Zhuoyue WAN

Hong Kong
Email: zhuoy.wan@connect.polyu.hk
Homepage: https://zwanah.github.io
Google Scholar: https://scholar.google.com/citations?user=28rvyrEAAAAJ
GitHub: https://github.com/zwanah
LinkedIn: https://www.linkedin.com/in/ZhuoyueWAN

Profile

Ph.D. candidate in Computer Science at The Hong Kong Polytechnic University, supervised by Assistant Professor Chen Jason Zhang and working closely with Professor Raymond Chi-Wing Wong. My research focuses on Natural Language Processing for Databases, especially data-centric tasks, structured query generation, data visualization understanding, and data agents. I am also interested in applying mathematical optimization techniques to improve the performance and efficiency of data agents.

Education

The Hong Kong Polytechnic University, Hong Kong
Ph.D. in Computer Science, Jan. 2025 - Present
Supervisor: Assistant Professor Chen Jason Zhang

The Hong Kong University of Science and Technology, Hong Kong
M.S. in Data-Driven Modeling, Sep. 2022 - Nov. 2023

Chongqing University, Chongqing, China
B.S. in Statistics, Sep. 2017 - Jun. 2021

Research Experience

The Hong Kong Polytechnic University, Hong Kong
Research Assistant, Jan. 2024 - Dec. 2024

  • Conducted research on NLP for databases and data-centric AI.
  • Worked on language-model-based systems for structured data, OpenStreetMap query generation, and data visualization understanding.
  • Collaborated with researchers across database, NLP, and data mining topics.

Research Interests

  • Natural Language Processing for Databases
  • Data-centric AI and data agents
  • Structured query generation
  • OpenStreetMap query understanding
  • Data visualization understanding
  • Mathematical optimization for agent efficiency

Publications

Published Papers

  1. Zhuoyue Wan, Wentao Hu, Hwanhee Kim, Chen Jason Zhang, Shuaimin Li, Yuanfeng Song, Ming Deng, Xiao-Yong Wei, Raymond Chi-Wing Wong.
    TACO: Token-Aware Context Optimization for Structured OpenStreetMap Query Generation.
    Accepted at 2027 ACM Conference on Management of Data (SIGMOD 2027, CCF-A).

  2. Zhuoyue Wan, Wentao Hu, Chen Jason Zhang, Yuanfeng Song, Shuaimin Li, Ruiqiang Xiao, Xiao-Yong Wei, Raymond Chi-Wing Wong.
    OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models.
    Accepted at 2026 International Conference on Data Engineering (ICDE 2026, CCF-A).

  3. Zhuoyue Wan, Yuanfeng Song, Shuaimin Li, Chen Jason Zhang, Raymond Chi-Wing Wong.
    DataVisT5: A Pre-trained Language Model for Jointly Understanding Text and Data Visualization.
    Accepted at 2025 International Conference on Data Engineering (ICDE 2025, CCF-A).

  4. Shuaimin Li, Liyang Fan, Zeyang Li, Zhuoyue Wan, Yufang Lin, Shiwen Ni, Feiteng Fang, Hamid Alinejad-Rokny, Yuanfeng Song, Kun Jing, Chen Jason Zhang, Min Yang.
    SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models.
    Accepted at Findings of the Association for Computational Linguistics: ACL 2026.

  5. Shuaimin Li, Yuanfeng Song, Xuanang Chen, Anni Peng, Zhuoyue Wan, Chen Jason Zhang, Raymond Chi-Wing Wong.
    VisPoison: An Effective Backdoor Attack Framework for Tabular Data Visualization Models.
    Accepted at 2026 International Conference on Data Engineering (ICDE 2026, CCF-A).

  6. Luyang Luo, Xin Huang, Minghao Wang, Zhuoyue Wan, Hao Chen.
    Medical Image Debiasing by Learning Adaptive Agreement from a Biased Council.
    Medical Image Analysis, 2025 (MIA, JCR Q1).

Preprints

  1. Huahang Li, Wentao Hu, Zhuoyue Wan, Chen Jason Zhang, Haoyang Li, Xiaoyong Wei.
    DataClaw: An Autonomous Data Agent with Instant Messaging Integration.
    arXiv preprint, 2026.

  2. Yan Luo, Zhuoyue Wan, Nemin Wu, Yuzhong Chen, Gengchen Mai, Fu-lai Chung, Kent Larson.
    TransFlower: An Explainable Transformer-Based Model with Flow-to-Flow Attention for Commuting Flow Prediction.
    arXiv preprint, 2024.

Honors and Awards

  • Second-class Scholarship, Chongqing University, May 2021
  • Advanced Individual of Scientific and Technological Academic Innovation, Chongqing University, Dec. 2020
  • Third Prize, The 8th TipDM Cup Data Mining Challenge Committee, Jun. 2020
  • Outstanding Student, Chongqing University, Jan. 2020
  • Outstanding Student, Chongqing University, Jan. 2019
  • Second Prize, Chinese Mathematics Competitions, Nov. 2018
  • Third-class Scholarship, Chongqing University, Nov. 2018

Additional Information

  • Pronouns: he/him/his
  • Basketball: Won the Chongqing Championship in the CUBA second-level league while at Chongqing University.