{"total":79,"rows":[{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"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":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66,"area":null},{"id":"2306.10577","title":"OpenDataVal: a Unified Benchmark for Data Valuation","created":"2023-06-18","cited_by_count":55,"area":null},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43,"area":null},{"id":"2306.10280","title":"OpenGSL: A Comprehensive Benchmark for Graph Structure Learning","created":"2023-06-17","cited_by_count":30,"area":null},{"id":"2403.12776","title":"Automated Data Curation for Robust Language Model Fine-Tuning","created":"2024-03-19","cited_by_count":27,"area":null},{"id":"2212.03332","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","created":"2022-11-02","cited_by_count":24,"area":null},{"id":"2303.13988","title":"Machine Psychology","created":"2023-03-24","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2302.10671","title":"Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations","created":"2023-02-21","cited_by_count":18,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","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":"2502.02379","title":"No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets","created":"2025-02-04","cited_by_count":16,"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":"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":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2212.09321","title":"Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2311.13712","title":"Data Acquisition: A New Frontier in Data-centric AI","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2304.03243","title":"Synthetic Data in Healthcare","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2308.11290","title":"ShadowNet for Data-Centric Quantum System Learning","created":"2023-08-22","cited_by_count":8,"area":null},{"id":"2310.00109","title":"FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2408.02253","title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2301.01228","title":"DMOps: Data Management Operation and Recipes","created":"2023-01-02","cited_by_count":7,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2211.10442","title":"Deep learning methods for drug response prediction in cancer: predominant and emerging trends","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2307.11525","title":"Model Reporting for Certifiable AI: A Proposal from Merging EU Regulation into AI Development","created":"2023-07-21","cited_by_count":6,"area":null},{"id":"2409.18055","title":"Visual Data Diagnosis and Debiasing with Concept Graphs","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2312.14095","title":"RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2405.12317","title":"Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operators","created":"2024-05-20","cited_by_count":5,"area":null},{"id":"2410.02688","title":"User-centric Immersive Communications in 6G: A Data-oriented Framework via Digital Twin","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2411.15796","title":"Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2501.06261","title":"CAMs as Shapley Value-based Explainers","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2505.20429","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2605.10906","title":"DataMaster: Data-Centric Autonomous AI Research","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2405.09602","title":"Improving Label Error Detection and Elimination with Uncertainty Quantification","created":"2024-05-15","cited_by_count":4,"area":null},{"id":"2406.11730","title":"CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2505.06621","title":"Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2401.10397","title":"Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset","created":"2024-01-18","cited_by_count":3,"area":null},{"id":"2502.12690","title":"Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2505.11034","title":"CleanPatrick: A Benchmark for Image Data Cleaning","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.12312","title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2509.10712","title":"MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2512.01045","title":"Med-CRAFT: An Information System for Explainable and Configurable Construction of Multimodal Medical QA Datasets","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2607.03926","title":"TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2303.10888","title":"Self-Improving-Leaderboard(SIL): A Call for Real-World Centric Natural Language Processing Leaderboards","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2402.16380","title":"An Automated End-to-End Open-Source Software for High-Quality Text-to-Speech Dataset Generation","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2405.00892","title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2501.00691","title":"Labels Generated by Large Language Models Help Measure People's Empathy in Vitro","created":"2025-01-01","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":"2607.20465","title":"DataPrep-Bench: Benchmarking LLMs as Training Data Preparators","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2211.06440","title":"Data Quality Over Quantity: Pitfalls and Guidelines for Process Analytics","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2302.07872","title":"Data-Centric Governance","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2306.14377","title":"Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2306.15538","title":"DataCI: A Platform for Data-Centric AI on Streaming Data","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2311.16485","title":"Class-Adaptive Sampling Policy for Efficient Continual Learning","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2406.01086","title":"Diverse Subset Selection via Norm-Based Sampling and Orthogonality","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2406.02566","title":"Combining X-Vectors and Bayesian Batch Active Learning: Two-Stage Active Learning Pipeline for Speech Recognition","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2407.07560","title":"Instrumentation and Analysis of Native ML Pipelines via Logical Query Plans","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2409.12289","title":"MetaPix: A Data-Centric AI Development Platform for Efficient Management and Utilization of Unstructured Computer Vision Data","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.07110","title":"Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2504.04241","title":"oneDAL Optimization for ARM Scalable Vector Extension: Maximizing Efficiency for High-Performance Data Science","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2505.08940","title":"NeurIPS 2024 Ariel Data Challenge: Characterisation of Exoplanetary Atmospheres Using a Data-Centric Approach","created":"2025-05-13","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":"2509.24420","title":"A Data-Centric Perspective on the Influence of Image Data Quality in Machine Learning Models","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2602.23388","title":"Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.14137","title":"From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.16704","title":"Convex Dataset Valuation for Post-Training","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.16175","title":"PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.25356","title":"Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.35113","title":"SymbolicArena: A Unified Infrastructure for Benchmark Distillation and Dynamic Evaluation in Symbolic Regression","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35449","title":"From internal representations to model improvement through prediction errors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16956","title":"DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}