About

I am a Ph.D. candidate in the Department of Computer Science at the University of California, Santa Barbara. I am co-advised by Professor Divyakant Agrawal and Professor Amr El Abbadi. I'm interested in developing new algorithms and systems to manage big data efficiently. Currently, I am exploring opportunities in applying large language models in data systems, such as translating natural language into SQL and enabling approximate query processing with LLMs.
Besides research, I enjoy trying new food, watching movies, and playing tennis and badminton. I'm also a trumpet player in which I played trumpet solo in Danzón No. 2 at the Disney Hall.

I am honored to have received the Microsoft Research PhD Fellowship from Microsoft Research, Charles Dana Fellowship, research gifts from Snowflake.

Interested in collaboration? Drop me an email and let's chat!

Selected Publications and Projects

Integrating LLMs into Data Systems

Sphinteract: Resolving Ambiguities in NL2SQL Through User Interaction

Fuheng Zhao, Shaleen Deep, Fotis Psallidas, Avrilia Floratou, Divyakant Agrawal, Amr El Abbadi

VLDB 2025

Hybrid Querying Over Relational Databases and Large Language Models

Fuheng Zhao, Divyakant Agrawal, Amr El Abbadi

CIDR 2025

NL2SQL is a Solved Problem... Not!

Work done while interning at Microsoft Gray System Lab

CIDR 2024

Streaming Algorithms

Panakos: Chasing the Tails for Multidimensional Data Streams

Fuheng Zhao, Punnal Ismail Khan, Divyakant Agrawal, Amr El Abbadi, Arpit Gupta, Zaoxing Liu

VLDB 2023

Differentially Private Linear Sketches: Efficient Implementations and Applications

Fuheng Zhao*, Dan Qiao*, Rachel Redberg, Divyakant Agrawal, Amr El Abbadi, Yu-Xiang Wang

NeurIPS 2022

SpaceSaving±: An Optimal Algorithm for Frequency Estimation and Frequent Items in the Bounded Deletion Model

Fuheng Zhao, Divyakant Agrawal, Amr El Abbadi, Ahmed Metwally

VLDB 2022

KLL±: Approximate Quantile Sketches over Dynamic Datasets

Fuheng Zhao, Sujaya Maiyya, Ryan Wiener, Divyakant Agrawal, Amr El Abbadi

VLDB 2021

Storage Engines

Autumn: A Scalable Read Optimized LSM-tree based Key-Value Stores with Fast Point and Range Read Speed

Looked into the trade-off between write and read. Proposed a new ganerning compaction policy to enhance read performance .

preprint

Redwood Storage Engine, FoundationDB

Redwood project is lead by Steve Atherton.

I contributed on monitoring, caching, and scheduling disk I/O during my two summer internships at Snowflake. Most of my contributions can be found here.