mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 8 Jan 2025

228 papers

  1. iServe: An Intent-based Serving System for LLMsEfficient LLM inference and serving → Serving systems and request scheduling
  2. FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain ToolsLLM agents and tool use → Financial trading and forecasting agents
  3. Microservice Deployment in Space Computing Power Networks via Robust Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  4. Tuning-Free Long Video Generation via Global-Local Collaborative DiffusionDiffusion models → Video generation
  5. Geophysical inverse problems with measurement-guided diffusion modelsDiffusion models → Inverse problems and image restoration
  6. Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  7. Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for OptimizationRetrieval-augmented generation → RAG pipeline design and evaluation
  8. EDMB: Edge Detector with MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  9. TREAD: Token Routing for Efficient Architecture-agnostic Diffusion TrainingDiffusion models → Diffusion foundations and sampling
  10. ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time TuningDiffusion models → Video generation
  11. Re-ranking the Context for Multimodal Retrieval Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  12. Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language GroundingVision-language-action models → Generalist VLA models and benchmarks
  13. Unlocking Multimodal Mathematical Reasoning via Process Reward ModelLLM reasoning → Multimodal reasoning +1
  14. Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  15. Enhancing Financial VQA in Vision Language Models using Intermediate Structured RepresentationsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  16. Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving ScenariosLLM reasoning → Multimodal reasoning +2
  17. Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  18. Multi-task retriever fine-tuning for domain-specific and efficient RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  19. Knowledge Retrieval Based on Generative AIRetrieval-augmented generation → RAG pipeline design and evaluation
  20. Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware InversionDiffusion models → Video generation
  21. InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and ReflectionLLM reasoning → Multimodal reasoning +1
  22. Feedback-Driven Vision-Language Alignment with Minimal Human SupervisionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech SynthesisLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  24. HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical SystemsDeep reinforcement learning methods → RL theory and sample complexity
  25. rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep ThinkingLLM reasoning → Mathematical reasoning +1
  26. Improving Image Captioning by Mimicking Human Reformulation Feedback at Inference-timeLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  27. Collaborative Inference Acceleration with Non-Penetrative Tensor PartitioningEfficient LLM inference and serving → Early exit and edge inference
  28. Safe Reinforcement Learning with Minimal SupervisionDeep reinforcement learning methods → Safe and constrained RL
  29. Hybrid Artificial Intelligence Strategies for Drone NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  30. Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated LearningLLM safety and security → Federated unlearning and poisoning
  31. NSA: Neuro-symbolic ARC ChallengeLLM reasoning → Multimodal reasoning
  32. Risk-averse policies for natural gas futures trading using distributional reinforcement learningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  33. ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial TrainingDiffusion models → Audio, speech and music
  34. Online Gaussian Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  35. Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-PromptingLLM reasoning → Prompting and chain-of-thought reasoning
  36. Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  37. Edit as You See: Image-guided Video Editing via Masked Motion ModelingDiffusion models → Video generation
  38. Eve: Efficient Multimodal Vision Language Models with Elastic Visual ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  39. DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  40. H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  41. ContextMRI: Enhancing Compressed Sensing MRI through Metadata ConditioningDiffusion models → Medical imaging and segmentation
  42. Robotic Programmer: Video Instructed Policy Code Generation for Robotic ManipulationLLM reasoning → Spatial and embodied reasoning
  43. IOLBENCH: Benchmarking LLMs on Linguistic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  44. Constraints as Rewards: Reinforcement Learning for Robots without Reward FunctionsDeep reinforcement learning methods → Deep RL algorithms and representations
  45. Agent Laboratory: Using LLM Agents as Research AssistantsLLM agents and tool use → Web, search, and research agents
  46. Generative Dataset Distillation Based on Self-knowledge DistillationKnowledge distillation → General knowledge distillation methods
  47. From Conceptual Data Models to Multimodal Representation
  48. Ethical Concerns of Generative AI and Mitigation Strategies: A Systematic Mapping Study
  49. Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages
  50. Making Software FAIR: A machine-assisted workflow for the research software lifecycle
  51. Intelligent Anti-Money Laundering Solution Based upon Novel Community Detection in Massive Transaction Networks on Spark
  52. Generative AI for Cel-Animation: A Survey
  53. Scalable Cosmic AI Inference using Cloud Serverless Computing
  54. Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models
  55. A Survey on Algorithmic Developments in Optimal Transport Problem with Applications
  56. A Partition Cover Approach to Tokenization
  57. Agent TCP/IP: An Agent-to-Agent Transaction System
  58. Intelligent Task Offloading: Advanced MEC Task Offloading and Resource Management in 5G Networks
  59. Predicting House Rental Prices in Ghana Using Machine Learning
  60. The Convergence of Dynamic Routing between Capsules
  61. Towards a scalable AI-driven framework for data-independent Cyber Threat Intelligence Information Extraction
  62. Multi-field Visualization: Trait design and trait-induced merge trees
  63. Forecasting Anonymized Electricity Load Profiles
  64. Data-Driven Radio Propagation Modeling using Graph Neural Networks
  65. NextStop: An Improved Tracker For Panoptic LIDAR Segmentation Data
  66. Mechanics and Design of Metastructured Auxetic Patches with Bio-inspired Materials
  67. An Interpretable ML-based Model for Predicting p-y Curves of Monopile Foundations in Sand
  68. Sustainable and Intelligent Public Facility Failure Management System Based on Large Language Models
  69. BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
  70. Open-Source Manually Annotated Vocal Tract Database for Automatic Segmentation from 3D MRI Using Deep Learning: Benchmarking 2D and 3D Convolutional and Transformer Networks
  71. EndoDINO: A Foundation Model for GI Endoscopy
  72. The Future of AI: Exploring the Potential of Large Concept Models
  73. Towards an Ontology of Traceable Impact Management in the Food Supply Chain
  74. S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic Analysis
  75. Reach Measurement, Optimization and Frequency Capping In Targeted Online Advertising Under k-Anonymity
  76. Leveraging Log Probabilities in Language Models to Forecast Future Events
  77. Topological Classification of points in Z2 by using Topological Numbers for 2D discrete binary images
  78. Real-Time Textless Dialogue Generation
  79. Back Home: A Computer Vision Solution to Seashell Identification for Ecological Restoration
  80. RieszBoost: Gradient Boosting for Riesz Regression
  81. Deep Transfer Q-Learning for Offline Non-Stationary Reinforcement Learning
  82. LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning
  83. Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware
  84. Intelligent experiments through real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and future EIC detectors
  85. Enhancing Listened Speech Decoding from EEG via Parallel Phoneme Sequence Prediction
  86. Do Code LLMs Understand Design Patterns?
  87. ActPC-Geom: Towards Scalable Online Neural-Symbolic Learning via Accelerating Active Predictive Coding with Information Geometry & Diverse Cognitive Mechanisms
  88. Quantum Hybrid Support Vector Machines for Stress Detection in Older Adults
  89. Building Foundations for Natural Language Processing of Historical Turkish: Resources and Models
  90. Intelligent Gradient Boosting Algorithms for Estimating Strength of Modified Subgrade Soil
  91. Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization
  92. Planing It by Ear: Convolutional Neural Networks for Acoustic Anomaly Detection in Industrial Wood Planers
  93. Decentralised Resource Sharing in TinyML: Wireless Bilayer Gossip Parallel SGD for Collaborative Learning
  94. Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks
  95. Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting
  96. Fast, Fine-Grained Equivalence Checking for Neural Decompilers
  97. Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval
  98. Cued Speech Generation Leveraging a Pre-trained Audiovisual Text-to-Speech Model
  99. A Steerable Deep Network for Model-Free Diffusion MRI Registration
  100. Leveraging Registers in Vision Transformers for Robust Adaptation
All 228
  1. GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting
  2. Video Summarisation with Incident and Context Information using Generative AI
  3. Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations
  4. Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty
  5. Efficient License Plate Recognition in Videos Using Visual Rhythm and Accumulative Line Analysis
  6. Discovering new robust local search algorithms with neuro-evolution
  7. Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures
  8. EditAR: Unified Conditional Generation with Autoregressive Models
  9. Grokking at the Edge of Numerical Stability
  10. Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation
  11. EpiCoder: Encompassing Diversity and Complexity in Code Generation
  12. Comparative Analysis of Quantum and Classical Support Vector Classifiers for Software Bug Prediction: An Exploratory Study
  13. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
  14. Toward Sufficient Statistical Power in Algorithmic Bias Assessment: A Test for ABROCA
  15. RadGPT: Constructing 3D Image-Text Tumor Datasets
  16. Natural Variational Annealing for Multimodal Optimization
  17. Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling
  18. HyFusion: Enhanced Reception Field Transformer for Hyperspectral Image Fusion
  19. On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena
  20. Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
  21. FlairGPT: Repurposing LLMs for Interior Designs
  22. Discrete Wavelet Transform-Based Capsule Network for Hyperspectral Image Classification
  23. A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI
  24. Disentangled Clothed Avatar Generation with Layered Representation
  25. FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency
  26. XGeM: A Multi-Prompt Foundation Model for Multimodal Medical Data Generation
  27. A Semantic Partitioning Method for Large-Scale Training of Knowledge Graph Embeddings
  28. Resilient Peer-to-peer Learning based on Adaptive Aggregation
  29. Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems
  30. FrontierNet: Learning Visual Cues to Explore
  31. Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning
  32. Federated-Continual Dynamic Segmentation of Histopathology guided by Barlow Continuity
  33. Identity-Preserving Video Dubbing Using Motion Warping
  34. Accelerated Extragradient-Type Methods -- Part 2: Generalization and Sublinear Convergence Rates under Co-Hypomonotonicity
  35. Boosting Salient Object Detection with Knowledge Distillated from Large Foundation Models
  36. Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision
  37. A 65 nm Bayesian Neural Network Accelerator with 360 fJ/Sample In-Word GRNG for AI Uncertainty Estimation
  38. Regret Analysis: a control perspective
  39. Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report
  40. Learnable Scaled Gradient Descent for Guaranteed Robust Tensor PCA
  41. Medical artificial intelligence toolbox (MAIT): an explainable machine learning framework for binary classification, survival modelling, and regression analyses
  42. Cyber-Physical Steganography in Robotic Motion Control
  43. Combining YOLO and Visual Rhythm for Vehicle Counting
  44. A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes
  45. Towards a Problem-Oriented Domain Adaptation Framework for Machine Learning
  46. Towards Fair Class-wise Robustness: Class Optimal Distribution Adversarial Training
  47. Histogram-Equalized Quantization for logic-gated Residual Neural Networks
  48. SplineFormer: An Explainable Transformer-Based Approach for Autonomous Endovascular Navigation
  49. CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection
  50. Developing a Modular Compiler for a Subset of a C-like Language
  51. The Role of Machine Learning in Congenital Heart Disease Diagnosis: Datasets, Algorithms, and Insights
  52. Integrating remote sensing data assimilation, deep learning and large language model for interactive wheat breeding yield prediction
  53. MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration
  54. PolInterviews -- A Dataset of German Politician Public Broadcast Interviews
  55. Research on environment perception and behavior prediction of intelligent UAV based on semantic communication
  56. Rethinking High-speed Image Reconstruction Framework with Spike Camera
  57. When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages
  58. Regularising NARX models with multi-task learning
  59. Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)
  60. Rapid Automated Mapping of Clouds on Titan With Instance Segmentation
  61. Hidden Entity Detection from GitHub Leveraging Large Language Models
  62. A novel Facial Recognition technique with Focusing on Masked Faces
  63. Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
  64. Motif Discovery Framework for Psychiatric EEG Data Classification
  65. RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
  66. Effect of Information Technology on Job Creation to Support Economic: Case Studies of Graduates in Universities (2023-2024) of the KRG of Iraq
  67. Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions
  68. Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions
  69. A Digital Shadow for Modeling, Studying and Preventing Urban Crime
  70. Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
  71. End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach
  72. Machine Learning and statistical classification of CRISPR-Cas12a diagnostic assays
  73. User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation
  74. Lossless Privacy-Preserving Aggregation for Decentralized Federated Learning
  75. Rising Rested MAB with Linear Drift
  76. Tracking UWB Devices Through Radio Frequency Fingerprinting Is Possible
  77. SEO: Stochastic Experience Optimization for Large Language Models
  78. iFADIT: Invertible Face Anonymization via Disentangled Identity Transform
  79. The unbearable lightness of Restricted Boltzmann Machines: Theoretical Insights and Biological Applications
  80. On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
  81. Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixing
  82. Instructive3D: Editing Large Reconstruction Models with Text Instructions
  83. FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection
  84. DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion
  85. A Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data
  86. Decoding EEG Speech Perception with Transformers and VAE-based Data Augmentation
  87. DeFusion: An Effective Decoupling Fusion Network for Multi-Modal Pregnancy Prediction
  88. TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs
  89. Interpretable deep convolutional model for nonlinear multivariate time series in complex systems
  90. AutoDFL: A Scalable and Automated Reputation-Aware Decentralized Federated Learning
  91. Neural Parameter Estimation with Incomplete Data
  92. An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks
  93. Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models
  94. VerifBFL: Leveraging zk-SNARKs for A Verifiable Blockchained Federated Learning
  95. Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts
  96. RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation
  97. FSC-loss: A Frequency-domain Structure Consistency Learning Approach for Signal Data Recovery and Reconstruction
  98. LLM4SR: A Survey on Large Language Models for Scientific Research
  99. Physics-Informed Super-Resolution Diffusion for 6D Phase Space Diagnostics
  100. Graph-Based Multimodal Contrastive Learning for Chart Question Answering
  101. HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation
  102. Circuit Complexity Bounds for Visual Autoregressive Model
  103. TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning
  104. MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
  105. An Analysis of Model Robustness across Concurrent Distribution Shifts
  106. ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization
  107. Mapping the Edge of Chaos: Fractal-Like Boundaries in The Trainability of Decoder-Only Transformer Models
  108. Enhancing Scene Classification in Cloudy Image Scenarios: A Collaborative Transfer Method with Information Regulation Mechanism using Optical Cloud-Covered and SAR Remote Sensing Images
  109. Cluster & Disperse: a general air conflict resolution heuristic using unsupervised learning
  110. Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
  111. On weight and variance uncertainty in neural networks for regression tasks
  112. Open set label noise learning with robust sample selection and margin-guided module
  113. Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning
  114. KN-LIO: Geometric Kinematics and Neural Field Coupled LiDAR-Inertial Odometry
  115. Modeling All Response Surfaces in One for Conditional Search Spaces
  116. Stable Derivative Free Gaussian Mixture Variational Inference for Bayesian Inverse Problems
  117. Integrated Offline and Online Learning to Solve a Large Class of Scheduling Problems
  118. Dynamic Localisation of Spatial-Temporal Graph Neural Network
  119. Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks
  120. Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images
  121. UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles
  122. CURing Large Models: Compression via CUR Decomposition
  123. Recognition-Oriented Low-Light Image Enhancement based on Global and Pixelwise Optimization
  124. GRAPHITE: Graph-Based Interpretable Tissue Examination for Enhanced Explainability in Breast Cancer Histopathology
  125. LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition
  126. Comparison of Neural Models for X-ray Image Classification in COVID-19 Detection
  127. STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification
  128. GNN-based Decentralized Perception in Multirobot Systems for Predicting Worker Actions