Yizhang ZHU
Incoming Ph.D. Student @ HKUST(GZ)-DIAL

👋 Hi, welcome to my page!

I'm an incoming Ph.D. student in Data Science and Analytics, supervised by Prof. Yuyu LUO at the Hong Kong University of Science and Technology (Guangzhou), where I also completed my M.Phil. studies. Prior to that, I earned my B.Eng. degree in Computer Science and Technology from Chongqing University. My research centers on AI for data analytics, with the aim of democratizing data science. Currently, I'm particularly interested in Natural Language to SQL and Automated Data Analysis.

I'm open to opportunities for communication and collaboration. Feel free to reach out!

Google Scholar GitHub LinkedIn ORCID Résumé
Education
  • The Hong Kong University of Science and Technology (Guangzhou)
    The Hong Kong University of Science and Technology (Guangzhou)
    Ph.D. Student in Data Science and Analytics
    Sept. 2025 - Present
  • The Hong Kong University of Science and Technology (Guangzhou)
    The Hong Kong University of Science and Technology (Guangzhou)
    M.Phil. in Data Science and Analytics
    Sept. 2023 - Jul. 2025
  • Chongqing University
    Chongqing University
    B.Eng. in Computer Science and Technology
    Sept. 2019 - Jul. 2023
Experience
  • NUS Chongqing Research Institute
    NUS Chongqing Research Institute
    Visiting Student in Computer Engineering Joint Program
    Sept. 2022 - May. 2023
Fundings and Awards
  • Data Science and Analytics Thrust Volunteer Grant
    2025/05
  • Greater Bay Area CS Academic Poster Competition (Most Popular Poster)
    2025/03
  • HKUST(GZ) Red Bird M.Phil. Studentship
    2023/09
  • Excellent Graduates of Chongqing University
    2023/06
  • General Scholarship of Chongqing University
    2022/09
  • National Mathematical Contest of Modelling (First Prize in Chongqing)
    2021/10
News
2025
🎉 EllieSQL has been accepted by COLM 2025! Finger crossed for the Canada visa...
Jul 08
🎓️ I successfully defended my M.Phil. thesis! Thanks all support throughout my M.Phil. journey!
May 23
🎉 RAMer has been accepted by IJCAI 2025! Thanks to Xudong!
Apr 29
🐘 We released EllieSQL, a cost-efficient Text-to-SQL framework with complexity-aware routing.
Apr 03
2024
🎉 Our paper "Are Large Language Models Good Statisticians?" has been accepted by NeurIPS 2024!
Jun 21
🥳 Passed the Master Thesis Proposal Quality Assessment!
Jan 12
2023
🔬 Started my RPg studies at HKUST(GZ) and joined DIAL.
Sep 01
🎓️ Graduated from Chongqing University with a B.Eng. in Computer Science and Technology!
Jun 23
Selected Publications (view all )
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian LIN, Yanlin QI, Yizhang ZHU, Themis Palpanas, Chengliang CHAI, Nan TANG, Yuyu LUO

ArXiv

[Paper] [Code]

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian LIN, Yanlin QI, Yizhang ZHU, Themis Palpanas, Chengliang CHAI, Nan TANG, Yuyu LUO

ArXiv

[Paper] [Code]

Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights
Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights

Yifan WU, Lutao YAN, Yizhang ZHU, Yinan MEI, Jiannan WANG, Nan TANG, Yuyu LUO

ArXiv

[Paper]

Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights
Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights

Yifan WU, Lutao YAN, Yizhang ZHU, Yinan MEI, Jiannan WANG, Nan TANG, Yuyu LUO

ArXiv

[Paper]

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing
EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

Yizhang ZHU, Runzhi JIANG, Boyan LI, Nan TANG, Yuyu LUO

COLM 2025

[Homepage] [Paper] [Code]

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing
EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

Yizhang ZHU, Runzhi JIANG, Boyan LI, Nan TANG, Yuyu LUO

COLM 2025

[Homepage] [Paper] [Code]

RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition
RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

Xudong YANG, Yizhang ZHU, Nan TANG, Yuyu LUO

IJCAI 2025

[Paper] [Code]

RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition
RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

Xudong YANG, Yizhang ZHU, Nan TANG, Yuyu LUO

IJCAI 2025

[Paper] [Code]

Are Large Language Models Good Statisticians?
Are Large Language Models Good Statisticians?

Yizhang ZHU, Shiyin DU, Boyan LI, Yuyu LUO, Nan TANG

NeurIPS 2024

[Homepage] [Paper] [Code] [Video]

Are Large Language Models Good Statisticians?
Are Large Language Models Good Statisticians?

Yizhang ZHU, Shiyin DU, Boyan LI, Yuyu LUO, Nan TANG

NeurIPS 2024

[Homepage] [Paper] [Code] [Video]

All publications