About me

Hi! I am an incoming Computer Science PhD student at University of Pennsylvania, advised by Surbhi Goel in Computer Science, and Enric Boix from Wharton Statistics and Data Science. I am about to graduate from The Hong Kong University of Science and Technology (HKUST), with BSc in Computer Science & Mathematics.

My research interests lie in the theory and empirical science of deep learning and LLMs. I am particularly interested in theories that can guide practical applications, such as scaling laws and mup transfer, or theories that uncover fundamental principles of deep learning. In terms of empirical science, I am interested in using sandbox setups to explore the mechanisms of language models (and possibly the interplay with theory), as well as developing mechanistic interpretability tools to probe their inner working structures. Here’s a recent workshop that echoes my interest!

My research interest and taste are shaped by chatting with peers and senior researchers (see Friend Link). Therefore, do reach out and chat if you share similar interests! I have also compiled some preliminary notes on these topics (see Note).

Education

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

Undergraduate Research Experience

• July 2024 ~ Jan 2025: Research Internship
  • Interned under Wei Hu, at University of Michigan
  • Worked on understanding linear representation hypothesis, and mechanism of compositional generalization under in-context learning setup
• July 2023 ~ Sep 2024: Remote
  • Interned under Yiping Lu, at Northwestern University
  • Worked on benign overfitting for PINN
  • Had a first-authored paper under review
  • Organized the Deep Learning Theory Reading Group inside the research group
• Oct 2022 ~ Nov 2023: Undergraduate Research Opportunities Program (UROP) @ HKUST
  • Interned under Tong Zhang’s group, advised by PhD Student Yong Lin
  • Worked on out-of-distribution generalization
  • Published a coauthored paper at ICLR2024, and attended the Conference at Vienna

Academics

• Cumulative GPA: 4.099/4.3, Rank: 1 (Before Grad School Application)
• Graduate-level courses: COMP5212 Machine Learning (A), MATH5411 Advanced Probability Theory (A), CS439 Optimization in Machine Learning (6/6, at EPFL), CS552 Modern NLP (5.5/6, at EPFL)
• Selected Undergraduate courses: COMP3711 Design and Analysis of Algorithms (A+), MATH4335 Optimization (A), MATH4063 Functional Analysis (A), MATH3312 Numerical Analysis (A+), COMP2012H Honors OOP and Data Structure (A+), MATH3043 Honors Real Analysis (A+), MATH2431 Honors Probability (A+), CS251 Theory of Computation (5.5/6, at EPFL)

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)

Awards

• Summer Research Sponsorship (HKD25,000 from Computer Science and Mathematics department)
• Hong Kong Government Scholarship 22’ (HKD40,000 per year, for students with GPA>3.95)
• HKUST Epsilon Fund Award 24’ (HKD5,000, for top students in the math department at HKUST, <5 undergraduates each year)
• Tin Ka Ping Scholarship (Exchange) 24’ (HKD20,000)
• HKUST Study Abroad Funding Support 24’ (HKD10,000)
• Chern Class Entry & Talent Scholarship 22’, 23’, 24’ (for top students in the math department at HKUST)
• Dean List in all semesters

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