Seminar: Data + AI: LLM-powered Data Management by Prof Guoliang Li

Abstract: Large language models (LLMs) have shown superior performance in various areas. And LLMs have the potential to revolutionize data management by serving as the "brain" of next-generation database systems. However, there are several challenges that utilize LLMs to optimize databases, including hallucinations, high overhead, and complex reasoning. In this talk, I will present the challenges and opportunities of designing LLM-powered data management systems.

Bio: Guoliang Li is a full professor at Department of Computer Science, Tsinghua University, Beijing, China. The research interests of Guoliang Li include database systems, machine learning for databases, human-in-the-loop data management, large-scale data cleaning and integration. He got VLDB 2017 Early Research Contribution Award, TCDE 2014 Early Career Award, SIGMOD 2024 Research Highlight Award, SIGMOD 2023 Best Papers, VLDB 2023 Best Industry Paper Runner-up, VLDB 2020 Best Papers, CIKM 2017 Best Paper Award, KDD 2018 Best Papers, ICDE 2018 Best Papers, DASFAA 2023 Best Paper Award, DASFAA 2014 Best Paper Runnerup, APWeb 2014 Best Paper Award, EDBT 2013 Similarity Join and Search Champion. He was SIGMOD 2021 General Co-Chair. He regularly served as PC Member of SIGMOD, VLDB, ICDE, KDD, WWW. He is serving as associate editor for IEEE TKDE and VLDB Journal.