{"total":15,"rows":[{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2402.01049","title":"IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition","created":"2024-02-01","cited_by_count":22,"area":null},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2311.16054","title":"Metric Space Magnitude for Evaluating the Diversity of Latent Representations","created":"2023-11-27","cited_by_count":17,"area":null},{"id":"2502.11671","title":"Diversity-oriented Data Augmentation with Large Language Models","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2409.03021","title":"CLUE: Concept-Level Uncertainty Estimation for Large Language Models","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2507.20858","title":"A survey of diversity quantification in natural language processing: The why, what, where and how","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2406.04257","title":"Data Measurements for Decentralized Data Markets","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2607.19848","title":"emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2207.02534","title":"Learning to Diversify for Product Question Generation","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2510.09475","title":"Few-shot multi-token DreamBooth with LoRa for style-consistent character generation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.09340","title":"Measuring Dataset Diversity from a Geometric Perspective","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2610.14031","title":"PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}