Qingyuan Zeng

Qingyuan Zeng

The Hong Kong University of Science and Technology (Guangzhou)

About Me

I am a Ph.D. student in the Artificial Intelligence Thrust at the Hong Kong University of Science and Technology (Guangzhou), supervised by Dr. Jintai Chen. My current doctoral research focuses on ECG signal analysis, rule mining for tabular data, and drug discovery.

I earned my Master's degree in Artificial Intelligence from Xiamen University, where I was advised by Prof. Min Jiang. During my master's studies, I focused on building trustworthy AI algorithms, specifically enhancing their security, robustness, interpretability, and fairness.

I hold a Bachelor's degree in Computer Science and Technology from Guangzhou University of Chinese Medicine, where I was advised by Prof. Wu Zhou. My academic journey has been driven by a passion for bridging machine learning theory with practical applications in high-stakes domains, particularly in clinical medicine.

Education

Ph.D. in Artificial Intelligence

The Hong Kong University of Science and Technology (Guangzhou)

Jan. 2026 - Present

Master of Artificial Intelligence

Xiamen University

Sep. 2022 - Jun. 2025

Bachelor of Computer Science

Guangzhou University of Chinese Medicine

Sep. 2018 - Jun. 2022

Research Experience

AI for Healthcare and Tabular Data Mining

Supervisor: Dr. Jintai Chen | Nov. 2025 - present

Developing advanced deep learning models for precise ECG classification and automated rule mining from clinical trial tabular data.

Security and Robustness of AI Algorithms

Supervisor: Professor Min Jiang | Feb. 2023 - Sep. 2025

This research reveals how attackers can subtly and efficiently alter AI outputs, like image captioning and object detection, without internal model access.

Interpretability and Fairness of AI Algorithms

Supervisor: Professor Min Jiang | Sep. 2022 - Feb. 2024

This research underscores the need for fairness in ML algorithms, examining how subgraph patterns cause bias in GNNs and suggesting mitigation strategies.

AI Algorithms for Clinical Tumor Characterization

Supervisor: Professor Wu Zhou | Sep. 2020 - Jun. 2022

This research exposes the shortcomings of conventional mathematical models in DWI and DCE-MRI for tumor analysis, proposing an AI model with spatiotemporal attention for direct prediction.

Publications

Publication Summary: total: 14 papers including 8 first-author papers

(* denotes corresponding author, co-first authors are equally contributed.)

Academic Service

Honors & Awards

Work Experience

Medical Imaging Algorithm Engineer

Bayer AG (Top-500 company) | Guangzhou, China | Jun. 2021 - Mar. 2022

Conducted research on Deep Neural Networks (DNN) to accelerate the computation of pharmacokinetic (PK) parameter maps in Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI), enhancing the efficiency and accuracy of diagnostic tools.

Skills