Sphinteract: Resolving Ambiguities in NL2SQL Through User Interaction
Fuheng Zhao, Shaleen Deep, Fotis Psallidas, Avrilia Floratou, Divyakant Agrawal, Amr El Abbadi
VLDB 2025
About
I recently completed my Ph.D. in Computer Science at the University of California, Santa Barbara, where I was co-advised by Professor Divyakant Agrawal and Professor Amr El Abbadi.
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.
Excited to share that I will be joining the University of Utah as a Tenure-Track Assistant Professor.
I am looking for self-motivated students who are interested in the data systems. A few specific topics that I'm very interested at: hybrid queries (AI SQL), NL2SQL, streaming algorithms, and vector index. If you are passionate about building the next generation of intelligent data systems, please check out my research interests and advising information and feel free to reach out!
Interested in collaboration? Drop me an email and let's chat!
Selected Publications and Projects
Integrating LLMs into Data Systems
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
Proposed a new compaction policy to gradually expand LSM horizontally and enhance the read performance.
ICDE 2025
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.