mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 26 Jul 2025

169 papers

  1. OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augmented Generation ToolsRetrieval-augmented generation → RAG pipeline design and evaluation
  2. AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex TasksLLM reasoning → Reasoning for agents, planning and code +1
  3. CANDLE: A Cross-Modal Agentic Knowledge Distillation Framework for Interpretable Sarcopenia DiagnosisLLM agents and tool use → Medical and scientific domain agents +1
  4. Toward Revealing Nuanced Biases in Medical LLMsLLM safety and security → Safety alignment, refusal and guardrails
  5. KB-DMGen: Knowledge-Based Global Guidance and Dynamic Pose Masking for Human Image GenerationDiffusion models → Video generation
  6. The Devil is in the EOS: Sequence Training for Detailed Image CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. PERRY: Policy Evaluation with Confidence Intervals using Auxiliary DataDeep reinforcement learning methods → RL theory and sample complexity
  8. PITA: Preference-Guided Inference-Time Alignment for LLM Post-TrainingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval AugmentationRetrieval-augmented generation → RAG pipeline design and evaluation
  10. FaRMamba: Frequency-based learning and Reconstruction aided Mamba for Medical SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  11. FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  12. When Engineering Outruns Intelligence: Rethinking Instruction-Guided NavigationLLM reasoning → Spatial and embodied reasoning
  13. SAMUeL: Efficient Vocal-Conditioned Music Generation via Soft Alignment Attention and Latent DiffusionDiffusion models → Audio, speech and music
  14. Improving the Performance of Sequential Recommendation Systems with an Extended Large Language ModelLLM reasoning → LLM reasoning for recommendation
  15. SkinDualGen: Prompt-Driven Diffusion for Simultaneous Image-Mask Generation in Skin LesionsDiffusion models → Medical imaging and segmentation
  16. Predicting Brain Responses To Natural Movies With Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot LearningDiffusion models → 3D, point cloud and scene generation
  18. Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem SolvingLLM agents and tool use → Software engineering coding agents
  19. LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  20. MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  21. CaliDrop: KV Cache Compression with CalibrationEfficient LLM inference and serving → KV cache optimization
  22. ConSeg: Contextual Backdoor Attack Against Semantic SegmentationLLM safety and security → Backdoor and data poisoning attacks
  23. AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development AutomationLLM agents and tool use → Software engineering coding agents
  24. Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation ProtocolsLLM safety and security → Vision-language and text-to-image safety
  25. All-in-One Medical Image Restoration with Latent Diffusion-Enhanced Vector-Quantized Codebook PriorDiffusion models → Inverse problems and image restoration
  26. Inducing Causal World Models in LLMs for Zero-Shot Physical ReasoningWorld models → World models for language agents +1
  27. Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  28. A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  29. Agentic Reinforced Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  30. Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  31. HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMsEfficient LLM inference and serving → KV cache optimization
  32. SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion ModelsDiffusion models → Medical imaging and segmentation
  33. TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object DetectionDiffusion models → Video generation
  34. Reinforcement Learning for Multi-Objective Multi-Echelon Supply Chain OptimisationDeep reinforcement learning methods → RL for energy, networks and operations
  35. HydraMamba: Multi-Head State Space Model for Global Point Cloud LearningState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  36. Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation +1
  37. MoFRR: Mixture of Diffusion Models for Face Retouching RestorationDiffusion models → Inverse problems and image restoration
  38. UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning AbilitiesLLM reasoning → Reinforcement learning for reasoning
  39. Computing optimal policies for managing inventories with noisy observationsDeep reinforcement learning methods → RL for energy, networks and operations
  40. Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version)LLM reasoning → Reasoning benchmarks and evaluation
  41. JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language ModelsLLM reasoning → Mathematical reasoning
  42. DOA: A Degeneracy Optimization Agent with Adaptive Pose Compensation Capability based on Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  43. Basic Reading DistillationKnowledge distillation → Knowledge distillation for LLMs
  44. Minding Motivation: The Effect of Intrinsic Motivation on Agent BehaviorsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  45. TurQUaz at CheckThat! 2025: Debating Large Language Models for Scientific Web Discourse Detection
  46. Planning with Dynamically Changing Domains
  47. FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
  48. How Much Is Too Much? Adaptive, Context-Aware Risk Detection in Naturalistic Driving
  49. FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
  50. Stochastic Optimal Control via Measure Relaxations
  51. SmartCourse: A Contextual AI-Powered Course Advising System for Undergraduates
  52. Patch-Based 3D Variational Autoencoder for Super-Resolution of Turbulent Channel Flow
  53. FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
  54. A ChatGPT-based approach for questions generation in higher education
  55. Ontological Foundations of State Sovereignty
  56. An ontological analysis of risk in Basic Formal Ontology
  57. Lasso Penalization for High-Dimensional Beta Regression Models: Computation, Analysis, and Inference
  58. Cluster Purge Loss: Structuring Transformer Embeddings for Equivalent Mutants Detection
  59. Sparse Equation Matching: A Derivative-Free Learning for General-Order Dynamical Systems
  60. Geometric Operator Learning with Optimal Transport
  61. Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?
  62. ModShift: Model Privacy via Designed Shifts
  63. Modeling Parkinson's Disease Progression Using Longitudinal Voice Biomarkers: A Comparative Study of Statistical and Neural Mixed-Effects Models
  64. What Can Grokking Teach Us About Learning Under Nonstationarity?
  65. A Tensor-Based Compiler and a Runtime for Neuron-Level DNN Certifier Specifications
  66. Improving Deep Learning-based Respiratory Sound Analysis with Frequency Selection and Attention Mechanism
  67. K4: Online Log Anomaly Detection Via Unsupervised Typicality Learning
  68. Irredundant k-Fold Cross-Validation
  69. Infogen: Generating Complex Statistical Infographics from Documents
  70. Dependency Network-Based Portfolio Design with Forecasting and VaR Constraints
  71. Improving Audio Classification by Transitioning from Zero- to Few-Shot
  72. Digital and Robotic Twinning for Validation of Proximity Operations and Formation Flying
  73. TAPS : Frustratingly Simple Test Time Active Learning for VLMs
  74. Region-based Cluster Discrimination for Visual Representation Learning
  75. Discrete Gaussian Vector Fields On Meshes
  76. Anomaly Detection in Human Language via Meta-Learning: A Few-Shot Approach
  77. The Carbon Cost of Conversation, Sustainability in the Age of Language Models
  78. VAMPIRE: Uncovering Vessel Directional and Morphological Information from OCTA Images for Cardiovascular Disease Risk Factor Prediction
  79. FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
  80. Policy-Driven AI in Dataspaces: Taxonomy, Explainability, and Pathways for Compliant Innovation
  81. Finding Personalized Good-Enough Solutions to Unsatisfiable Stable Roommates Problems
  82. Robust Taxi Fare Prediction Under Noisy Conditions: A Comparative Study of GAT, TimesNet, and XGBoost
  83. Matching Game Preferences Through Dialogical Large Language Models: A Perspective
  84. VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
  85. FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images
  86. Development and Evaluation of an Ontology for Non-Invasive Respiratory Support in Acute Care
  87. Visual Analytics Using Tensor Unified Linear Comparative Analysis
  88. CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints
  89. Exploring LLM Autoscoring Reliability in Large-Scale Writing Assessments Using Generalizability Theory
  90. Extreme value theory for singular subspace estimation in the matrix denoising model
  91. A roadmap for AI in robotics
  92. Digital Twin Channel-Enabled Online Resource Allocation for 6G: Principle, Architecture and Application
  93. Leveraging Fine-Tuned Large Language Models for Interpretable Pancreatic Cystic Lesion Feature Extraction and Risk Categorization
  94. Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
  95. Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training
  96. Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
  97. KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models
  98. Pic2Diagnosis: A Method for Diagnosis of Cardiovascular Diseases from the Printed ECG Pictures
  99. What Does 'Human-Centred AI' Mean?
  100. AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation
All 169
  1. UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block
  2. Spatial Language Likelihood Grounding Network for Bayesian Fusion of Human-Robot Observations
  3. SCALAR: Scale-wise Controllable Visual Autoregressive Learning
  4. Deep Learning Based Joint Channel Estimation and Positioning for Sparse XL-MIMO OFDM Systems
  5. DynamiX: Large-Scale Dynamic Social Network Simulator
  6. A Fast Parallel Median Filtering Algorithm Using Hierarchical Tiling
  7. HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly
  8. A mini-batch training strategy for deep subspace clustering networks
  9. DriveIndia: An Object Detection Dataset for Diverse Indian Traffic Scenes
  10. The Impact of Fine-tuning Large Language Models on Automated Program Repair
  11. TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking
  12. CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation
  13. A Gold Standard Dataset and Evaluation Framework for Depression Detection and Explanation in Social Media using LLMs
  14. TS-Insight: Visualizing Thompson Sampling for Verification and XAI
  15. Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control
  16. Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention
  17. CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation
  18. Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam
  19. Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation
  20. FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Driving
  21. Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
  22. Efficient Self-Supervised Neuro-Analytic Visual Servoing for Real-time Quadrotor Control
  23. ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
  24. RestoreAI -- Pattern-based Risk Estimation Of Remaining Explosives
  25. OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration
  26. The Polish Vocabulary Size Test: A Novel Adaptive Test for Receptive Vocabulary Assessment
  27. DRIVE: Disfluency-Rich Synthetic Dialog Data Generation Framework for Intelligent Vehicle Environments
  28. Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos with Practical Quantum Advantage
  29. Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization
  30. RaGS: Unleashing 3D Gaussian Splatting from 4D Radar and Monocular Cues for 3D Object Detection
  31. FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing
  32. A Scalable and High Availability Solution for Recommending Resolutions to Problem Tickets
  33. VAE-GAN Based Price Manipulation in Coordinated Local Energy Markets
  34. Hybrid Deep Learning and Handcrafted Feature Fusion for Mammographic Breast Cancer Classification
  35. A Cooperative Approach for Knowledge-based Business Process Design in a Public Authority
  36. AutoSign: Direct Pose-to-Text Translation for Continuous Sign Language Recognition
  37. Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models
  38. ChoreoMuse: Robust Music-to-Dance Video Generation with Style Transfer and Beat-Adherent Motion
  39. Taking Language Embedded 3D Gaussian Splatting into the Wild
  40. Debunking Optimization Myths in Federated Learning for Medical Image Classification
  41. LAVA: Language Driven Scalable and Versatile Traffic Video Analytics
  42. FM-LC: A Hierarchical Framework for Urban Flood Mapping by Land Cover Identification Models
  43. DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
  44. From Few-Label to Zero-Label: An Approach for Cross-System Log-Based Anomaly Detection with Meta-Learning
  45. Sequence-based protein-protein interaction prediction and its applications in drug discovery
  46. ForCenNet: Foreground-Centric Network for Document Image Rectification
  47. AI-Based Clinical Rule Discovery for NMIBC Recurrence through Tsetlin Machines
  48. Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling
  49. Analyzing and Mitigating Repetitions in Trip Recommendation
  50. Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning
  51. DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation
  52. Sparse-mode Dynamic Mode Decomposition for Disambiguating Local and Global Structures
  53. Flora: Effortless Context Construction to Arbitrary Length and Scale
  54. SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
  55. JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection
  56. Bag of Coins: A Statistical Probe into Neural Confidence Structures
  57. Self-Guided Masked Autoencoder
  58. A Machine Learning Framework for Predicting Microphysical Properties of Ice Crystals from Cloud Particle Imagery
  59. Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs
  60. Modeling enzyme temperature stability from sequence segment perspective
  61. Latest Object Memory Management for Temporally Consistent Video Instance Segmentation
  62. TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations
  63. What Makes Code Generation Ethically Sourced?
  64. Preserving Guidance in Cost-Volume Retrieval under Extreme LiDAR Sparsity in Iterative Stereo
  65. Predicting Human Mobility during Extreme Events via LLM-Enhanced Cross-City Learning
  66. A Metabolic-Imaging Integrated Model for Prognostic Prediction in Colorectal Liver Metastases
  67. Integrating Activity Predictions in Knowledge Graphs
  68. Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos
  69. HypKG: Hypergraph-based Knowledge Graph Contextualization for Precision Healthcare