mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 6 Jan 2025

226 papers

  1. Sustainable Digitalization of Business with Multi-Agent RAG and LLMLLM agents and tool use → Web, search, and research agents
  2. RTLSquad: Multi-Agent Based Interpretable RTL DesignLLM agents and tool use → Software engineering coding agents
  3. Mixture-of-Experts Graph Transformers for Interpretable Particle Collision DetectionMixture-of-experts → MoE for time series and graphs
  4. A Self-supervised Diffusion Bridge for MRI ReconstructionDiffusion models → Medical imaging and segmentation
  5. A Study of the Efficacy of Generative Flow Networks for Robotics and Machine Fault-AdaptationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  6. DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D MeshesDiffusion models → 3D, point cloud and scene generation
  7. License Plate Images Generation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  8. K-space Diffusion Model Based MR Reconstruction Method for Simultaneous Multislice ImagingDiffusion models → Medical imaging and segmentation
  9. OpenLKA: an open dataset of lane keeping assist from market autonomous vehiclesEnd-to-end autonomous driving → VLMs for autonomous driving
  10. BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoningLLM reasoning → Mathematical reasoning
  11. Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. MObI: Multimodal Object Inpainting Using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  13. Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  14. Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning PoliciesDeep reinforcement learning methods → Safe and constrained RL
  15. PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
  16. Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical ReasoningLLM reasoning → Test-time compute and efficient thinking
  17. DDRM-PR: Fourier Phase Retrieval using Denoising Diffusion Restoration ModelsDiffusion models → Inverse problems and image restoration
  18. Analyzing Finetuning Representation Shift for Multimodal LLMs SteeringMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  19. GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCTState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  20. STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  21. FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation ModelsRetrieval-augmented generation → Privacy and security of RAG
  22. Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the WildLLM reasoning → Multimodal reasoning
  23. MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  24. Offline-to-online hyperparameter transfer for stochastic banditsOffline RL and imitation learning from data → Offline RL algorithms
  25. Sim-to-Real Transfer for Mobile Robots with Reinforcement Learning: from NVIDIA Isaac Sim to Gazebo and Real ROS 2 RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  26. Towards HRTF Personalization using Denoising Diffusion ModelsDiffusion models → Audio, speech and music
  27. IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference AlignmentLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  28. Diff-Lung: Diffusion-Based Texture Synthesis for Enhanced Pathological Tissue Segmentation in Lung CT ScansDiffusion models → Medical imaging and segmentation
  29. Large Language Models for Video Surveillance ApplicationsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  30. GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text ClassificationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  31. Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space ModelsState-space sequence models (S4, Mamba) → Speech and audio SSMs
  32. Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context LearningLLM reasoning → Reasoning benchmarks and evaluation
  33. InpDiffusion: Image Inpainting Localization via Conditional Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  34. InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM FusionLLM reasoning → Test-time compute and efficient thinking +1
  35. Segmenting Text and Learning Their Rewards for Improved RLHF in Language ModelLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  36. Learn A Flexible Exploration Model for Parameterized Action Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  37. Visual Large Language Models for Generalized and Specialized ApplicationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  38. MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention DistillationLLM safety and security → Backdoor and data poisoning attacks
  39. Brick-Diffusion: Generating Long Videos with Brick-to-Wall DenoisingDiffusion models → Video generation
  40. OpenGU: A Comprehensive Benchmark for Graph UnlearningLLM safety and security → Graph unlearning
  41. Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test DataRetrieval-augmented generation → Medical and biomedical RAG
  42. Advances in Artificial Intelligence: A Review for the Creative IndustriesDiffusion models → Image generation, text-to-image and editing
  43. Horizon Generalization in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  44. Multilevel Semantic-Aware Model for AI-Generated Video Quality AssessmentDiffusion models → Video generation
  45. Knowledge Distillation with Adapted WeightKnowledge distillation → General knowledge distillation methods
  46. QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA PerformanceRetrieval-augmented generation → RAG robustness and adaptive retrieval
  47. Political Events using RAG with LLMs
  48. Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
  49. Leveraging Cross-Attention Transformer and Multi-Feature Fusion for Cross-Linguistic Speech Emotion Recognition
  50. WhACC: Whisker Automatic Contact Classifier with Expert Human-Level Performance
  51. Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models
  52. The 2nd Place Solution from the 3D Semantic Segmentation Track in the 2024 Waymo Open Dataset Challenge
  53. Found in Translation: semantic approaches for enhancing AI interpretability in face verification
  54. RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
  55. DAMAGE: Detecting Adversarially Modified AI Generated Text
  56. SALT: Sales Autocompletion Linked Business Tables Dataset
  57. Expectation-Maximization as the Engine of Scalable Medical Intelligence
  58. Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements
  59. BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations
  60. On the Adversarial Robustness of Benjamini Hochberg
  61. Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs
  62. Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
  63. Over-the-Air Fair Federated Learning via Multi-Objective Optimization
  64. The Artificial Scientist -- in-transit Machine Learning of Plasma Simulations
  65. Existential Crisis: A Social Robot's Reason for Being
  66. Advanced Machine Learning Techniques for Social Support Detection on Social Media
  67. Detecting Defective Wafers Via Modular Networks
  68. Quantum Feature-Empowered Deep Classification for Fast Mangrove Mapping
  69. Data integrity vs. inference accuracy in large AIS datasets
  70. FTA-FTL: A Fine-Tuned Aggregation Federated Transfer Learning Scheme for Lithology Microscopic Image Classification
  71. Mobile Augmented Reality Framework with Fusional Localization and Pose Estimation
  72. CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets
  73. Analyzing Bias in Swiss Federal Supreme Court Judgments Using Facebook's Holistic Bias Dataset: Implications for Language Model Training
  74. The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks
  75. Plant Leaf Disease Detection and Classification Using Deep Learning: A Review and A Proposed System on Bangladesh's Perspective
  76. LiLMaps: Learnable Implicit Language Maps
  77. Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective
  78. Method of data forward generation with partial differential equations for machine learning modeling in fluid mechanics
  79. A Soft Sensor Method with Uncertainty-Awareness and Self-Explanation Based on Large Language Models Enhanced by Domain Knowledge Retrieval
  80. Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model
  81. ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
  82. A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detection
  83. Adaptive Pruning of Pretrained Transformer via Differential Inclusions
  84. CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models
  85. Inverse Design of Optimal Stern Shape with Convolutional Neural Network-based Pressure Distribution
  86. Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting
  87. Gaussian Masked Autoencoders
  88. LightGNN: Simple Graph Neural Network for Recommendation
  89. Rate-My-LoRA: Efficient and Adaptive Federated Model Tuning for Cardiac MRI Segmentation
  90. Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
  91. RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network
  92. ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
  93. Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
  94. Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text
  95. Detecting AI-Generated Text in Educational Content: Leveraging Machine Learning and Explainable AI for Academic Integrity
  96. The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input
  97. CLIX: Cross-Lingual Explanations of Idiomatic Expressions
  98. Multimodal Machine Learning Can Predict Videoconference Fluidity and Enjoyment
  99. Turn-based Multi-Agent Reinforcement Learning Model Checking
  100. Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
All 226
  1. Scalable Forward-Forward Algorithm
  2. GLiREL -- Generalist Model for Zero-Shot Relation Extraction
  3. Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text
  4. Deep-Relative-Trust-Based Diffusion for Decentralized Deep Learning
  5. SAM-EM: Real-Time Segmentation for Automated Liquid Phase Transmission Electron Microscopy
  6. The Scaling Law for LoRA Base on Mutual Information Upper Bound
  7. Efficient Document Image Dewarping via Hybrid Deep Learning and Cubic Polynomial Geometry Restoration
  8. VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity
  9. Communication Bounds for the Distributed Experts Problem
  10. SpinSVAR: Estimating Structural Vector Autoregression Assuming Sparse Input
  11. Generalized coarsened confounding for causal effects: a large-sample framework
  12. Normalizing Batch Normalization for Long-Tailed Recognition
  13. CAT: Content-Adaptive Image Tokenization
  14. From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning
  15. Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
  16. LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
  17. MVP: Multimodal Emotion Recognition based on Video and Physiological Signals
  18. A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks
  19. Sentiment-guided Commonsense-aware Response Generation for Mental Health Counseling
  20. Personalized Fashion Recommendation with Image Attributes and Aesthetics Assessment
  21. Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks
  22. AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation
  23. Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system
  24. Trust Modeling in Counseling Conversations: A Benchmark Study
  25. Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation
  26. Survival Analysis Revisited: Understanding and Unifying Poisson, Exponential, and Cox Models in Fall Risk Analysis
  27. To Analyze and Regulate Human-in-the-loop Learning for Congestion Games
  28. Dr. Tongue: Sign-Oriented Multi-label Detection for Remote Tongue Diagnosis
  29. Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments
  30. Group Shapley with Robust Significance Testing and Its Application to Bond Recovery Rate Prediction
  31. ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events
  32. Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders
  33. Putnam's Critical and Explanatory Tendencies Interpreted from a Machine Learning Perspective
  34. A Trust-Guided Approach to MR Image Reconstruction with Side Information
  35. Probably Correct Optimal Stable Matching for Two-Sided Markets Under Uncertainty
  36. Convexity in ReLU Neural Networks: beyond ICNNs?
  37. Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation
  38. TransPixeler: Advancing Text-to-Video Generation with Transparency
  39. PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling
  40. CALM: Curiosity-Driven Auditing for Large Language Models
  41. NeuroPMD: Neural Fields for Density Estimation on Product Manifolds
  42. SurgRIPE challenge: Benchmark of Surgical Robot Instrument Pose Estimation
  43. Classifier Weighted Mixture models
  44. A Bio-Inspired Research Paradigm of Collision Perception Neurons Enabling Neuro-Robotic Integration: The LGMD Case
  45. CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networks
  46. Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation
  47. CAMP: Collaborative Attention Model with Profiles for Vehicle Routing Problems
  48. Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls
  49. HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos
  50. Proof-of-Data: A Consensus Protocol for Collaborative Intelligence
  51. LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views
  52. Human Gaze Boosts Object-Centered Representation Learning
  53. SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild
  54. A Point Process Model for Optimizing Repeated Personalized Action Delivery to Users
  55. Key-value memory in the brain
  56. MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification
  57. From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
  58. Improved Approximation Algorithms for Orthogonally Constrained Problems Using Semidefinite Optimization
  59. 4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation
  60. A Bayesian Approach for Discovering Time- Delayed Differential Equation from Data
  61. Predicting band gap from chemical composition: A simple learned model for a material property with atypical statistics
  62. Self-Attention as a Parametric Endofunctor: A Categorical Framework for Transformer Architectures
  63. Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology
  64. Unsupervised Tomato Split Anomaly Detection using Hyperspectral Imaging and Variational Autoencoders
  65. Spiking monocular event based 6D pose estimation for space application
  66. Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
  67. Comprehensive Pathological Image Segmentation via Teacher Aggregation for Tumor Microenvironment Analysis
  68. Skillful High-Resolution Ensemble Precipitation Forecasting with an Integrated Deep Learning Framework
  69. Region of Interest based Medical Image Compression
  70. FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection
  71. Explaining Humour Style Classifications: An XAI Approach to Understanding Computational Humour Analysis
  72. MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
  73. PARF-Net: integrating pixel-wise adaptive receptive fields into hybrid Transformer-CNN network for medical image segmentation
  74. Conditional Mutual Information Based Diffusion Posterior Sampling for Solving Inverse Problems
  75. Two-Dimensional Unknown View Tomography from Unknown Angle Distributions
  76. Seeing the Whole in the Parts in Self-Supervised Representation Learning
  77. A Novel Vision Transformer for Camera-LiDAR Fusion based Traffic Object Segmentation
  78. ParetoLens: A Visual Analytics Framework for Exploring Solution Sets of Multi-objective Evolutionary Algorithms
  79. Synthetic Fungi Datasets: A Time-Aligned Approach
  80. Exact Matching in Correlated Networks with Node Attributes for Improved Community Recovery
  81. HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation
  82. RAHN: A Reputation Based Hourglass Network for Web Service QoS Prediction
  83. Foundations of GenIR
  84. Enhanced Rooftop Solar Panel Detection by Efficiently Aggregating Local Features
  85. Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation
  86. Universal Features Guided Zero-Shot Category-Level Object Pose Estimation
  87. Proteomic Learning of Gamma-Aminobutyric Acid (GABA) Receptor-Mediated Anesthesia
  88. RDD4D: 4D Attention-Guided Road Damage Detection And Classification
  89. A Stable Measure of Similarity for Time Series using Persistent Homology
  90. Analogue Forecast System for Daily Precipitation Prediction Using Autoencoder Feature Extraction: Application in Hong Kong
  91. First-place Solution for Streetscape Shop Sign Recognition Competition
  92. DarkFarseer: Robust Spatio-temporal Kriging under Graph Sparsity and Noise
  93. AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene
  94. Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism
  95. COph100: A comprehensive fundus image registration dataset from infants constituting the "RIDIRP" database
  96. GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection
  97. Fairness Through Matching
  98. Orthogonal greedy algorithm for linear operator learning with shallow neural network
  99. GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation
  100. CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
  101. Hybrid deep convolution model for lung cancer detection with transfer learning
  102. From Dense to Sparse: Event Response for Enhanced Residential Load Forecasting
  103. ICFNet: Integrated Cross-modal Fusion Network for Survival Prediction
  104. Unsupervised Domain Adaptation for Occlusion Resilient Human Pose Estimation
  105. GeAR: Generation Augmented Retrieval
  106. WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation
  107. Multi-Agent Pathfinding Under Team-Connected Communication Constraint via Adaptive Path Expansion and Dynamic Leading
  108. Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training
  109. Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?
  110. LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
  111. Beyond O(√T) Regret: Decoupling Learning and Decision-making in Online Linear Programming
  112. CHAT: Beyond Contrastive Graph Transformer for Link Prediction in Heterogeneous Networks
  113. Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?
  114. Intelligent logistics management robot path planning algorithm integrating transformer and GCN network
  115. Interpretable Recognition of Fused Magnesium Furnace Working Conditions with Deep Convolutional Stochastic Configuration Networks
  116. TARDiS : Text Augmentation for Refining Diversity and Separability
  117. Holistic Semantic Representation for Navigational Trajectory Generation
  118. Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
  119. AFed: Algorithmic Fair Federated Learning
  120. Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators
  121. Improved Data Encoding for Emerging Computing Paradigms: From Stochastic to Hyperdimensional Computing
  122. KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
  123. Refining Coarse-Grained Molecular Topologies: A Bayesian Optimization Approach
  124. Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation
  125. Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis
  126. EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models