About me

Hi! I am a second-year PhD student at the University of Pennsylvania, advised by Surbhi Goel (Computer Science) and Enric Boix-Adsera (Wharton Statistics & Data Science). I received my Bachelor’s degree in Computer Science & Mathematics from HKUST in 2025. My research is supported by AWS Asset Fellowship at Penn.

My research interests lie in the theory and empirical science of deep learning and LLMs: running experiments that probe how these models work, then building theory to explain what those experiments reveal. Recently, I am focusing on these research questions:

• Scaling Science. How to train and scale models in a principled way, and how do we understand their training dynamics, both in theory and in practice?
• Alignment Science. How could we keep a model aligned as its capabilities improve? I am interested in exploring the misalignment phenomena that remain poorly understood in AI safety, such as emergent misalignment.

Education

• PhD in Computer & Information Science, The University of Pennsylvania (2025.8 - now)
• BSc in Computer Science & Mathematics, The Hong Kong University of Science and Technology, 2025
• Spring Exchange, EPFL, 2024

Review Experience

• Conference / Journal: NeurIPS (2024, 2025, 2026), ICML 2025, L4DC 2025, TMLR
• Workshop: ICML 2026 Mech Interp Workshop, ICML 2026 CoLoRAI Workshop, ICLR 2026 Workshop on Scientific Methods for Understanding Deep Learning (Sci4DL), ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (BGPT), ICML 2024 Workshop on Theoretical Foundations of Foundation Models (TF2M)

Selected Awards

• AWS Asset Fellowship 26’
• HKUST Epsilon Fund Award 24’ (For top math students at HKUST, <5 undergraduates each year)
• Hong Kong Government Scholarship 22’-25‘ (Highest Undergraduate Academic Award)

Other Academic Activities

• Princeton ML Theory Summer School, August 2026
• Workshop on Theoretical Perspectives on LLMs, UCSD, San Diego, March 2025
• Heidelberg Laureate Forum, Heidelberg, Germany, Sep 2024