Banner Banner

BIFOLD Colloquium 07/07/23


July 07, 2023 Icon 13:30 - 14:30


EN 719 or Virtual


Prof. Immanuel Trummer

Tuning Tools that "Read" the Manual: New Use Cases for Large Language Models in Data Management


The past years have been marked by several breakthrough results in the domain of generative AI, culminating in the rise of tools like ChatGPT, able to solve a variety of language-related tasks without specialized training. In his talk, Immanuel Trummer outlines novel opportunities in the context of data management, enabled by these advances. He discusses several recent research projects at Cornell, aimed at exploiting advanced language processing for tasks such as parsing a database manual to support automated tuning, or mining data for patterns, described in natural language. Finally, he will present recent and ongoing research, aimed at synthesizing code for SQL processing in general-purpose programming languages, while enabling customization via natural language commands.

Curriculum Vitae: 

Immanuel Trummer is an assistant professor at Cornell University and heads the Cornell Database Group. His papers were selected for “Best of VLDB”, “Best of SIGMOD”, for the ACM SIGMOD Research Highlight  Award, and for publication in CACM as CACM Research Highlight. His online lecture introducing students to database topics collected over a million views. He received the NSF CAREER Award and multiple Google Faculty Research Awards.


In case you want to attend virtually, please contact: