applications
  95. Incoherent Values? Probing LLM Preferences Through Parametric VariationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  96. Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial GeneralizationDiffusion models → Diffusion and flow policies for robotics
  97. MV-WAM: Manifold-Aware World Action Model with Value AugmentationWorld models → Embodied and robot world models
  98. ReFPO: Reflow Regularization for Flow Matching Policy GradientsDiffusion models → Diffusion and flow policies for robotics +1
  99. Sim2O: Efficient Offline-to-Online MARL via Joint Action CompositionOffline RL and imitation learning from data → Offline multi-agent RL
  100. Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
All 342
  1. Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long ConversationsLLM safety and security → Jailbreaking
  2. OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt OptimizationLLM safety and security → Jailbreaking
  3. Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime LayerLLM agents and tool use → Agent threats, guardrails and governance
  4. Imitation Learning for Elder-Facing Speech SynthesisOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  5. Backdoor Attacks on Speech Emotion Recognition via TTS-Generated PoisoningLLM safety and security → Audio jailbreaks and speech backdoors
  6. Honeyquest for LLMs: Rethinking Cyber Deception for AI AttackersLLM reasoning → Reasoning for agents, planning and code
  7. Diffusion-Driven State Space ModelsDiffusion models → Flow matching, time series and science
  8. MoECodec: Image Compression for joint human and machine perception via Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
  9. FlowCodec: One-Step Flow Prior for Generative Image CompressionDiffusion models → Diffusion for compression and wireless
  10. Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEALEfficient LLM inference and serving → Serving systems and request scheduling
  11. CheXpercept: A Benchmark for Evaluating Expert-Level Lesion Perception in Chest X-raysMultimodal LLMs / vision-language models → Medical vision-language models
  12. BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac SamplingDiffusion models → Diffusion and flow policies for robotics
  13. Agentic Time Machine as an Infrastructure for Future-Event ForecastingLLM agents and tool use → Financial trading and forecasting agents
  14. Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention
  15. Recipes for Steering and Scaling LLMs via Sampling
  16. When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
  17. ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora
  18. Research Paper Quality Recognition Through Textual Feature Analysis
  19. Evaluation of Motivational Interviewing Counsellors with Task-Aware Multi-Stage LLM-Based Simulated Clients
  20. HenTwin: A Multimodal Digital Twin Framework for Longitudinal Biological State Monitoring in Laying Hens
  21. When Kernel Ridge Regression Meets the H"older-Zygmund Class: Minimax Optimality and Failure of Properness
  22. LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation
  23. VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
  24. Overcoming the BCI Calibration Bottleneck: A Clinically-Grounded Architecture using Riemannian Alignment and Stochastic Weight Averaging
  25. International Agreements to Limit Frontier AI: Objectives and Exit
  26. An Empirical Study of Handcrafted Feature Learning and Convolutional Neural Networks for Facial Expression Recognition
  27. Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence
  28. Interpretable Language Model for Closed-Loop Type 1 Diabetes Control
  29. Analysis of Public Schools Educational Performance Based on Causal Models and Hierarchical Clustering
  30. Targeted Recovery of Weight-Space Mechanisms From Neural Networks
  31. Low-Rank Attention Residuals
  32. Reference-Based Distillation Detection in LLMs
  33. Memory-Augmented LSTM Autoencoder for Unsupervised Activity Recognition with IMU Sensor Fusion
  34. Multiscale Exit-Join Dynamics: Tactical Consensus and Strategic Coalition Formation
  35. Velocity Prediction in Automatic Guitar Transcription
  36. Attractive and Repulsive Pattern Control in Sequence Generation
  37. End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
  38. Computational references are not experiments: pre-registered validation of machine-learned sodium-cathode voltages
  39. EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering
  40. Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images
  41. Is Agent Code Less Maintainable Than Human Code?
  42. Test-Time Training with Next-Token Prediction
  43. THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion
  44. Bayesian three-dimensional seismic travel-time tomography for active- and passive-source seismic data using physics-informed neural network
  45. Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation
  46. RocketPFN: Accurate Time Series Classification via In-Context Learning
  47. Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence
  48. A Causal DAG Prior for Synthetic Time-Series Classification Datasets
  49. Decision-Focused Learning: When and Why Traditional Prediction Models Fail
  50. From Gradient Clipping to Structural Refinement: Improving DPSGD for Medical Image Segmentation
  51. AdaPrivate-TS: Private Thompson Sampling for Contextual Bandits with Privacy Amplification
  52. Scaling up fine-grained intracranial vessel annotations in computed tomography angiography
  53. Embedded Polygon Symbolic Transfer Entropy (EPSTE): A Geometric Token and Deep Learning Approach to Estimating Transfer Entropy in Neuroimaging Time Series
  54. Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
  55. Configurable Algorithms for Histopathologic Cancer Detection on Quantum Hardware
  56. Quantile Adaptive Temperature Scaling for Confidence Calibration
  57. Cohort Organized Learning: Clustering Through Agreement
  58. Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling
  59. Entropy Objectives in Markov Decision Processes
  60. Physics-Informed Neural Networks for Computing the Morse Index of the Critical Catenoid
  61. Leveraging LaBSE with Progressive Curriculum Learning for Multicultural Polarization
  62. Edge-Aligned Beam Placement in Scanning Probe Tomography via Reconstruction-Free Sequential Design of Experiments
  63. BatchGen: An Architecture for Scalable and Efficient Batch Inference
  64. Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space
  65. ARCO-Mars: A Unified Cloud-Optimized Archive of Mars Atmosphere Reanalysis
  66. VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation
  67. A Hybrid, Multi-Layered Pipeline for Phishing and Threat Classification: Independently Validated URL and NLP Engines with a Calibrated Multi-Channel Fusion Stage
  68. Clinical Term Extraction using Open-Source Small Language Models
  69. Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity
  70. TACO: Task-Aware Column Description Generation Using LLMs
  71. Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
  72. Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers
  73. Enlight: Fast Low-Light Image Enhancement via Multi-Objective Optimization and Shadow-Aware Refinement
  74. A Framework for Directed Acyclic Hypergraph Learning
  75. UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
  76. Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models
  77. PaaF: Raising the perceived quality of INR-Based Image Compression
  78. When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
  79. A new classification method based on Minimum Spanning Trees
  80. Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
  81. Time-Frequency Weighted Losses for Phoneme Reconstruction in DNN-Based Speech Enhancement
  82. Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment
  83. The Alignment Problem in Constrained Code Generation
  84. LLM and Human Modes of Representation
  85. Cross-Modal Corroboration for Annotation-Free Wildlife Monitoring
  86. μMatch: Foundation Models for Semi-supervised Learning and Domain Adaptation in EM
  87. Learning to Place Guards by Reinforcement: A Geo-Free Neural Policy for the Vertex-Guard Art Gallery Problem
  88. Deep Unrolled Networks in Representation Space Applied to MRI Reconstruction
  89. φ-Scene: Physically Grounded Image-to-3D Scene Reconstruction
  90. Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration
  91. Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts
  92. Geometric and Information Compression of Representations in Deep Learning
  93. Radial Basis Function Networks as Projection Heads in Self-Supervised Learning
  94. Unsupervised Susceptibility Distortion Correction of EPI without Calibration Scans via Image Translation-Based Registration
  95. A Transport-Based Geometry of Belief-Cost
  96. A Smart Classroom Behavior Analysis Framework with a New Highly Congested Classroom Dataset
  97. LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers
  98. Compressing History into Memory: Distilling Transformers into Recurrent Transformers
  99. Rubric-as-Experts: Case-Specific MQM Rubrics for Translation Error Span Detection
  100. PeerMathDial: A Middle School Dialogue Dataset for Student Collaborative Math Problem Solving
  101. Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering
  102. Accelerated and Stable Convergence with Anchored Generalized Optimistic Method
  103. LOGOS: LiDAR-Only Gaussian Elevation Splatting for Unified Tiny Obstacle Segmentation
  104. MedHal-Loc: Are "Explainable-by-Architecture" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark
  105. A Censored Transformed Model for Proportional Outcomes with Boundary Mass and an Application to Loss Given Default Modeling
  106. Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
  107. Privacy-Preserving Federated Temporal Graph Learning with Digital Twin--Guided Adaptive Deception for Cyber-Resilient IoMT
  108. Bayesian model selection of vine copulas: a loss-based perspective
  109. A Skin-Tone-Aware Dual-Representation Remote Photoplethysmography Framework for Contactless Respiratory Rate Estimation
  110. Breaking Chains with Trees: Model-Parallel Deep Learning with O(log N) Time Complexity
  111. Predicting High-Risk Colorectal Polyps in African Americans Using Pre-Colonoscopy Clinical Features: Machine Learning Model Development and Temporal Validation
  112. Robustness Cannot be Reduced to Regularization: Studying Adversarial Training Beyond the Linear Case
  113. Economic Transformation and Cultural Change: Evidence from Two Centuries of French Drama
  114. Deep Learning for Soil Moisture Estimation: Fusing Satellite Data with Optimally-Lagged Meteorological Features
  115. Towards Transparent Mental Health Insights: An Explainable AI Model for Career-Related Depression and Anxiety Among University Students Using Structured Data
  116. ASCII Art Turns LLMs into VLA Controllers
  117. Native space based pipelines outperform template space based pipeline in subcortical segmentation
  118. Evaluation of Small Language Models for Arabic Language Processing
  119. Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Exploring Query-Based Segmentation and Increased Spatial Context for Outdoor Scene Understanding
  120. Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning
  121. Synergistic Dual-Branch Adaptation for Multi-modal Generalized Category Discovery
  122. Fusing Backdoors, Machine Learning, and Optimization for Large-Scale Parametric Mixed-Integer Programs
  123. Universal Encoders for Modular Relational Deep Learning
  124. Central limit theorem for the averaged Adam optimizer
  125. Dual-Attention Convolution Experts for Sparse Tensor Completion
  126. Federated Temporal Attention Intelligence for Cyber-Resilient IoMT: Lightweight Digital Twins and PPO-Driven Honeypot Deception
  127. One Size does not Fit All: Heterogeneous Latent Space Alignment for Unsupervised Domain Adaptation
  128. CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation
  129. Robot Self-Improvement via Human-Video Dynamics Models
  130. Evaluating LLMs for Real-World Web Vulnerability Detection
  131. Atomistic Language Models Understand and Generate Materials
  132. Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
  133. EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis
  134. OSOG: A Differentiable, Physics-Informed Synthetic Data Engine for Micro-Optical Environments
  135. Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework
  136. FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction
  137. Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification
  138. Sexualised synthetic personas encode and amplify gendered power asymmetries through voice
  139. LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
  140. Predictive Repair Management Using a Multi-Head Attention Transformer and Online Learning
  141. Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs
  142. LEViL: Label-Efficient Video Learning via Zero-Shot Distillation over VLM-Generated Pseudo-Label Spaces
  143. SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Training
  144. Urban Power Grid Topology and Hierarchy Identification from Open Data
  145. Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process
  146. Mind the Noise: Sensitivity of Transformer-based Interaction-Aware Trajectory Prediction Models to Noisy Data
  147. An Evaluation Framework for Text-to-Speech Voice Reconstruction
  148. Synthetic Audio Generation Framework for Air Traffic Control Speech Recognition
  149. Direct Raw Audio Signal Processing via Reservoir Computing: An Investigation into 'Feature-Free' Architectures
  150. Ramanujan Graph Rewiring with Non Negative Resistance Curvature
  151. MedTS-TTT: Test-Time Training for Medical Time Series Classification
  152. Sea-Scan: High-Accuracy, ML-based Dark Vessel Detection and Localisation via Weakly Supervised DAS Monitoring
  153. Distinguishing indistinguishable attractors: Unsupervised anomaly detection with reservoir computers
  154. Objective-Behavior Alignment: Diagnostics for MORL Policy Selection
  155. Warning labels shift perceptions of sycophantic AI, but not its influence
  156. WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
  157. Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks
  158. Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessment
  159. LISE : Listenable Interpretable Speaker Embeddings
  160. SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
  161. Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling
  162. Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models
  163. NoduLoCC2026: Lung Nodule Localization and Classification Contest from Chest X-Ray Images
  164. Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers
  165. Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement
  166. Beyond Damage Assessment: Recyclable Material Detection in Aerial Disaster Imagery Using a Lightweight Patch-Based Framework
  167. Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering
  168. Few-Shot Hyperspectral Aphid Detection via FastGAN Synthetic Data Generation, Transformer-Based Classification and Explainable AI
  169. Subsampling for supervised learning in reproducing kernel Hilbert spaces
  170. Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM
  171. An Empirical Study of openPangu Quantization on Ascend NPUs
  172. SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services
  173. Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation
  174. A Neurosymbolic Framework for Interpretable Skeleton-Based Seizure Detection via Concept-Driven Logical Reasoning
  175. Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families
  176. ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting
  177. DIPBox: A Multi-scale Testing Framework for Tracking Dataset Regeneration
  178. Recency/Frequency Adaptive KV Caching for Large Language Model Serving
  179. OpenWER: Improving Cross-Lingual ASR Evaluation and Enabling Token-Based Accuracy Metrics
  180. Context-Aware Autoregressive Diffusion for Gloss-Wise Sign Language Production
  181. Comparative Evaluation of Machine Learning and Deep Learning Models for Wound-Rotor Synchronous Motor Performance Prediction
  182. FleetAgent: Teleoperation Assistant for Autonomous Fleets via Vectorized V2N Messages
  183. QBioFusion-QSAR: Morgan-Anchored Quantum Multiple Kernel Learning for Small-Data Ligand Classification
  184. DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
  185. Arc-Length Parameterized Interpolating Splines
  186. When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs
  187. Communication Heterogeneity and Collective Consensus in Neural Cellular Automata
  188. Whistleblowing and the machine -- towards a considered position
  189. Real-time pedestrian attribute recognition with YOLOv8 and ResNet18
  190. Orthogonal Discrepancy Kernels for Learning with Partial Physics
  191. Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding
  192. TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations
  193. Two Layers of Instability in Causal Estimation
  194. Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy
  195. Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors
  196. HERO: Hypothesis-Driven Evidence Retrieval from Omics for Multi-Task Breast Cancer Analysis
  197. An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game
  198. PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling
  199. Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity
  200. Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
  201. DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
  202. Context-Aware Generative AI for Automated Telecom Test Script Generation
  203. PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
  204. SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection
  205. Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion
  206. Learning Burst-Aware Early Warning Models for Capacity Stress under AI Workload Surges in Hyperscale Data Centers
  207. What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility
  208. PulseCX: Breaking the Closed-World Assumption in Real-Time CX
  209. Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models
  210. ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading
  211. MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems
  212. Object-Centric Dataset Resources for Constrained-Data Image Generation and Augmentation
  213. Chem2Gen-Bench: Benchmarking Chemical-to-Genetic Translation in Perturbation Response Space
  214. SARIF: Segment Anything for Robust Image Forensics
  215. Enhancing Differentially Private Mechanisms via Empirical Bayes
  216. ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging
  217. LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations
  218. GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems
  219. SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
  220. How Should a Robot Configure Its Laser Scanner for Inspection?
  221. BASIL: Bayesian Application for Scientific Iteration and Learning
  222. Bayesian Model Averaging under Predictor Redundancy via Density-Ratio Posterior Compression
  223. Validation-Gated Causal Interventions for Interpreting High-Stakes Large Language Model Behavior: A Case Study in Suicidality Detection
  224. FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling
  225. SqLinear: Balanced Square Partitioning Makes Linear Interaction Sufficient for Large-Scale Traffic Forecasting
  226. Quality and Agreement in Multilabel Emotion Annotation: A Case Study and Evaluation Framework
  227. Demographic Metadata as Construct-Irrelevant Noise in DistilBERT-Based Automated Essay Scoring
  228. Neural Architecture Distributions: A New Paradigm for Stochastic Segmentation
  229. Event Ontology Expansion via LLM-Based Conceptualization
  230. OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals
  231. Self-Supervised Dual-Frequency Phase Decomposition for Single-Shot Composite Fringe Projection Profilometry
  232. Sparse Point-Guided Fusion of Supervised and Self-Supervised Learning Model for Seaweed Segmentation
  233. Negative Knowledge as Failure-aware Shared Memory for AutoResearch
  234. Structure-Aware Graph Multi-Task Learning for Dynamic Sparse OD Demand Prediction
  235. Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting
  236. LK Jam: System Architecture and Implementation of a Real-Time Human-AI Interactive Music Generation System using Role-Aware GRU
  237. The AI Evaluability Gap: The Missing Layer for Managing Risk and Sustaining Value
  238. Closure of Self-Determining System Based on Causal and Constitutive Relations
  239. The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures
  240. Building Agent Harnesses for Scientific Curation from Multimodal Sources
  241. Inductive Generalization for Robotic Manipulation
  242. BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery