Event Title: Next-Generation Data Management with Large Language Models

Speaker: Prof. Immanuel Trummer

Dates: 22 April 2026

Time: 13:00-14:00

Location: 2 Semple Street

Join Online: https://app.huawei.com/wmeeting/join/96790342/otktXazpjfbmUIwbdrTjHXJxUn4umcfEp

Abstract:

Large language models (LLMs) open up exciting opportunities in data management and analysis. In this talk, I will discuss our recent and ongoing work, aimed at leveraging LLMs to test, tune, generalize, and, ultimately, build database systems. In particular, I will discuss recent projects on generating various customizable benchmarks via LLMs, thereby avoiding overfitting to standard benchmarks. I will touch on an ongoing line of work, leveraging LLMs to tune database systems more efficiently. I will also introduce several recent projects, aimed at expanding the scope of SQL-style analysis by supporting AI operators on multimodal data. Finally, I will discuss our recent results on leveraging multi-agent systems with state-of-the-art LLMs to write highly efficient, platform-specific code for data processing.

Bio:

Immanuel Trummer is an associate professor of computer science at Cornell University. His research focuses on making data analysis more efficient and more user-friendly. In particular, he studies novel use cases for LLMs in the database area and ways to scale up processing via LLMs to large data sets. His papers were selected for “Best of VLDB”, “Best of SIGMOD”, and the CACM research highlight award. He received an NSF CAREER grant for his work combining LLMs with databases and multiple Google Faculty Research Awards.

【Edinburgh Bayes Coffee House Talk】Next-Generation Data Management with Large Language Models / Huawei-Edinburgh Joint Lab by blogadmin is licensed under a Creative Commons Attribution CC BY 3.0