{"total":26,"rows":[{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"area":null},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"area":null},{"id":"2207.06214","title":"Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation","created":"2022-07-13","cited_by_count":43,"area":null},{"id":"2403.01931","title":"VariErr NLI: Separating Annotation Error from Human Label Variation","created":"2024-03-04","cited_by_count":42,"area":null},{"id":"2211.14611","title":"The Principles of Data-Centric AI (DCAI)","created":"2022-11-26","cited_by_count":26,"area":null},{"id":"2307.08701","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","created":"2023-07-17","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":"2302.07560","title":"Unsupervised classification to improve the quality of a bird song recording dataset","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2304.07874","title":"A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer","created":"2023-04-16","cited_by_count":9,"area":null},{"id":"2410.13761","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2406.08800","title":"Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2501.02004","title":"General Information Metrics for Improving AI Model Training Efficiency","created":"2025-01-02","cited_by_count":4,"area":null},{"id":"2305.12811","title":"Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2309.14406","title":"Provable advantages of kernel-based quantum learners and quantum preprocessing based on Grover's algorithm","created":"2023-09-25","cited_by_count":3,"area":null},{"id":"2207.11001","title":"POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion","created":"2022-07-22","cited_by_count":2,"area":null},{"id":"2408.12778","title":"Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2209.11464","title":"Smart Active Sampling to enhance Quality Assurance Efficiency","created":"2022-09-23","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":"2208.02007","title":"Maintaining Performance with Less Data","created":"2022-08-03","cited_by_count":0,"area":null},{"id":"2209.10178","title":"Deep Learning based pipeline for anomaly detection and quality enhancement in industrial binder jetting processes","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2305.18260","title":"Synfeal: A Data-Driven Simulator for End-to-End Camera Localization","created":"2023-05-29","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":"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":"2509.09195","title":"Breaking the Statistical Similarity Trap in Extreme Convection Detection","created":"2025-09-11","cited_by_count":0,"area":null}],"next_cursor":null}