{"total":15,"rows":[{"id":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2306.00745","title":"Column Type Annotation using ChatGPT","created":"2023-06-01","cited_by_count":19,"area":null},{"id":"2307.04217","title":"LakeBench: Benchmarks for Data Discovery over Data Lakes","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2404.03988","title":"Model Selection with Model Zoo via Graph Learning","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2508.13901","title":"Multimodal Data Storage and Retrieval for Embodied AI: A Survey","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2412.11472","title":"Leveraging Foundation Language Models (FLMs) for Automated Cohort Extraction from Large EHR Databases","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2604.18939","title":"TabEmb: Joint Semantic-Structure Embedding for Table Annotation","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2310.15373","title":"Semantic Data Management in Data Lakes","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2507.22186","title":"SourceSplice: Source Selection for Machine Learning Tasks","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2509.04632","title":"Conceptual Schema Inference for Tabular Datasets using Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2603.11436","title":"ZTab: Domain-based Zero-shot Annotation for Table Columns","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.18199","title":"PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.28880","title":"LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.08056","title":"H2: A Dual Hybrid Semantic Data Lake Architecture for Medical Data Harmonization with Human-In-the-Loop verified, LLM Driven Metadata Annotation System","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.31726","title":"High-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacement","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}