About me

Hi! I am a first-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 the Hong Kong University of Science and Technology (HKUST) in 2025.

My research interests lie in theory and empirical science of deep learning and LLMs. I am interested in fundamental principles of learning and scaling. For language models, I am interested in understanding the architecture, reasoning, alignment and efficency properties via clean sandbox setups. Empirically I am interested in interpretability as a tool to understand neural networks. Overall I am passionate about opening the black box of neural network and LLM through all possible ways.

Outside of research, I enjoy exploring the world. I also enjoy listening to music and watching anime. I am running a popular science channel with over 34K subscribers and 1.6 million total views.

Education

• PhD in Computer & Information Science, The University of Pennsylvania (Ongoing)
• BSc in Computer Science & Mathematics, The Hong Kong University of Science and Technology, 2025 (GPA 4.099/4.3, Rank 1st, before grad-school app.)
• Spring Exchange, EPFL, 2024

Review Experience

• Conference / Journal: NeurIPS 2025, ICML 2025, L4DC 2025, NeurIPS 2024, TMLR
• Workshop: ICML 2024 Workshop on Theoretical Foundations of Foundation Models (TF2M), ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (BGPT)

Selected Coursework

• PhD: Machine Learning Theory, Generative AI for Research, Randomized Algorithm (Audit)
• Undergraduate: Machine Learning, Optimization for ML, Functional Analysis, Numerical Analysis, Design and Analysis of algorithms

Selected Awards

• Chern Class Achievement Scholarship (Outstanding) (Highest Award for math graduates)
• HKUST Epsilon Fund Award 24’ (For top math students at HKUST, <5 undergraduates each year)
• Hong Kong Government Scholarship 22’ (Highest Academic Award in undergraduate, renewed annually)

Academic Activities

• Heidelberg Laureate Forum, Heidelberg, Germany, Sep 2024
• LeT-All Mentorship Workshop, Learning Theory Alliance, Online, June 2024
• International Conference on Learning Representations (ICLR), Vienna, May 2024
• Conference on Parismony and Learning (CPAL), Hong Kong, Jan 2024