mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 18 Jan 2026

186 papers

  1. Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic WebLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. LOGOS-CA: A Cellular Automaton Using Natural Language as State and RuleLLM reasoning → Reasoning for agents, planning and code
  3. RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-MakingLLM agents and tool use → Multimodal and embodied agents
  4. Linear Mechanisms for Spatiotemporal Reasoning in Vision Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  5. Disagreement as Data: Reasoning Trace Analytics in Multi-Agent SystemsLLM reasoning → Reasoning for agents, planning and code +1
  6. A Cloud-based Multi-Agentic Workflow for ScienceLLM agents and tool use → Web, search, and research agents
  7. Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with f-SoftArgmax Parameterization & Coupled RegularizationDeep reinforcement learning methods → RL theory and sample complexity
  8. Do MLLMs See What We See? Analyzing Visualization Literacy Barriers in AI SystemsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  9. Primate-like perceptual decision making emerges through deep recurrent reinforcement learningDeep reinforcement learning methods → Deep RL algorithms and representations
  10. Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective AgentsLLM reasoning → Reasoning for agents, planning and code +2
  12. Improving Low-Resource Machine Translation via Round-Trip Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  13. Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic CognitionLLM agents and tool use → Software engineering coding agents
  14. DoPE: Decoy Oriented Perturbation Encapsulation Human-Readable, AI-Hostile Documents for Academic IntegrityMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  15. Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition BottleneckLLM reasoning → Knowledge- and tool-augmented reasoning
  16. Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language AdaptationMultimodal LLMs / vision-language models → Medical vision-language models
  17. Incentivizing In-depth Reasoning over Long Contexts with Process Advantage ShapingLLM reasoning → Test-time compute and efficient thinking
  18. TrojanPraise: Jailbreak LLMs via Benign Fine-TuningLLM safety and security → Jailbreaking
  19. AgenTRIM: Tool Risk Mitigation for Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  20. Large Language Model for OWL ProofsLLM reasoning → Reasoning benchmarks and evaluation
  21. Adversarial Defense in Vision-Language Models: An OverviewMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  22. System-Mediated Attention Imbalances Make Vision-Language Models Say YesMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  23. ReWorld: Multi-Dimensional Reward Modeling for Embodied World ModelsWorld models → Embodied and robot world models +1
  24. Orthogonalized Policy Optimization:Policy Optimization as Orthogonal Projection in Hilbert SpaceLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  25. Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image GenerationDeep reinforcement learning methods → RL with diffusion and flow models
  26. Learning Diverse Skills for Behavior Models with Mixture of ExpertsOffline RL and imitation learning from data → Robot manipulation imitation learning
  27. Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene GenerationDiffusion models → 3D, point cloud and scene generation
  28. LR-DWM: Efficient Watermarking for Diffusion Language ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  29. Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert TaxonomiesLLM agents and tool use → Web, search, and research agents
  30. Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMsLLM safety and security → Prompt injection and agent security
  31. From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous VehiclesEnd-to-end autonomous driving → Large language models for driving +1
  32. Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion ModelsDiffusion models → Audio, speech and music
  33. Mind the Gap: Action Rebinding Attacks against Android GUI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  34. MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  35. Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving EncryptionRetrieval-augmented generation → Privacy and security of RAG
  36. FlowIID: Single-Step Intrinsic Image Decomposition via Latent Flow MatchingDiffusion models → Flow matching, time series and science
  37. MARO: Learning Stronger Reasoning from Social InteractionLLM reasoning → Reasoning for agents, planning and code
  38. Explanova: Automatically Discover Data Insights in N × M Table via XAI Combined LLM WorkflowLLM agents and tool use → Web, search, and research agents
  39. GazeFormer-MoE: Context-Aware Gaze Estimation via CLIP and MoE TransformerMixture-of-experts → Vision mixture-of-experts
  40. Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated SelectionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  41. Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent BaselineLLM reasoning → Reasoning for agents, planning and code +1
  42. A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  43. Facet-Aware Multi-Head Mixture-of-Experts Model with Text-Enhanced Pre-training for Sequential RecommendationMixture-of-experts → MoE for recommender systems
  44. ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using AgentsLLM reasoning → Reinforcement learning for reasoning +2
  45. Conversational Context Classification: A Representation Engineering ApproachMechanistic interpretability → Knowledge and representations inside LLMs
  46. SDiT: Semantic Region-Adaptive for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  47. An Efficient and Multi-Modal Navigation System with One-Step World ModelWorld models → World models for navigation
  48. Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  49. Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model RankersMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  50. Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  51. FutureX-Pro: Extending Future Prediction to High-Value Vertical DomainsLLM agents and tool use → Financial trading and forecasting agents
  52. Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  53. DiffusionQC: Artifact Detection in Histopathology via Diffusion ModelDiffusion models → Medical imaging and segmentation
  54. Speculative Sampling with Reinforcement LearningEfficient LLM inference and serving → Speculative decoding +1
  55. IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking
  56. Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
  57. An Embodied Companion for Visual Storytelling
  58. Exploring Human-in-the-Loop Themes in AI Application Development: An Empirical Thematic Analysis
  59. Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
  60. Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke
  61. IFNSO: Iteration-Free Newton-Schulz Orthogonalization
  62. Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints
  63. Synthetic Student Responses: LLM-Extracted Features for IRT Difficulty Parameter Estimation
  64. Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation
  65. Construct, Align, and Reason: Large Ontology Models for Enterprise Knowledge Management
  66. Stablecoin Design with Adversarial-Robust Multi-Agent Systems via Trust-Weighted Signal Aggregation
  67. Analyzing the Temporal Factors for Anxiety and Depression Symptoms with the Rashomon Perspective
  68. Prometheus Mind: Retrofitting Memory to Frozen Language Models
  69. An Optimized Decision Tree-Based Framework for Explainable IoT Anomaly Detection
  70. Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding
  71. DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
  72. Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approach
  73. Learning Deterministic Finite-State Machines from the Prefixes of a Single String is NP-Complete
  74. Creating Disability Story Videos with Generative AI: Motivation, Expression, and Sharing
  75. Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations
  76. What Trace Powers Reveal About Log-Determinants: Closed-Form Estimators, Certificates, and Failure Modes
  77. HERMES: A Unified Open-Source Framework for Realtime Multimodal Physiological Sensing, Edge AI, and Intervention in Closed-Loop Smart Healthcare Applications
  78. onepot CORE -- an enumerated chemical space to streamline drug discovery, enabled by automated small molecule synthesis and AI
  79. SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition
  80. Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization
  81. SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training
  82. A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schr"odinger Equations
  83. Ontology-aligned structuring and reuse of multimodal materials data and workflows towards automatic reproduction
  84. Camera Pose Revisited
  85. Life, Machine Learning, and the Search for Habitability: Predicting Biosignature Fluxes for the Habitable Worlds Observatory
  86. Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
  87. Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
  88. PISE: Physics-Anchored Semantically-Enhanced Deep Computational Ghost Imaging for Robust Low-Bandwidth Machine Perception
  89. Benchmarking Concept-Spilling Across Languages in LLMs
  90. How Clinicians Think and What AI Can Learn From It
  91. Press Start to Charge: Videogaming the Online Centralized Charging Scheduling Problem
  92. Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery
  93. MemeLens: Multilingual Multitask VLMs for Memes
  94. Encoding Emotion Through Self-Supervised Eye Movement Reconstruction
  95. BirdsEye-RU: A Dataset For Detecting Faces from Overhead Images
  96. XRefine: Attention-Guided Keypoint Match Refinement
  97. Deep Feature Deformation Weights
  98. Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging
  99. Approximating splits for decision trees quickly in sparse data streams
  100. Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks
All 186
  1. Cooperative Multi-agent RL with Communication Constraints
  2. Fine-Tuning Cycle-GAN for Domain Adaptation of MRI Images
  3. CoLR-Det: Collaborative Latent Restoration for Small Object Detection in Low-Resolution Remote Sensing Images
  4. Semidefinite Programming for Quantum Channel Learning
  5. Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods
  6. Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs
  7. A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding
  8. NeuralFur: Animal Fur Reconstruction From Multi-View Images
  9. Capability-Aware Early-Stage Research Idea Evaluation
  10. Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
  11. DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors
  12. Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting
  13. Large-scale EM Benchmark for Multi-Organelle Instance Segmentation in the Wild
  14. Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees
  15. Constraint-Aware Neurosymbolic Uncertainty Quantification with Bayesian Deep Learning for Scientific Discovery
  16. Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition
  17. Temporal Data and Short-Time Averages Improve Multiphase Mass Flow Metering
  18. SkeFi: Cross-Modal Knowledge Transfer for Wireless Skeleton-Based Action Recognition
  19. Graph Attention Networks with Physical Constraints for Anomaly Detection
  20. HOT-POT: Optimal Transport for Sparse Stereo Matching
  21. Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification
  22. Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimation
  23. De-Anonymization at Scale via Tournament-Style Attribution
  24. Explainable Machine Learning for Pediatric Dental Risk Stratification Using Socio-Demographic Determinants
  25. Weaknesses of Facial Emotion Recognition Systems
  26. BiCoLoR: Communication-Efficient Optimization with Bidirectional Compression and Local Training
  27. Psych=eChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
  28. NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages
  29. A Hierarchical Benchmark of Foundation Models for Dermatology
  30. Statistical-Neural Interaction Networks for Interpretable Mixed-Type Data Imputation
  31. Utilizing the Score of Data Distribution for Hyperspectral Anomaly Detection
  32. LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G
  33. A Scalable Entity-Based Framework for Auditing Bias in Large Language Models
  34. CD-TWINSAFE: A ROS-enabled Digital Twin for Scene Understanding and Safety Emerging V2I Technology
  35. DepthCropSeg++: Scaling a Crop Segmentation Foundation Model With Depth-Labeled Data
  36. Machine Learning-Based Framework for Real Time Detection and Early Prediction of Control Valve Stiction in Industrial Control Systems
  37. SimpleMatch: A Simple and Strong Baseline for Semantic Correspondence
  38. Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
  39. Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios
  40. How Well Do LLMs Predict Human Behavior? A Measure of their Pretrained Knowledge
  41. Time-Continuous Modeling for Temporal Affective Pattern Recognition in LLMs
  42. Actionable Advice from Reviews via Mixture of LoRA Experts: A Two-LLM Pipeline for Issue Extraction and Business Recommendations
  43. Turbo-GoDec: Exploiting the Cluster Sparsity Prior for Hyperspectral Anomaly Detection
  44. IceWatch: Forecasting Glacial Lake Outburst Floods (GLOFs) using Multimodal Deep Learning
  45. The Expert Validation Framework (EVF): Enabling Domain Expert Control in AI Engineering
  46. EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation
  47. Multi-Sensor Matching with HyperNetworks
  48. Ordered Local Momentum for Asynchronous Distributed Learning under Arbitrary Delays
  49. Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence
  50. S^2F-Net:A Robust Spatial-Spectral Fusion Framework for Cross-Model AIGC Detection
  51. CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding
  52. Cross-reality location privacy protection in 6G-enabled vehicular metaverses: an LLM-enhanced hybrid generative diffusion model-based approach
  53. Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification
  54. Machine Learning as a Service (MLaaS) Dataset Generator Framework for IoT Environments
  55. Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
  56. Distribution Shift Is Key to Learning Invariant Prediction
  57. OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigation
  58. ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech
  59. TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization
  60. LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines
  61. CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training
  62. HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding
  63. Predictive Prototyping: Evaluating Design Concepts with ChatGPT
  64. AgenticPruner: MAC-Constrained Neural Network Compression via LLM-Driven Strategy Search
  65. Environment-Aware Code Generation: How far are We?
  66. DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression
  67. Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy
  68. Improving Large Molecular Language Model via Relation-aware Multimodal Collaboration
  69. DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression
  70. Federated Joint Learning for Domain and Class Generalization
  71. Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation
  72. An Innovative Framework for Breast Cancer Detection Using Pyramid Adaptive Atrous Convolution, Transformer Integration, and Multi-Scale Feature Fusion
  73. AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering
  74. Less is More: Label-Guided Efficient Summarization of Procedural and Instructional Videos
  75. Optimal Power Allocation and Sub-Optimal Channel Assignment for Downlink NOMA Systems Using Deep Reinforcement Learning
  76. On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
  77. Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models
  78. Wavelet-Aware Anomaly Detection in Multi-Channel User Logs via Deviation Modulation and Resolution-Adaptive Attention
  79. Learning Longitudinal Health Representations from EHR and Wearable Data
  80. Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion
  81. Persistent Sheaf Laplacian Analysis of Protein Stability and Solubility Changes upon Mutation
  82. Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models
  83. One-Sided Matrix Completion from Ultra-Sparse Samples
  84. CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation
  85. Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks
  86. CTC-DID: CTC-Based Arabic dialect identification for streaming applications