{"total":116,"rows":[{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2307.10485","title":"FinGPT: Democratizing Internet-scale Data for Financial Large Language Models","created":"2023-07-19","cited_by_count":67,"area":null},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2212.11854","title":"Data-Centric Artificial Intelligence","created":"2022-12-22","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2307.14397","title":"A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot","created":"2023-07-26","cited_by_count":19,"area":null},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2307.05506","title":"Data-Driven Design for Metamaterials and Multiscale Systems: A Review","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2312.15561","title":"README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP","created":"2023-12-24","cited_by_count":17,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2309.10979","title":"Towards Data-centric Graph Machine Learning: Review and Outlook","created":"2023-09-20","cited_by_count":15,"area":null},{"id":"2402.05968","title":"Federated Learning Priorities Under the European Union Artificial Intelligence Act","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2402.13635","title":"The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2205.06935","title":"DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps","created":"2022-05-14","cited_by_count":12,"area":null},{"id":"2512.19363","title":"From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples","created":"2025-12-22","cited_by_count":12,"area":null},{"id":"2312.07087","title":"Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise","created":"2023-12-12","cited_by_count":11,"area":null},{"id":"2403.02619","title":"Training Machine Learning models at the Edge: A Survey","created":"2024-03-05","cited_by_count":11,"area":null},{"id":"2407.00125","title":"A Survey on Failure Analysis and Fault Injection in AI Systems","created":"2024-06-28","cited_by_count":10,"area":null},{"id":"2309.16211","title":"VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models","created":"2023-09-28","cited_by_count":9,"area":"mllm"},{"id":"2310.01765","title":"Data Cleaning and Machine Learning: A Systematic Literature Review","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2408.08143","title":"Unlearnable Examples Detection via Iterative Filtering","created":"2024-08-15","cited_by_count":9,"area":"safety"},{"id":"2410.24105","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","created":"2024-10-31","cited_by_count":9,"area":"synth"},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9,"area":"mllm"},{"id":"2208.08982","title":"Quality issues in Machine Learning Software Systems","created":"2022-08-18","cited_by_count":7,"area":null},{"id":"2306.09762","title":"The Big Data Myth: Using Diffusion Models for Dataset Generation to Train Deep Detection Models","created":"2023-06-16","cited_by_count":7,"area":"diffusion"},{"id":"2406.19614","title":"A Survey on Data Quality Dimensions and Tools for Machine Learning","created":"2024-06-28","cited_by_count":7,"area":null},{"id":"2408.04026","title":"Multimodal Gender Fairness in Depression Prediction: Insights on Data from the USA & China","created":"2024-08-07","cited_by_count":7,"area":null},{"id":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2311.18252","title":"Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective","created":"2023-11-30","cited_by_count":6,"area":"safety"},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2401.12722","title":"Falcon: Fair Active Learning using Multi-armed Bandits","created":"2024-01-23","cited_by_count":6,"area":null},{"id":"2402.06353","title":"Copycats: the many lives of a publicly available medical imaging dataset","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2408.14329","title":"Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2412.16089","title":"The Evolution of LLM Adoption in Industry Data Curation Practices","created":"2024-12-20","cited_by_count":6,"area":null},{"id":"2210.11717","title":"A Survey of Dataset Refinement for Problems in Computer Vision Datasets","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2306.03481","title":"Transition Role of Entangled Data in Quantum Machine Learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2307.02465","title":"Large-scale Detection of Marine Debris in Coastal Areas with Sentinel-2","created":"2023-07-05","cited_by_count":5,"area":null},{"id":"2309.13610","title":"VisionKG: Unleashing the Power of Visual Datasets via Knowledge Graph","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2311.05792","title":"Is a Seat at the Table Enough? Engaging Teachers and Students in Dataset Specification for ML in Education","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2312.03437","title":"Data-Centric Digital Agriculture: A Perspective","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2306.10841","title":"Blockchain-Enabled Federated Learning: A Reference Architecture Design, Implementation, and Verification","created":"2023-06-19","cited_by_count":4,"area":null},{"id":"2311.07389","title":"Transpose Attack: Stealing Datasets with Bidirectional Training","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2405.04251","title":"A General Model for Detecting Learner Engagement: Implementation and Evaluation","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2408.16683","title":"A Catalog of Fairness-Aware Practices in Machine Learning Engineering","created":"2024-08-29","cited_by_count":4,"area":null},{"id":"2307.02140","title":"Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectives","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2407.19784","title":"Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2411.11266","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2502.18620","title":"Diffusion Models for conditional MRI generation","created":"2025-02-25","cited_by_count":3,"area":"diffusion"},{"id":"2504.21211","title":"A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2507.19822","title":"Debunking Optimization Myths in Federated Learning for Medical Image Classification","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2209.01566","title":"Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables","created":"2022-09-04","cited_by_count":2,"area":null},{"id":"2306.14572","title":"Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks","created":"2023-06-26","cited_by_count":2,"area":null},{"id":"2309.01226","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2310.19503","title":"Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determination","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2312.08198","title":"Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2405.07653","title":"Fast Training Data Acquisition for Object Detection and Segmentation using Black Screen Luminance Keying","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2409.00997","title":"DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2412.01849","title":"Towards Data-centric Machine Learning on Directed Graphs: a Survey","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2501.06399","title":"GenAI Confessions: Black-box Membership Inference for Generative Image Models","created":"2025-01-11","cited_by_count":2,"area":"safety"},{"id":"2506.05520","title":"Toward Data Systems That Are Business Semantic Centric and AI Agents Assisted","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2603.19931","title":"SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia","created":"2026-03-20","cited_by_count":2,"area":"agents"},{"id":"2206.05052","title":"Meta-data Study in Autism Spectrum Disorder Classification Based on Structural MRI","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2306.12189","title":"Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2308.08234","title":"Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2311.01744","title":"Data-Centric Long-Tailed Image Recognition","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2312.14565","title":"Improving Task Instructions for Data Annotators: How Clear Rules and Higher Pay Increase Performance in Data Annotation in the AI Economy","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2402.07258","title":"Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models","created":"2024-02-11","cited_by_count":1,"area":null},{"id":"2402.08209","title":"Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2402.18292","title":"FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2403.06888","title":"Process signature-driven high spatio-temporal resolution alignment of multimodal data","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2410.06460","title":"A Benchmark on Directed Graph Representation Learning in Hardware Designs","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2503.01086","title":"FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.04350","title":"EDCA - An Evolutionary Data-Centric AutoML Framework for Efficient Pipelines","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2510.12728","title":"Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2512.19723","title":"End-to-End Data Quality-Driven Framework for Machine Learning in Production Environment","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2512.23385","title":"Securing the AI Supply Chain: What Can We Learn From Developer-Reported Security Issues and Solutions of AI Projects?","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2602.14357","title":"Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Study","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.12718","title":"The COTe score: A decomposable framework for evaluating Document Layout Analysis models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2212.12303","title":"Introduction to Machine Learning for Physicians: A Survival Guide for Data Deluge","created":"2022-12-23","cited_by_count":0,"area":null},{"id":"2303.11564","title":"Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery","created":"2023-03-21","cited_by_count":0,"area":null},{"id":"2306.15007","title":"Quality Issues in Machine Learning Software Systems","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2312.08999","title":"Conformalised data synthesis","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2401.14705","title":"Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2406.02600","title":"Data Quality in Edge Machine Learning: A State-of-the-Art Survey","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2407.12376","title":"Deep Learning-based Sentiment Analysis of Olympics Tweets","created":"2024-07-17","cited_by_count":0,"area":null},{"id":"2408.07718","title":"Impact of Inaccurate Contamination Ratio on Robust Unsupervised Anomaly Detection","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2412.03009","title":"Data Acquisition for Improving Model Fairness using Reinforcement Learning","created":"2024-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2412.06742","title":"ContRail: A Framework for Realistic Railway Image Synthesis using ControlNet","created":"2024-12-09","cited_by_count":0,"area":"diffusion"},{"id":"2503.13921","title":"Learning Over Dirty Data with Minimal Repairs","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.20801","title":"SE-GNN: Seed Expanded-Aware Graph Neural Network with Iterative Optimization for Semi-supervised Entity Alignment","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2504.02269","title":"Engineering Artificial Intelligence: Framework, Challenges, and Future Direction","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.01584","title":"VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scale","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.02214","title":"Is PMBOK Guide the Right Fit for AI? Re-evaluating Project Management in the Face of Artificial Intelligence Projects","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.11584","title":"A Comparative Analysis of Influence Signals for Data Debugging","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2506.20573","title":"LARP: Learner-Agnostic Robust Data Prefiltering","created":"2025-06-25","cited_by_count":0,"area":null}],"next_cursor":"100"}