I am directing the Data Intelligence lab, which focuses on finding good data and smart analytics that are fundamental to data management, data science and artificial intelligence.
Retrieval-based language models using multi-modal data lakes. Data lakes have become increasingly popular for many organizations. Given a natural language question, retrieving datasets (e.g., text, tables, graphs) and reasoning with language models are key for business intelligence.
Good data for AI (a.k.a. data-centric AI). For most machine learning practitioners, the success of machine learning projects heavily depends on whether we can find good data for model training.
AI for good data. Data scientists spend at least 80% of their time on data preparation. Machine learning models can help address diverse data preparation challenges.
Visualization. Data visualization is important to data analytics. I am working on automatic visualization, visualization recommendation, chat-to-story, chat-to-video, and visualization using AR/VR devices.