mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 19 Oct 2025

188 papers

  1. Agentic AI as Undercover Teammates: Argumentative Knowledge Construction in Hybrid Human-AI Collaborative LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. Diabetes Lifestyle Medicine Treatment Assistance Using Reinforcement LearningDeep reinforcement learning methods → RL for clinical treatment and surgery
  3. Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-MakingMixture-of-experts → MoE theory and gating functions
  4. DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMsLLM reasoning → Mathematical reasoning
  5. TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in EducationLLM agents and tool use → Educational agents and math problem solving
  6. Interpretability Framework for LLMs in Undergraduate CalculusLLM reasoning → Mathematical reasoning
  7. BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code ExecutionLLM safety and security → Jailbreaking
  8. Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  9. L-MoE: End-to-End Training of a Lightweight Mixture of Low-Rank Adaptation ExpertsMixture-of-experts → Mixture of LoRA experts
  10. Hierarchical Federated Unlearning for Large Language ModelsLLM safety and security → Machine unlearning
  11. ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue SystemsLLM agents and tool use → Tool learning and function calling
  12. Video Reasoning without TrainingLLM reasoning → Multimodal reasoning +1
  13. Where, Not What: Compelling Video LLMs to Learn Geometric Causality for 3D-GroundingLLM reasoning → Spatial and embodied reasoning +1
  14. Enrich and Detect: Video Temporal Grounding with Multimodal LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  15. Curiosity-driven RL for symbolic equation solvingDeep reinforcement learning methods → Interpretable and logic-guided RL
  16. Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM UnlearningLLM safety and security → Backdoor and data poisoning attacks
  17. SafeSearch: Do Not Trade Safety for Utility in LLM Search AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  18. Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective PamperingLLM agents and tool use → Software engineering coding agents
  19. Online Learning Defense against Iterative Jailbreak Attacks via Prompt OptimizationLLM safety and security → Jailbreaking
  20. ReclAIm: A Multi-Agent Framework for Monitoring and Correcting Performance Decline in Medical Imaging AILLM agents and tool use → Medical and scientific domain agents
  21. EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog CircuitLLM agents and tool use → Software engineering coding agents
  22. Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMsLLM safety and security → Jailbreaking
  23. Towards Real-Time Generative Speech Restoration with Flow-MatchingDiffusion models → Audio, speech and music
  24. STARK: Strategic Team of Agents for Refining KernelsLLM agents and tool use → Software engineering coding agents
  25. Adaptive Deterministic Flow Matching for Target Speaker ExtractionDiffusion models → Audio, speech and music
  26. Training-free Online Video Step GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  27. One-step Diffusion Models with Bregman Density Ratio MatchingDiffusion models → Diffusion foundations and sampling
  28. Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  29. Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert SignaturesMixture-of-experts → MoE large language models +1
  30. Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed PredictionDiffusion models → Flow matching, time series and science
  31. A Comparative User Evaluation of XRL Explanations using Goal IdentificationDeep reinforcement learning methods → Interpretable and logic-guided RL
  32. Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution InputMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided SearchLLM reasoning → Test-time compute and efficient thinking
  35. VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM AgentsWorld models → World models for language agents +3
  36. Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit FeedbackLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  37. Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer DiagnosisDiffusion models → Medical imaging and segmentation
  38. DeepAnalyze: Agentic Large Language Models for Autonomous Data ScienceLLM agents and tool use → Web, search, and research agents
  39. Uncovering Brain-Like Hierarchical Patterns in Vision-Language Models through fMRI-Based Neural EncodingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  40. Agentic InequalityLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Schr"odinger Bridge Mamba for One-Step Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
  42. From Mannequin to Human: A Pose-Aware and Identity-Preserving Video Generation Framework for Lifelike Clothing DisplayDiffusion models → 3D, point cloud and scene generation
  43. Finding Manifolds With Bilinear AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  44. Improving Model Representation and Reducing KV Cache via Skip Connections with First Value HeadsEfficient LLM inference and serving → KV cache optimization
  45. Black-box Optimization of LLM Outputs by Asking for DirectionsLLM safety and security → Jailbreaking
  46. More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding AgentsLLM agents and tool use → Software engineering coding agents
  47. Segmentation as A Plug-and-Play Capability for Frozen Multimodal LLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  48. Xiaoice: Training-Free Video Understanding via Self-Supervised Spatio-Temporal Clustering of Semantic FeaturesLLM reasoning → Multimodal reasoning +1
  49. EMRRG: Efficient Fine-Tuning Pre-trained X-ray Mamba Networks for Radiology Report GenerationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  50. Region in Context: Text-condition Image editing with Human-like semantic reasoningLLM reasoning → Multimodal reasoning
  51. See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  52. WaMaIR: Image Restoration via Multiscale Wavelet Convolutions and Mamba-based Channel Modeling with Texture EnhancementState-space sequence models (S4, Mamba) → Mamba for image restoration
  53. Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial GamesLLM agents and tool use → Reinforcement learning for LLM agents +1
  54. End-to-end Listen, Look, Speak and ActMixture-of-experts → Multimodal MoE models
  55. ELMM: Efficient Lightweight Multimodal Large Language Models for Multimodal Knowledge Graph CompletionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  56. Visual Autoregressive Models Beat Diffusion Models on Inference Time ScalingLLM reasoning → Diffusion reasoning and test-time scaling +1
  57. A Comprehensive Survey on World Models for Embodied AIWorld models → World models for navigation
  58. Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World ModelsWorld models → World models for autonomous driving +1
  59. A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and ApplicationsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  60. Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  61. DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the EdgeKnowledge distillation → Federated, robust and private distillation
  62. Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph SummarizationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  63. SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D ScenesLLM reasoning → Spatial and embodied reasoning
  64. HumanCM: One Step Human Motion PredictionDiffusion models → Video generation
  65. Rotation, Scale, and Translation Resilient Black-box Fingerprinting for Intellectual Property Protection of EaaS ModelsLLM safety and security → Watermarking generated content and models
  66. An Agentic Framework with LLMs for Solving Complex Vehicle Routing ProblemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. Resolution-Aware Retrieval Augmented Zero-Shot ForecastingRetrieval-augmented generation → Time series and agricultural RAG
  68. Pursuing Minimal Sufficiency in Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  69. Investigating the Impact of Rationales for LLMs on Natural Language UnderstandingLLM reasoning → Prompting and chain-of-thought reasoning
  70. Evaluating protein binding interfaces with PUMBAState-space sequence models (S4, Mamba) → Core SSM architectures for language
  71. Architect in the Loop Agentic Hardware Design and Verification
  72. The Impact of Concept Explanations and Interventions on Human-Machine Collaboration
  73. Cultural Prompting Improves the Empathy and Cultural Responsiveness of GPT-Generated Therapy Responses
  74. Matrix Phylogeny: Compact Spectral Fingerprints for Trap-Robust Preconditioner Selection
  75. Mismatch reconstruction theory for unknown measurement matrix in imaging through multimode fiber bending
  76. EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
  77. Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics
  78. NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
  79. Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models
  80. Learning Time-Varying Graphs from Incomplete Graph Signals
  81. Activation Manifold Projection: Liberating Task-Specific Behaviors from LLM Architectures
  82. The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications
  83. Automated Algorithm Design for Auto-Tuning Optimizers
  84. Conformal Lesion Segmentation for 3D Medical Images
  85. Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism
  86. How Universal Are SAM2 Features?
  87. Person Re-Identification via Generalized Class Prototypes
  88. Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
  89. Click, Predict, Trust: Clinician-in-the-Loop AI Segmentation for Lung Cancer CT-Based Prognosis within the Knowledge-to-Action Framework
  90. DINO-CVA: A Multimodal Goal-Conditioned Vision-to-Action Model for Autonomous Catheter Navigation
  91. Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
  92. Conditional Synthetic Live and Spoof Fingerprint Generation
  93. Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models
  94. CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification
  95. Do Satellite Tasks Need Special Pretraining?
  96. DiscoTrack: A Multilingual LLM Benchmark for Discourse Tracking
  97. An empirical study of the effect of video encoders on Temporal Video Grounding
  98. Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic
  99. Graph4MM: Weaving Multimodal Learning with Structural Information
  100. CARE: Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams
All 188
  1. Back to Bytes: Revisiting Tokenization Through UTF-8
  2. When to Transfer: Adaptive Source Selection for Positive Transfer in Linear Models
  3. Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection
  4. MuonBP: Faster Muon via Block-Periodic Orthogonalization
  5. Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision
  6. Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees
  7. Foundation Models in Medical Image Analysis: A Systematic Review and Meta-Analysis
  8. Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models
  9. Unlocking Off-the-Grid Sparse Recovery with Unlimited Sensing: Simultaneous Super-Resolution in Time and Amplitude
  10. Peering Inside the Black Box: Uncovering LLM Errors in Optimization Modelling through Component-Level Evaluation
  11. A Primer on Kolmogorov-Arnold Networks (KANs) for Probabilistic Time Series Forecasting
  12. A Topological Approach to Parameterizing Deep Hedging Networks
  13. Prediction-Augmented Trees for Reliable Statistical Inference
  14. Tutoring LLM into a Better CUDA Optimizer
  15. Prompt-MII: Meta-Learning Instruction Induction for LLMs
  16. ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models
  17. Closing the Curvature Gap: Full Transformer Hessians
  18. UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
  19. SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
  20. Domain Generalizable Continual Learning
  21. Beyond RGB: Leveraging Vision Transformers for Thermal Weapon Segmentation
  22. A Lightweight DL Model for Smart Grid Power Forecasting with Feature and Resolution Mismatch
  23. Epistemic Memory: A Validity Layer for Self-Maintaining Intelligent Systems
  24. Adaptive Online Learning with LSTM Networks for Energy Price Prediction
  25. DeepChem Equivariant: SE(3)-Equivariant Support in an Open-Source Molecular Machine Learning Library
  26. Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
  27. Contrail-to-Flight Attribution Using Ground Visible Cameras and Flight Surveillance Data
  28. UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
  29. Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
  30. Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
  31. Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
  32. BARL: Bilateral Alignment in Representation and Label Spaces for Semi-Supervised Volumetric Medical Image Segmentation
  33. DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization
  34. ArmFormer: Lightweight Transformer Architecture for Real-Time Multi-Class Weapon Segmentation and Classification
  35. Neuronal Group Communication for Efficient Neural representation
  36. FinSight: Towards Real-World Financial Deep Research
  37. 2DGS-R: Revisiting the Normal Consistency Regularization in 2D Gaussian Splatting
  38. Robust Cross-Domain Adaptation in Texture Features Transferring for Wood Chip Moisture Content Prediction
  39. Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy
  40. Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation
  41. ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
  42. ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
  43. Cross-Genre Authorship Attribution via LLM-Based Retrieve-and-Rerank
  44. Trace Regularity PINNs: Enforcing H^frac12(partial Omega) for Boundary Data
  45. Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator
  46. Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities
  47. Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcity
  48. Graph Learning Is Suboptimal in Causal Bandits
  49. When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation
  50. Computational Budget Should Be Considered in Data Selection
  51. Mixed-Precision Quantization for Language Models: Techniques and Prospects
  52. Domain-Contextualized Concept Graphs: A Computable Framework for Knowledge Representation
  53. An RGB-D Image Dataset for Lychee Detection and Maturity Classification for Robotic Harvesting
  54. MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning
  55. Personalized Image Filter: Mastering Your Photographic Style
  56. Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry
  57. LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding
  58. Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games
  59. 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
  60. GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation
  61. Learning to play: A Multimodal Agent for 3D Game-Play
  62. SAMOSA: Sharpness Aware Minimization for Open Set Active learning
  63. Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
  64. On Robust Hypothesis Testing with respect to the Hellinger Distance
  65. An Efficient Semantic Segmentation Decoder for In-Car or Distributed Applications
  66. Kernel-Based Nonparametric Tests For Shape Constraints
  67. Zero-Shot Performance Prediction for Probabilistic Scaling Laws
  68. Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration
  69. A Control-Theoretic Approach to Dynamic Payment Routing for Success Rate Optimization
  70. UKANFormer: Noise-Robust Semantic Segmentation for Coral Reef Mapping via a Kolmogorov-Arnold Network-Transformer Hybrid
  71. Local regression on path spaces with signature metrics
  72. Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models
  73. LSTM-Based Forecasting and Analysis of EV Charging Demand in a Dense Urban Campus
  74. U-Codec: Ultra Low Frame-rate Neural Speech Codec for Fast High-fidelity Speech Generation
  75. so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs
  76. The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models
  77. Natural Language Processing for Cardiology: A Narrative Review
  78. Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
  79. On the Granularity of Causal Effect Identifiability
  80. SDPA++: A General Framework for Self-Supervised Denoising with Patch Aggregation
  81. CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning
  82. High-Dimensional Privacy-Utility Dynamics of Noisy Stochastic Gradient Descent on Least Squares
  83. Structured yet Bounded Temporal Understanding in Large Language Models
  84. Filtering of Small Components for Isosurface Generation
  85. Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers
  86. Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory
  87. Infinite Neural Operators: Gaussian processes on functions
  88. All You Need is One: Capsule Prompt Tuning with a Single Vector