Honam WONG

Honam WONG

First-year PhD @ UPenn, passionate about understanding deep learning & LLM

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 is supported by AWS Asset Fellowship at Penn.

My research interests lie in the theory and empirical science of deep learning and LLMs. On the theoretical side, I study fundamental principles of learning and scaling, with an emphasis on training dynamics and expressiveness. On the empirical side, I investigate the model’s behavior through controlled experiments. I am also interested in mechanistic interpretability as a way to uncover how neural networks represent and manipulate information.

Overall, I see myself as both a theorist and an experimentalist, driven by the goal of opening the black box of neural networks and LLMs from multiple complementary angles.

Outside of research, I am (was) running a popular science channel with over 34K subscribers and 1.7 million total views.

Lessons learnt while doing theory

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 PhD application)
  • 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), ICLR 2026 Workshop on Scientific Methods for Understanding Deep Learning (Sci4DL)

Selected Coursework

  • PhD: Machine Learning Theory, Stochastic Process, Statistical Theory, Hedging and Acceleration in Optimization.

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)

Academic Activities

  • Heidelberg Laureate Forum, Heidelberg, Germany, Sep 2024
  • International Conference on Learning Representations (ICLR), Vienna, May 2024