mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 7 Aug 2024

199 papers

  1. Prompt and PrejudiceMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  2. FDC: Fast KV Dimensionality Compression for Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
  3. PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement LearningOffline RL and imitation learning from data → Robot manipulation imitation learning +1
  4. Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary ObjectivesDeep reinforcement learning methods → Deep RL algorithms and representations
  5. How Well Can Vision Language Models See Image Details?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Dual-Modeling Decouple Distillation for Unsupervised Anomaly DetectionKnowledge distillation → Detection and dense prediction distillation
  7. From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent SystemsLLM agents and tool use → Multimodal and embodied agents
  8. PackMamba: Efficient Processing of Variable-Length Sequences in Mamba trainingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  9. Target Prompting for Information Extraction with Vision Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  10. Generative Language Models with Retrieval Augmented Generation for Automated Short Answer ScoringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  11. Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation LearningOffline RL and imitation learning from data → Social robot navigation
  12. HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision NetworksDeep reinforcement learning methods → RL for robot navigation and UAV control
  13. Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion ModelDiffusion models → Diffusion foundations and sampling
  14. Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient AdaptationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  15. RL-ADN: A High-Performance Deep Reinforcement Learning Environment for Optimal Energy Storage Systems Dispatch in Active Distribution NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  16. NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference TimeEfficient LLM inference and serving → KV cache optimization
  17. AI-Driven approach for sustainable extraction of earth's subsurface renewable energy while minimizing seismic activityDeep reinforcement learning methods → RL for energy, networks and operations
  18. Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion ModelsDiffusion models → Medical imaging and segmentation
  19. TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided OptimizationDiffusion models → Image generation, text-to-image and editing
  20. Improving Retrieval-Augmented Code Comment Generation by Retrieving for GenerationRetrieval-augmented generation → RAG for code
  21. A Logical Fallacy-Informed Framework for Argument GenerationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  22. Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
  23. Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon TasksLLM agents and tool use → Reinforcement learning for LLM agents
  24. EnJa: Ensemble Jailbreak on Large Language ModelsLLM safety and security → Jailbreaking
  25. DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with MambaEnd-to-end autonomous driving → End-to-end system architecture +1
  26. 2D-OOB: Attributing Data Contribution Through Joint Valuation FrameworkLLM safety and security → Backdoor and data poisoning attacks
  27. A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use CaseRetrieval-augmented generation → RAG pipeline design and evaluation +1
  28. D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion MethodsDiffusion models → Image generation, text-to-image and editing
  29. Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt InjectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  30. Deep Reinforcement Learning for Robotics: A Survey of Real-World SuccessesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  31. Lifelong Personalized Low-Rank Adaptation of Large Language Models for RecommendationLLM reasoning → LLM reasoning for recommendation
  32. A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic SystemsLLM safety and security → Prompt injection and agent security
  33. MoExtend: Tuning New Experts for Modality and Task ExtensionMixture-of-experts → Multimodal MoE models
  34. Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble ExploitationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  35. Automated Theorem Provers Help Improve Large Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  36. Sleeper Social Bots: a new generation of AI disinformation bots are already a political threat
  37. Fiber neural networks for the intelligent optical fiber communications
  38. Identifying and Mitigating Social Bias Knowledge in Language Models
  39. Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants
  40. Joint PET-MRI Reconstruction with Diffusion Stochastic Differential Model
  41. Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function
  42. StructuredRAG: JSON Response Formatting with Large Language Models
  43. Dynamic Code Orchestration: Harnessing the Power of Large Language Models for Adaptive Script Execution
  44. A Guide to Similarity Measures
  45. Handwritten Code Recognition for Pen-and-Paper CS Education
  46. MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into LaTeX Formulas for Improved Readability
  47. Anatomical Foundation Models for Brain MRIs
  48. SocFedGPT: Federated GPT-based Adaptive Content Filtering System Leveraging User Interactions in Social Networks
  49. ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses
  50. AutoFAIR : Automatic Data FAIRification via Machine Reading
  51. Forecasting Live Chat Intent from Browsing History
  52. Heterogeneous Graph Sequence Neural Networks for Dynamic Traffic Assignment
  53. Out-of-Core Dimensionality Reduction for Large Data via Out-of-Sample Extensions
  54. Incorporating Spatial Awareness in Data-Driven Gesture Generation for Virtual Agents
  55. VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs
  56. Overcoming Brittleness in Pareto-Optimal Learning-Augmented Algorithms
  57. Can Rule-Based Insights Enhance LLMs for Radiology Report Classification? Introducing the RadPrompt Methodology
  58. Combining Neural Architecture Search and Automatic Code Optimization: A Survey
  59. Zero-shot Factual Consistency Evaluation Across Domains
  60. UpLIF: An Updatable Self-Tuning Learned Index Framework
  61. Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization
  62. PaveCap: The First Multimodal Framework for Comprehensive Pavement Condition Assessment with Dense Captioning and PCI Estimation
  63. Hardware-Assisted Virtualization of Neural Processing Units for Cloud Platforms
  64. Decoding Visual Sentiment of Political Imagery
  65. ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
  66. Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  67. The Quest for Early Detection of Retinal Disease: 3D CycleGAN-based Translation of Optical Coherence Tomography into Confocal Microscopy
  68. PushPull-Net: Inhibition-driven ResNet robust to image corruptions
  69. Multi-scale structural complexity as a quantitative measure of visual complexity
  70. AEye: A Visualization Tool for Image Datasets
  71. Digital Avatars: Framework Development and Their Evaluation
  72. Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?
  73. PowerPM: Foundation Model for Power Systems
  74. Machine Learning-Based Reward-Driven Tuning of Scanning Probe Microscopy: Towards Fully Automated Microscopy
  75. Deep Generative Models for Subgraph Prediction
  76. Scaling Law of Sim2Real Transfer Learning in Expanding Computational Materials Databases for Real-World Predictions
  77. Task-oriented Sequential Grounding and Navigation in 3D Scenes
  78. Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?
  79. Multimodal Gender Fairness in Depression Prediction: Insights on Data from the USA & China
  80. Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity
  81. Image-to-LaTeX Converter for Mathematical Formulas and Text
  82. Learning from Noisy Labels for Long-tailed Data via Optimal Transport
  83. Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
  84. SLIM-RAFT: A Novel Fine-Tuning Approach to Improve Cross-Linguistic Performance for Mercosur Common Nomenclature
  85. From Words to Worth: Newborn Article Impact Prediction with LLM
  86. Fast Sprite Decomposition from Animated Graphics
  87. FMiFood: Multi-modal Contrastive Learning for Food Image Classification
  88. Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
  89. AdapMTL: Adaptive Pruning Framework for Multitask Learning Model
  90. CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
  91. LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
  92. Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
  93. Lightweight Video Denoising Using a Classic Bayesian Backbone
  94. Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond
  95. Simplifying Scholarly Abstracts for Accessible Digital Libraries
  96. MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems
  97. No-Reference Image Quality Assessment with Global-Local Progressive Integration and Semantic-Aligned Quality Transfer
  98. Knowledge Probing for Graph Representation Learning
  99. Personalized Clinical Note Generation from Doctor-Patient Conversations
  100. Inter-Series Transformer: Attending to Products in Time Series Forecasting
All 199
  1. Large Language Models for Biomedical Text Simplification: Promising But Not There Yet
  2. Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition
  3. Why transformers are obviously good models of language
  4. Hate Speech Detection and Classification in Amharic Text with Deep Learning
  5. Bi-Level Spatial and Channel-aware Transformer for Learned Image Compression
  6. MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models
  7. Using a Distance Sensor to Detect Deviations in a Planar Surface
  8. WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
  9. Automated Code Fix Suggestions for Accessibility Issues in Mobile Apps
  10. Towards Real-Time Gaussian Splatting: Accelerating 3DGS through Photometric SLAM
  11. Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields
  12. Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning
  13. Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting
  14. Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency
  15. Frank's triangular norms in Piaget's logical proportions
  16. Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection
  17. Counterfactuals and Uncertainty-Based Explainable Paradigm for the Automated Detection and Segmentation of Renal Cysts in Computed Tomography Images: A Multi-Center Study
  18. Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations
  19. Methodological Explainability Evaluation of an Interpretable Deep Learning Model for Post-Hepatectomy Liver Failure Prediction Incorporating Counterfactual Explanations and Layerwise Relevance Propagation: A Prospective In Silico Trial
  20. Nadaraya-Watson kernel smoothing as a random energy model
  21. Reliable Node Similarity Matrix Guided Contrastive Graph Clustering
  22. 'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization
  23. MMSummary: Multimodal Summary Generation for Fetal Ultrasound Video
  24. 3iGS: Factorised Tensorial Illumination for 3D Gaussian Splatting
  25. Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions
  26. Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
  27. Intuitionistic Fuzzy Cognitive Maps for Interpretable Image Classification
  28. Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal
  29. Bayes-optimal learning of an extensive-width neural network from quadratically many samples
  30. Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks
  31. A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models
  32. Pick of the Bunch: Detecting Infrared Small Targets Beyond Hit-Miss Trade-Offs via Selective Rank-Aware Attention
  33. Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
  34. CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications
  35. Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
  36. A Blockchain-based Reliable Federated Meta-learning for Metaverse: A Dual Game Framework
  37. Generative Design of Periodic Orbits in the Restricted Three-Body Problem
  38. L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection
  39. Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
  40. Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks
  41. PHOCUS: Physics-Based Deconvolution for Ultrasound Resolution Enhancement
  42. Consumer Transactions Simulation through Generative Adversarial Networks
  43. mucAI at WojoodNER 2024: Arabic Named Entity Recognition with Nearest Neighbor Search
  44. Path-SAM2: Transfer SAM2 for digital pathology semantic segmentation
  45. HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detection
  46. Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models
  47. CARE: A Clue-guided Assistant for CSRs to Read User Manuals
  48. Concept Conductor: Orchestrating Multiple Personalized Concepts in Text-to-Image Synthesis
  49. Large Language Model as a Catalyst: A Paradigm Shift in Base Station Siting Optimization
  50. PAGED: A Benchmark for Procedural Graphs Extraction from Documents
  51. Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
  52. On the choice of the non-trainable internal weights in random feature maps
  53. AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging
  54. Improving the quality of Persian clinical text with a novel spelling correction system
  55. Making Robust Generalizers Less Rigid with Loss Concentration
  56. Is Child-Directed Speech Effective Training Data for Language Models?
  57. JARViS: Detecting Actions in Video Using Unified Actor-Scene Context Relation Modeling
  58. Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation
  59. Activations Through Extensions: A Framework To Boost Performance Of Neural Networks
  60. PRISM: PRogressive dependency maxImization for Scale-invariant image Matching
  61. Hierarchical Quantum Control Gates for Functional MRI Understanding
  62. HistoSPACE: Histology-Inspired Spatial Transcriptome Prediction And Characterization Engine
  63. FOVAL: Calibration-Free and Subject-Invariant Fixation Depth Estimation Across Diverse Eye-Tracking Datasets
  64. Sensitivity analysis using the Metamodel of Optimal Prognosis
  65. Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation
  66. Hierarchical Neural Constructive Solver for Real-world TSP Scenarios
  67. Teach CLIP to Develop a Number Sense for Ordinal Regression
  68. AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling
  69. Maximum a Posteriori Estimation for Linear Structural Dynamics Models Using Bayesian Optimization with Rational Polynomial Chaos Expansions
  70. A comparative study of generative adversarial networks for image recognition algorithms based on deep learning and traditional methods
  71. Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning
  72. Riverbed litter monitoring using consumer-grade aerial-aquatic speedy scanner (AASS) and deep learning based super-resolution reconstruction and detection network
  73. MPC-Minimized Secure LLM Inference
  74. In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models
  75. Enhanced hermit crabs detection using super-resolution reconstruction and improved YOLOv8 on UAV-captured imagery
  76. VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction
  77. CLIP-based Point Cloud Classification via Point Cloud to Image Translation
  78. NatLan: Native Language Prompting Facilitates Knowledge Elicitation Through Language Trigger Provision and Domain Trigger Retention
  79. Automatic identification of the area covered by acorn trees in the dehesa (pastureland) Extremadura of Spain
  80. EXAONE 3.0 7.8B Instruction Tuned Language Model
  81. PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model
  82. PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relighting
  83. Neural active manifolds: nonlinear dimensionality reduction for uncertainty quantification
  84. Exploring the extent of similarities in software failures across industries using LLMs
  85. Minimum Enclosing Ball Synthetic Minority Oversampling Technique from a Geometric Perspective
  86. Hierarchical learning control for autonomous robots inspired by central nervous system
  87. EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora
  88. SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection
  89. RepoMasterEval: Evaluating Code Completion via Real-World Repositories
  90. Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian
  91. On-Demand Growth of Semiconductor Heterostructures Guided by Physics-Informed Machine Learning
  92. GUI Element Detection Using SOTA YOLO Deep Learning Models
  93. 1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data
  94. Opening the Black Box of 3D Reconstruction Error Analysis with VECTOR
  95. e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation
  96. FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks
  97. Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENN
  98. Simultaneous and Meshfree Topology Optimization with Physics-informed Gaussian Processes
  99. Harnessing the Power of LLMs in Source Code Vulnerability Detection