Profile Picture

Asim Biswal

CS PhD, University of California, Berkeley

abiswal[at]berkeley[dot]edu

I am a second year Ph.D. student advised by Prof. Joseph Gonzalez. My current research interest is studying the intersection of large language models and databases. Specifically, I am interested in leveraging the full potential of structured and unstructured data and their patterns of interactions using language models. This includes working on problems such as Text2SQL as well as the new paradigm TAG (Table Augmented Generation).

I previously graduated from the University of California, Berkeley with a B.S. degree in Electrical Engineering and Computer Science. During this time, I worked in the Sky Computing Lab on problems such as fair resource allocation and wide-area networking.

Publications

Text2SQL is Not Enough: Unifying AI and Databases with TAG 2025, CIDR Asim Biswal*, Liana Patel*, Siddarth Jha, Amog Kamsetty, Shu Liu, Joseph E. Gonzalez, Carlos Guestrin, Matei Zaharia
Optimizing LLM Queries in Relational Workloads 2024, Preprint Shu Liu*, Asim Biswal*, Audrey Cheng*, Xiangxi Mo, Shiyi Cao, Joseph E. Gonzalez, Ion Stoica, Matei Zaharia
Cilantro: Performance Aware Resource Allocation for General Objectives via Online Feedback 2023, OSDI Romil Bhardwaj, Kirthevasan Kandasamy, Asim Biswal, Wenshuo Guo, Benjamin Hindman, Joseph Gonzalez, Michael Jordan, Ion Stoica
Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays 2023, NSDI Paras Jain, Sam Kumar, Sarah Wooders, Shishir G. Patil, Joseph E. Gonzalez, Ion Stoica