Jiale Lao

Jiale Lao

Graduate Student

Cornell University

Biography

I am a PhD student in Computer Science at Cornell University advised by Professor Immanuel Trummer. I am currently interested in leveraging advanced techniques from the Natural Language Processing field (e.g., Large Language Model) to enhance the efficiency, usability and generality of database systems. During my time at Sichuan University as a B.Eng student, I was fortunate to be advised by Professor Mingjie Tang and Professor Jianguo Wang from Purdue University, focusing on utilizing machine learning techniques to optimize database performance. I have published multiple papers in SIGMOD and VLDB conferences and received the SIGMOD Research Highlight Award 2024.

Interests
  • Database
  • Machine Learning
  • Large Language Model
Education
  • PhD in Computer Science, Present

    Cornell University

  • B.Eng in Software Engineering, 2024

    Sichuan University

Recent News

  • [2025/11/03] SemBench is available now! Let us go for Semantic Query Processing!
  • [2025/10/04] SQLBarber and QUITE are under revision of SIGMOD 2026!
  • [2025/08/23] ToxicSQL is accepted by SIGMOD 2026!
  • [2025/03/15] SQLBarber Demo is accepted by SIGMOD 2025!
  • [2024/12/14] GPTuner wins SIGMOD Research Highlight Award! 10 papers selected!
  • [2024/03/16] GPTuner Demo is accepted by SIGMOD 2024!
  • [2024/03/15] GPTuner is accepted by VLDB 2024!
  • [2024/01/31] A video demonstration of GPTuner is available on YouTube!
  • [2023/11/02] GPTuner is open-sourced now!

Selected Publications

Quickly discover relevant content by filtering publications.
(0001). A Demonstration of GPTuner: A GPT-Based Manual-Reading Database Tuning System. Proceedings of ACM Conference on Management of Data (SIGMOD).

PDF Cite Code Video DOI

(0001). Demonstrating SQLBarber: Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads. Proceedings of ACM Conference on Management of Data (SIGMOD).

PDF Cite Video DOI

(0001). GPTuner: A Manual-Reading Database Tuning System. Very Large Data Bases Conference (VLDB), 🏆 SIGMOD Research Highlight Award 🏆.

PDF Cite Code Video DOI

(0001). GPTuner: An LLM-Based Database Tuning System. Proceedings of ACM Conference on Management of Data (SIGMOD), 🏆 SIGMOD Research Highlight Award 2024 🏆.

PDF Cite Code Video DOI

Awards

  • SIGMOD Research Highlight Award 2024 [link]

Experience

 
 
 
 
 
Research Assistant
Database Group at Cornell University
May 2025 – Present

Advised by

Projects

  • Customized and Realistic SQL Workload Generation with Large Language Model
 
 
 
 
 
Teaching Assistant
Cornell University, 3110 Functional Programming, 25 Spring
January 2025 – May 2025

Advised by

Course

  • This course is about a functional programming language, OCaml: Correct + Efficient + Beautiful
  • Course Website
 
 
 
 
 
Teaching Assistant
Cornell University, CS 4320/5320 Introduction to Database Systems, 24 Fall, 25 Fall
August 2024 – January 2025

Advised by

Course

  • This course is an introduction to relational database systems, NoSQL and NewSQL systems, and other tools for large-scale data analysis. Topics covered include the relational model, SQL, query processing and optimization, transactions, recovery, NoSQL and NewSQL systems, database design, as well as systems for graph, stream, and spatial data processing.
  • Course Website
 
 
 
 
 
Research Assistant
Database Systems Group at Purdue University
April 2023 – August 2024

Advised by

Projects

  • Automatic Optimization of Database with Large Language Model
  • Distance Indexing Optimization via Graph Neural Network
 
 
 
 
 
Research Assistant
AI and System Lab at Sichuan University
October 2022 – August 2024

Advised by

Projects

  • Automatic Optimization of Database with Large Language Model
  • Distance Indexing Optimization via Graph Neural Network