Jianhao Huang

Hi, I am Jianhao Huang (黄健浩). I am a first-year Ph.D. in Computer Science department of UCLA, advised by Prof. Baharan Mirzasoleiman.

Earlier, I completed my B.E. in Computer Science at Shanghai Jiao Tong University ACM class, where I was fortunate to be mentored by Prof. Junchi Yan and Prof. Shiyu Liang. I also had a wonderful time during my research internships at Princeton University with Prof. Jason D. Lee, and at New York University with Prof. Jinyang Li and Prof. Aurojit Panda.

GitHub  /  Google Scholar

profile photo

Research

(* indicates equal contribution)

I'm interested in machine learning (theory), optimization and interpretability. Currently, I am working on diffusion language models (DLMs).

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought


Jianhao Huang*, Zixuan Wang*, Jason D. Lee
ICLR 2025 (spotlight, top 5.1%), 2025
arxiv /

On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance Representation


Xinyu Ye, Hao Xiong, Jianhao Huang, Ziang Chen, Jia Wang, Junchi Yan
ICLR 2025 (Poster), 2025
pdf /

Service

I have served as a reviewer for ICLR.

I was also a teaching assistant for the following courses:

  • Programming (CS1953@SJTU, Fall 2022)
  • Principle and Practice of Computer Algorithms (CS1952@SJTU, Summer 2023)
  • Data Structure (CS1951@SJTU, Fall 2023)
  • Probability (MATH2701@SJTU, Spring 2024)

Miscellaneous

Besides research, I enjoy playing the violin and making music by myself, which brings me joy and inspiration.


Design and source code from Jon Barron's website
© 2025 Jianhao Huang