mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sun 21 Sep 2025

197 papers

  1. Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
  2. Influence Guided Context Selection for Effective Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  3. A Statistical Mixture-of-Experts Framework for EMG Artifact Removal in EEG: Empirical Insights and a Proof-of-Concept ApplicationMixture-of-experts → Medical and biomedical MoE
  4. Probabilistic Token Alignment for Large Language Model FusionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. Mind the Gap: Comparing Model- vs Agentic-Level Red Teaming with Action-Graph Observability on GPT-OSS-20BLLM agents and tool use → Agent threats, guardrails and governance +1
  6. Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle AcceleratorLLM agents and tool use → Web, search, and research agents
  7. Graph Signal Generative Diffusion ModelsDiffusion models → Flow matching, time series and science
  8. Scalable Multi Agent Diffusion Policies for Coverage ControlDiffusion models → Diffusion and flow policies for robotics
  9. TraceHiding: Scalable Machine Unlearning for Mobility DataLLM safety and security → Machine unlearning
  10. Can Agents Judge Systematic Reviews Like Humans? Evaluating SLRs with LLM-based Multi-Agent SystemLLM agents and tool use → Web, search, and research agents
  11. MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoELLM reasoning → Test-time compute and efficient thinking +1
  12. DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D ReconstructionDiffusion models → 3D, point cloud and scene generation
  13. Ratatouille: Imitation Learning Ingredients for Real-world Social Robot NavigationOffline RL and imitation learning from data → Imitation learning methods
  14. SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal ProcessingLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. VaseVQA: Multimodal Agent and Benchmark for Ancient Greek PotteryLLM agents and tool use → Multimodal and embodied agents
  16. LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  17. FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual QuestionsLLM reasoning → Multimodal reasoning
  18. SynergyNet: Fusing Generative Priors and State-Space Models for Facial Beauty PredictionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  19. SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic AnalysisLLM agents and tool use → Medical and scientific domain agents
  20. ARE: Scaling Up Agent Environments and EvaluationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. Imagine2Act: Leveraging Object-Action Motion Consistency from Imagined Goals for Robotic ManipulationLLM reasoning → Spatial and embodied reasoning
  22. Stencil: Subject-Driven Generation with Context GuidanceDiffusion models → Image generation, text-to-image and editing
  23. MCTS-EP: Empowering Embodied Planning with Online Preference OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  24. CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative PerceptionMixture-of-experts → Vision mixture-of-experts
  25. AlignedGen: Aligning Style Across Generated ImagesDiffusion models → Image generation, text-to-image and editing
  26. CoPlanner: An Interactive Motion Planner with Contingency-Aware Diffusion for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  27. Localizing Malicious Outputs from CodeLLMLLM safety and security → Backdoor and data poisoning attacks
  28. Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly DetectionDiffusion models → Diffusion and flow policies for robotics
  29. RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical RerankingRetrieval-augmented generation → RAG for recommendation
  30. RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation EnvironmentsOffline RL and imitation learning from data → Robot manipulation imitation learning
  31. FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation TasksOffline RL and imitation learning from data → Robot manipulation imitation learning
  32. Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy LearningEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
  33. From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image ReasoningLLM reasoning → Multimodal reasoning +1
  34. Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning SignalsLLM reasoning → Test-time compute and efficient thinking
  35. Advancing Speech Understanding in Speech-Aware Language Models with GRPOLLM reasoning → Reinforcement learning for reasoning
  36. Penalizing Boundary Activation for Object Completeness in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  37. Preference Distillation via Value based Reinforcement LearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous DrivingLLM safety and security → Prompt injection and agent security
  39. Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  40. K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge DecouplingLLM reasoning → Test-time compute and efficient thinking
  41. ME-Mamba: Multi-Expert Mamba with Efficient Knowledge Capture and Fusion for Multimodal Survival AnalysisState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  42. Temporal-Aware User Behaviour Simulation with Large Language Models for Recommender SystemsLLM agents and tool use → Agentic recommender systems
  43. LLMs as Layout Designers: Enhanced Spatial Reasoning for Content-Aware Layout GenerationLLM reasoning → Spatial and embodied reasoning
  44. Can GRPO Boost Complex Multimodal Table Understanding?LLM reasoning → Knowledge- and tool-augmented reasoning
  45. Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE AdaptationMixture-of-experts → Mixture of LoRA experts
  46. DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software SystemsLLM safety and security → Jailbreaking
  47. seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMsLLM reasoning → Test-time compute and efficient thinking
  48. AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered SoftwareLLM safety and security → Jailbreaking
  49. Towards an Adaptive Social Game-Playing Robot: An Offline Reinforcement Learning-Based FrameworkOffline RL and imitation learning from data → Offline RL algorithms
  50. ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix CachingEfficient LLM inference and serving → KV cache optimization
  51. Improving S&P 500 Volatility Forecasting through Regime-Switching Methods
  52. Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset
  53. LEMs: A Primer On Large Execution Models
  54. STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
  55. Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
  56. Are you sure? Measuring models bias in content moderation through uncertainty
  57. Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments
  58. A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised
  59. Data-driven approach to the design of complexing agents for trivalent transuranium elements
  60. Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs
  61. MDF-MLLM: Deep Fusion Through Cross-Modal Feature Alignment for Contextually Aware Fundoscopic Image Classification
  62. R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning
  63. MARS: A Malignity-Aware Backdoor Defense in Federated Learning
  64. Lightweight MobileNetV1+GRU for ECG Biometric Authentication: Federated and Adversarial Evaluation
  65. AUWave: A Data-Driven Model for Reconstructing Significant Wave Heights Using Sparse Observations
  66. Neural Network Based Framework for Passive Intermodulation Cancellation in MIMO Systems
  67. Similarity Field Theory: A Mathematical Framework for Intelligence
  68. nDNA -- the Semantic Helix of Artificial Cognition
  69. Change in Quantitative Bipolar Argumentation: Sufficient, Necessary, and Counterfactual Explanations
  70. Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations
  71. Joint Cooperative and Non-Cooperative Localization in WSNs with Distributed Scaled Proximal ADMM Algorithms
  72. Variational Task Vector Composition
  73. Event-Based Visual Teach-and-Repeat via Fast Fourier-Domain Cross-Correlation
  74. Automated Facility Enumeration for Building Compliance Checking using Door Detection and Large Language Models
  75. Task-Oriented Communications for 3D Scene Representation: Balancing Timeliness and Fidelity
  76. Training the next generation of physicians for artificial intelligence-assisted clinical neuroradiology: ASNR MICCAI Brain Tumor Segmentation (BraTS) 2025 Lighthouse Challenge education platform
  77. From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?
  78. Learning and Optimization with 3D Orientations
  79. Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing
  80. Optimized Learned Image Compression for Facial Expression Recognition
  81. Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization
  82. Extending Automatic Machine Translation Evaluation to Book-Length Documents
  83. SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
  84. Prospective Multi-Graph Cohesion for Multivariate Time Series Anomaly Detection
  85. Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness
  86. AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
  87. MirrorSAM2: Segment Mirror in Videos with Depth Perception
  88. Virtual Consistency for Audio Editing
  89. High Resolution UDF Meshing via Iterative Networks
  90. Prompt-Based Simplification for Plain Language using Spanish Language Models
  91. Active Learning for Machine Learning Driven Molecular Dynamics
  92. Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
  93. Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
  94. Conditional Policy Generator for Dynamic Constraint Satisfaction and Optimization
  95. Evolution of Concepts in Language Model Pre-Training
  96. Shall We Play a Game? Language Models for Open-ended Wargames
  97. Echo-Path: Pathology-Conditioned Echo Video Generation
  98. Ambiguous Medical Image Segmentation Using Diffusion Schr"odinger Bridge
  99. Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling
  100. PMRT: A Training Recipe for Fast, 3D High-Resolution Aerodynamic Prediction
All 197
  1. Regularizing Extrapolation in Causal Inference
  2. Attention Consistency for LLMs Explanation
  3. A Comprehensive Performance Comparison of Traditional and Ensemble Machine Learning Models for Online Fraud Detection
  4. Detecting Urban PM2.5 Hotspots with Mobile Sensing and Gaussian Process Regression
  5. Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks
  6. StyGazeTalk: Learning Stylized Generation of Gaze and Head Dynamics
  7. Time Series Forecasting Using a Hybrid Deep Learning Method: A Bi-LSTM Embedding Denoising Auto Encoder Transformer
  8. Unrolled Graph Neural Networks for Constrained Optimization
  9. Data-efficient Kernel Methods for Learning Hamiltonian Systems
  10. Flow-Induced Diagonal Gaussian Processes
  11. On the Simplification of Neural Network Architectures for Predictive Process Monitoring
  12. MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
  13. SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLM
  14. Delay compensation of multi-input distinct delay nonlinear systems via neural operators
  15. ScenGAN: Attention-Intensive Generative Model for Uncertainty-Aware Renewable Scenario Forecasting
  16. GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimization
  17. The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment
  18. Uncertainty-Supervised Interpretable and Robust Evidential Segmentation
  19. Machine Learning for Campus Energy Resilience: Clustering and Time-Series Forecasting in Intelligent Load Shedding
  20. Prompt-with-Me: in-IDE Structured Prompt Management for LLM-Driven Software Engineering
  21. Ultra-short-term solar power forecasting by deep learning and data reconstruction
  22. DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning
  23. On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark
  24. SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions
  25. Governing Automated Strategic Intelligence
  26. SFN-YOLO: Towards Free-Range Poultry Detection via Scale-aware Fusion Networks
  27. MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors
  28. HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis
  29. A Dual-Modulation Framework for RGB-T Crowd Counting via Spatially Modulated Attention and Adaptive Fusion
  30. Enhanced Detection of Tiny Objects in Aerial Images
  31. Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models
  32. CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner
  33. TSGym: Design Choices for Deep Multivariate Time-Series Forecasting
  34. From domain-landmark graph learning to problem-landmark graph generation
  35. TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?
  36. Enhancing Performance and Calibration in Quantile Hyperparameter Optimization
  37. Geodesic Prototype Matching via Diffusion Maps for Interpretable Fine-Grained Recognition
  38. Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
  39. Modeling Bottom-up Information Quality during Language Processing
  40. A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
  41. AgriDoctor: A Multimodal Intelligent Assistant for Agriculture
  42. Towards Generalized Synapse Detection Across Invertebrate Species
  43. KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration
  44. Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
  45. The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs
  46. Efficient 3D Scene Reconstruction and Simulation from Sparse Endoscopic Views
  47. When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
  48. VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module
  49. DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks
  50. DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment
  51. Persistence Spheres: Bi-continuous Representations of Persistence Diagrams
  52. PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
  53. A Cross-Hierarchical Difference Feature Fusion Network Based on Multiscale Encoder-Decoder for Hyperspectral Change Detection
  54. VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
  55. Leveraging Multiple Speech Enhancers for Non-Intrusive Intelligibility Prediction for Hearing-Impaired Listeners
  56. Optimal Transport for Handwritten Text Recognition in a Low-Resource Regime
  57. Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
  58. Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watching
  59. The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA
  60. LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
  61. Graph Coloring for Multi-Task Learning
  62. Quantum Abduction: A New Paradigm for Reasoning under Uncertainty
  63. MO R-CNN: Multispectral Oriented R-CNN for Object Detection in Remote Sensing Image
  64. VidCLearn: A Continual Learning Approach for Text-to-Video Generation
  65. Quantum Adaptive Self-Attention for Financial Rebalancing: An Empirical Study on Automated Market Makers in Decentralized Finance
  66. AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
  67. Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation
  68. Prototype-Based Pseudo-Label Denoising for Source-Free Domain Adaptation in Remote Sensing Semantic Segmentation
  69. SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
  70. NeuFACO: Neural Focused Ant Colony Optimization for Traveling Salesman Problem
  71. Adaptive Graph Convolution and Semantic-Guided Attention for Multimodal Risk Detection in Social Networks
  72. Parameter-efficient fine-tuning (PEFT) of Vision Foundation Models for Atypical Mitotic Figure Classification
  73. Equip Pre-ranking with Target Attention by Residual Quantization
  74. Auditability and the Landscape of Distance to Multicalibration
  75. Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment
  76. Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation
  77. PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control
  78. Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
  79. CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages
  80. SLAM-Former: Putting SLAM into One Transformer
  81. CLaC at DISRPT 2025: Hierarchical Adapters for Cross-Framework Multi-lingual Discourse Relation Classification
  82. FedEL: Federated Elastic Learning for Heterogeneous Devices
  83. The Complexity of Finding Local Optima in Contrastive Learning
  84. PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion
  85. DRES: Fake news detection by dynamic representation and ensemble selection
  86. Learning from Gene Names, Expression Values and Images: Contrastive Masked Text-Image Pretraining for Spatial Transcriptomics Representation Learning
  87. Rethinking Evaluation of Infrared Small Target Detection
  88. SAM-DCE: Addressing Token Uniformity and Semantic Over-Smoothing in Medical Segmentation
  89. Multi-task Pretraining for Enhancing Interpretable L2 Pronunciation Assessment
  90. Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
  91. mathttM3VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation
  92. PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction
  93. Large Language Models as End-to-end Combinatorial Optimization Solvers
  94. ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM
  95. LVADNet3D: A Deep Autoencoder for Reconstructing 3D Intraventricular Flow from Sparse Hemodynamic Data
  96. The Principles of Human-like Conscious Machine
  97. ISCS: Parameter-Guided Feature Pruning for Resource-Constrained Embodied Perception