mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 20 Sep 2025

189 papers

  1. ReSeFlow: Rectifying SE(3)-Equivariant Policy Learning FlowsDiffusion models → Diffusion and flow policies for robotics
  2. Phrase-grounded Fact-checking for Automatically Generated Chest X-ray ReportsMultimodal LLMs / vision-language models → Medical vision-language models
  3. KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV CacheMultimodal LLMs / vision-language models → Visual token pruning and efficiency +2
  4. Leveraging NTPs for Efficient Hallucination Detection in VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  5. SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  6. ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language ModelsMechanistic interpretability → SAE features and their applications
  7. Learning from Observation: A Survey of Recent AdvancesOffline RL and imitation learning from data → Imitation learning methods
  8. Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-ThoughtLLM reasoning → Spatial and embodied reasoning
  9. DoubleGen: Debiased Generative Modeling of CounterfactualsDiffusion models → Diffusion foundations and sampling
  10. Roundtable Policy: Confidence-Weighted-Consensus Aggregation Improves Multi-Agent-System ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  11. Factorizing Diffusion Policies for Observation Modality PrioritizationDiffusion models → Diffusion and flow policies for robotics
  12. DISCO: Disentangled Communication Steering for Large Language ModelsMechanistic interpretability → Activation steering methods
  13. Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven MediaLLM agents and tool use → Multimodal and embodied agents
  14. Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  15. Controlled Yet Natural: A Hybrid BDI-LLM Conversational Agent for Child Helpline TrainingLLM agents and tool use → Medical and scientific domain agents
  16. Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math TextbookRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  17. MMPart: Harnessing Multi-Modal Large Language Models for Part-Aware 3D GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  18. DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural ImagesDiffusion models → Video generation
  19. Discrete Diffusion Models: Novel Analysis and New Sampler GuaranteesDiffusion models → Diffusion foundations and sampling
  20. Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning TrajectoriesLLM reasoning → Test-time compute and efficient thinking
  21. Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven ApproachLLM agents and tool use → Agent threats, guardrails and governance
  22. Time to Revist Exact MatchLLM reasoning → Knowledge- and tool-augmented reasoning
  23. OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive DramaLLM agents and tool use → Multimodal and embodied agents
  24. Knowledge Distillation for Variational Quantum Convolutional Neural Networks on Heterogeneous DataKnowledge distillation → Graph neural network distillation
  25. InstanceAssemble: Layout-Aware Image Generation via Instance Assembling AttentionDiffusion models → Image generation, text-to-image and editing
  26. EG-MLA: Embedding-Gated Multi-head Latent Attention for Scalable and Efficient LLMsEfficient LLM inference and serving → KV cache optimization
  27. ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question AnsweringLLM reasoning → Multimodal reasoning
  28. Governed By Agents: A Survey On The Role Of Agentic AI In Future Computing EnvironmentsLLM agents and tool use → Software engineering coding agents
  29. MedCutMix: A Data-Centric Approach to Improve Radiology Vision-Language Pre-training with Disease AwarenessMultimodal LLMs / vision-language models → Medical vision-language models
  30. Robust Native Language Identification through Agentic DecompositionLLM agents and tool use → General LLM agent frameworks and benchmarks
  31. NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning AbilitiesLLM reasoning → Spatial and embodied reasoning +1
  32. Are VLMs Ready for Lane Topology Awareness in Autonomous Driving?LLM reasoning → Chain-of-thought reasoning for driving +2
  33. FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied AgentsLLM reasoning → Reasoning for agents, planning and code +2
  35. When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  36. Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-TuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic SurgeryMultimodal LLMs / vision-language models → Medical vision-language models
  38. PruneCD: Contrasting Pruned Self Model to Improve Decoding FactualityEfficient LLM inference and serving → Speculative decoding
  39. MCP: A Control-Theoretic Orchestration Framework for Synergistic Efficiency and Interpretability in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  40. Question Answering with LLMs and Learning from Answer SetsLLM reasoning → Reasoning benchmarks and evaluation
  41. Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild DataLLM reasoning → Audio-language model reasoning
  42. Zero-Shot Human Mobility Forecasting via Large Language Model with Hierarchical ReasoningLLM reasoning → Spatial and embodied reasoning
  43. SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  44. Captioning for Text-Video Retrieval via Dual-Group Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  45. Rethinking the Role of Text Complexity in Language Model PretrainingLLM reasoning → Reasoning benchmarks and evaluation
  46. Efficient Rectified Flow for Image FusionDiffusion models → Image generation, text-to-image and editing
  47. SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward LearningLLM reasoning → Reinforcement learning for reasoning +1
  48. ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic InstructionsSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  49. VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual AnalysisMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  50. CAF'E: Causal Black-Box Testing of Machine UnlearningLLM safety and security → Machine unlearning
  51. FG-Attn: Leveraging Fine-Grained Sparse Attention in Video Diffusion ModelsDiffusion models → Video generation
  52. Seeing Culture: A Benchmark for Visual Reasoning and GroundingLLM reasoning → Multimodal reasoning +1
  53. Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-RetrieverRetrieval-augmented generation → RAG pipeline design and evaluation
  54. OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  55. GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  56. RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video GenerationEnd-to-end autonomous driving → Reinforcement learning for driving +1
  57. A Closer Look at Model Collapse: From a Generalization-to-Memorization PerspectiveDiffusion models → Diffusion foundations and sampling +1
  58. Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic WorkloadsEfficient LLM inference and serving → Serving systems and request scheduling
  59. Can an Individual Manipulate the Collective Decisions of Multi-Agents?LLM agents and tool use → Agent threats, guardrails and governance
  60. Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  61. Towards Universal Debiasing for Language Models-based Tabular Data GenerationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  62. The Epistemic Suite: A Post-Foundational Diagnostic Methodology for Assessing AI Knowledge Claims
  63. Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
  64. DPSformer: A long-tail-aware model for improving heavy rainfall prediction
  65. Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Models
  66. Hyperbolic Optimization
  67. Learning Hyperspectral Images with Curated Text Prompts for Efficient Multimodal Alignment
  68. Explainable Deep Learning for Cataract Detection in Retinal Images: A Dual-Eye and Knowledge Distillation Approach
  69. A Novel Differential Feature Learning for Effective Hallucination Detection and Classification
  70. Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
  71. USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model
  72. ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation
  73. Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation
  74. Assessing Classical Machine Learning and Transformer-based Approaches for Detecting AI-Generated Research Text
  75. Vision-Based Perception for Autonomous Vehicles in Off-Road Environment Using Deep Learning
  76. Freshness and the Limits of Heuristic Trend Detection in Temporal RAG
  77. Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming
  78. Robot Learning with Sparsity and Scarcity
  79. SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training
  80. L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models
  81. KANO: Kolmogorov-Arnold Neural Operator
  82. Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
  83. Randomized Space-Time Sampling for Affine Graph Dynamical Systems
  84. Development of a Mobile Application for at-Home Analysis of Retinal Fundus Images
  85. Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition-Informed Approach to Quantifying Identity Fusion from Text
  86. SMART-3D: Three-Dimensional Self-Morphing Adaptive Replanning Tree
  87. Automated Procedural Analysis via Video-Language Models for AI-assisted Nursing Skills Assessment
  88. MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging
  89. KuBERT: Central Kurdish BERT Model and Its Application for Sentiment Analysis
  90. Sublinear Time Quantum Sensitivity Sampling
  91. A Study on Stabilizer R'enyi Entropy Estimation using Machine Learning
  92. Domain-Adaptive Pre-Training for Arabic Aspect-Based Sentiment Analysis: A Comparative Study of Domain Adaptation and Fine-Tuning Strategies
  93. Spectral Analysis of the Weighted Frobenius Objective
  94. MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
  95. Improving User Interface Generation Models from Designer Feedback
  96. Artificial Satellite Trails Detection Using U-Net Deep Neural Network and Line Segment Detector Algorithm
  97. Geometric Mixture Classifier (GMC): A Discriminative Per-Class Mixture of Hyperplanes
  98. The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology
  99. Interpretable Clinical Classification with Kolmogorov-Arnold Networks
  100. Evaluating LLM Generated Detection Rules in Cybersecurity
All 189
  1. HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
  2. On the System Theoretic Offline Learning of Continuous-Time LQR with Exogenous Disturbances
  3. CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding
  4. A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction
  5. Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
  6. Angular Dispersion Accelerates k-Nearest Neighbors Machine Translation
  7. Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment
  8. Exploring AI Capabilities in Participatory Budgeting within Smart Cities: The Case of Sao Paulo
  9. A Multi-Level Benchmark for Causal Language Understanding in Social Media Discourse
  10. Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
  11. Idiosyncratic Versus Normative Modeling of Atypical Speech Recognition: Dysarthric Case Studies
  12. Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modeling
  13. QASTAnet: A DNN-based Quality Metric for Spatial Audio
  14. HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
  15. Increase Alpha: Performance and Risk of an AI-Driven Trading Framework
  16. When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation
  17. Animalbooth: multimodal feature enhancement for animal subject personalization
  18. Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
  19. Spectral Compressive Imaging via Chromaticity-Intensity Decomposition
  20. Towards a Transparent and Interpretable AI Model for Medical Image Classifications
  21. Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget
  22. Design and Development of an Intelligent LLM-based LDAP Honeypot
  23. Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
  24. IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
  25. Segment-to-Act: Label-Noise-Robust Action-Prompted Video Segmentation Towards Embodied Intelligence
  26. FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World
  27. boldsymbolλ-Orthogonality Regularization for Compatible Representation Learning
  28. System-Level Uncertainty Quantification with Multiple Machine Learning Models: A Theoretical Framework
  29. On the de-duplication of the Lakh MIDI dataset
  30. Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
  31. Safe and Near-Optimal Control with Online Dynamics Learning
  32. AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval
  33. Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination
  34. KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
  35. Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification
  36. DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration
  37. Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation
  38. Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
  39. Conditional Multidimensional Scaling with Incomplete Conditioning Data
  40. Self-Supervised Learning of Graph Representations for Network Intrusion Detection
  41. CGTGait: Collaborative Graph and Transformer for Gait Emotion Recognition
  42. Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
  43. The Role of Vocabularies in Learning Sparse Representations for Ranking
  44. Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model
  45. ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworks
  46. LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts
  47. Describe-to-Score: A text-guided framework for image complexity assessment
  48. Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning
  49. FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection
  50. Computational-Assisted Systematic Review and Meta-Analysis (CASMA): Effect of a Subclass of GnRH-a on Endometriosis Recurrence
  51. Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
  52. Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
  53. SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
  54. Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
  55. From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations
  56. A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis
  57. Fusing Spectral Correlation Density Imaging with Deep Learning for Intelligent Fault Diagnosis in Rotating Machinery
  58. Learned Digital Over-the-Air Computing for Federated Edge Learning
  59. V-CECE: Visual Counterfactual Explanations via Conceptual Edits
  60. Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks
  61. MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs
  62. Person Identification from Egocentric Human-Object Interactions using 3D Hand Pose
  63. ViTCAE: ViT-based Class-conditioned Autoencoder
  64. ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting
  65. TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation
  66. Checking extracted rules in Neural Networks
  67. Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
  68. Mental Multi-class Classification on Social Media: Benchmarking Transformer Architectures against LSTM Models
  69. Long document summarization using page specific target text alignment and distilling page importance
  70. InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding
  71. Challenging the Evaluator: LLM Sycophancy Under User Rebuttal
  72. No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learning
  73. Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains
  74. AIPsychoBench: Understanding the Psychometric Differences between LLMs and Humans
  75. Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity
  76. Etude: Piano Cover Generation with a Three-Stage Approach -- Extract, strucTUralize, and DEcode
  77. mmExpert: Integrating Large Language Models for Comprehensive mmWave Data Synthesis and Understanding
  78. PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality
  79. LLM-Guided Co-Training for Text Classification
  80. SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging
  81. CommonForms: A Large, Diverse Dataset for Form Field Detection
  82. orb-QFL: Orbital Quantum Federated Learning
  83. Synergies between Federated Foundation Models and Smart Power Grids
  84. FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG
  85. Revisiting Broken Windows Theory
  86. The Oracle Has Spoken: A Multi-Aspect Evaluation of Dialogue in Pythia
  87. Octree Diffusion for Semantic Scene Generation and Completion
  88. Thermal Imaging-based Real-time Fall Detection using Motion Flow and Attention-enhanced Convolutional Recurrent Architecture
  89. Cross-Corpus and Cross-domain Handwriting Assessment of NeuroDegenerative Diseases via Time-Series-to-Image Conversion