llmdb Symphony Retrieval-augmented language models using multi-modal data lakes. VerifAI VerifAI is designed to verify the correctness of generative AI using multi-modal data lakes. NL2SQL Translating natural langauge to SQL queries llmprivacy ZT4MCP Zero Trust framework for MCP development & runtime dcai Data acquisition Discovering and selecting training data from data lakes Data augmentation Augment more data or features Coreset selection Selecting a subset of train data dataprep Data Matching Deciding whether two data elements are the "same" (a.k.a. a match) or not Data Prep Theories, algorithms, and systems Table representation learning Relational pre-trained transformer vis AutoVIS Automatic visualization Chart Understanding Understaning visualization chart images NL2VIS Translating natural langauge to visualizations finished Data Civilizer A Tool to Find, Ingest, Clean, and Integrate Diverse Data Sets