I am Yunjia Zhang, a Ph.D. candidate majoring in Computer Sciences at Department of Computer Sciences, University of Wisconsin-Madison (Madison, WI, US). Currently, I am in Database Group, under the supervision of Prof. Theodoros (Theo) Rekatsinas (currently at Apple) and Prof. Jignesh M. Patel (currently at CMU). I am also in strong collaboration with Microsoft GSL, and my mentor at GSL is Avrilia Floratou. I got my B.Eng in Computer Science at School of Computer Science, Wuhan University.
I have a broad interest in many topics in databases, especifically AI4DB. I am devoted to improving the data scientists’ pipeline, providing them with easier-to-use and faster-to-execute analytic tools. I am currently focusing on LLMs for databases and efficient query processing.
Office: 4360 @ CS Dept., 1201 W Dayton St, Madison, WI, United States, 53715
Email: yunjia [AT] cs.wisc.edu
Selected Publications
ReAcTable: Enhancing ReAct for Table Question Answering [pdf]
Yunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon, Shaleen Deep, Jignesh M. Patel
VLDB 2024
GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization [pdf]
Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Mingjie Tang, Jianguo Wang
VLDB 2024, Selected as SIGMOD Research Highlight
A Demonstration of GPTuner: A GPT-Based Manual-Reading Database Tuning System
Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Yuanchun Zhou, Mingjie Tang, Jianguo Wang
SIGMOD 2024 Demo
Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis [pdf] [code]
Yunjia Zhang, Yannis Chronis, Jignesh M. Patel, Theodoros Rekatsinas
VLDB 2023, Invited by VLDB Journal Special Issue: “Best of VLDB 2023”
Schema Matching using Pre-Trained Language Models [pdf]
Yunjia Zhang, Avrilia Floratou, Joyce Cahoon, Subru Krishnan, Andreas Mueller, Dalitso Banda, Fotis Psallidas, Jignesh M. Patel
ICDE 2023
Can Transfer Learning be Used to Build Query Optimizers [talk]
Yunjia Zhang, Yannis Chronis, Jignesh M. Patel, Theodoros Rekatsinas
CIDR 2022
A Statistical Perspective on Discovering Functional Dependencies in Noisy Data [pdf] [code]
Yunjia Zhang, Zhihan Guo, Theodoros Rekatsinas
SIGMOD 2020
Statistical Estimation of Diffusion Network Topologies [pdf] [slides]
Keqi Han, Yuan Tian, Yunjia Zhang, Ling Han, Hao Huang, Yunjun Gao
ICDE 2020
News
Joining Gray System Lab (GSL) at Microsoft Azure Data Research as research intern in summer 2021! [01/27/2021]
Our paper on discovering functional dependency from a statistical perspective is to appear in SIGMOD 2020. [03/22/2020]
Paper on diffusion network topology resconstruction is accepted by ICDE 2020. [12/13/2019]
Joining Database Group of Computer Science Dept. at University of Wisconsin-Madison for Ph.D study. GO BADGERS! [05/13/2019]
Attending AAAI 2019 (Jan.27 2019) at Hawaii, USA and giving an oral presentation! [12/13/2018]
Joining Prof. Xiaokui Xiao’s Database Research Lab at National University of Singapore from Nov 2018! [10/01/2018]
Joining Prof. Gao Cong’s Singtel Cognitive and AI Lab for Enterprises at Nanyang Technological University in Singapore from Jul 2018! [06/29/2018]