Jianhao Huang

Hi, I am Jianhao Huang (黄健浩). I am a first-year Ph.D. in UCLA CS department, 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.

Research

(* indicates equal contribution)

I'm interested in machine learning (theory), optimization and interpretability.

Why is A+B Better Than B? A Simple Graph Perspective on Task Transfer [PDF]

Dang Nguyen*, Jianhao Huang*, Ali Payani, Baharan Mirzasoleiman

ICML Workshop, 2026

How Transformers Learn to Plan via Multi-Token Prediction [arXiv]

Jianhao Huang*, Zhanpeng Zhou*, Renqiu Xia, Baharan Mirzasoleiman, Weijie Su, Wei Huang

COLM (poster), 2026

Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision [arXiv]

Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai, Baharan Mirzasoleiman

In Submission, 2026

Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from k-Parity [arXiv]

Jianhao Huang, Baharan Mirzasoleiman

ICML (poster), 2026

Scaling Point-based Differentiable Rendering for Large Scale 3D Reconstruction [arXiv]

Hexu Zhao, Xiaoteng Liu, Xiwen Min, Jianhao Huang, Youming Deng, Yanfei Li, Ang Li, Jinyang Li, Aurojit Panda

In Submission, 2025

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

Jianhao Huang*, Zixuan Wang*, Jason D. Lee

ICLR (spotlight, top 5.1%), 2025

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

Xinyu Ye, Hao Xiong, Jianhao Huang, Ziang Chen, Jia Wang, Junchi Yan

ICLR (poster), 2025

[2026 Jun. - 2026 Nov.] Student Researcher, Google, Los Angeles, CA, advised by Prof. Adel Javanmard.

[2024 Jul. - 2024 Dec.] Research Intern, Princeton University, Princeton, NJ, advised by Prof. Jason D. Lee.

[2024 Jul. - 2024 Dec.] Research Intern, New York University, New York, NY, advised by Profs. Jinyang Li and Aurojit Panda.

[SU. 2026] COSMOS Cluster 10 , Graduate Teaching Instructor, UCLA.

[SP. 2024] Probability Theory (MATH2701), Teaching Assistant, SJTU.

[FA. 2023] Data Structure (CS1951), Teaching Assistant, SJTU.

[SU. 2023] Principle and Practice of Computer Algorithms (CS1952), Teaching Assistant, SJTU.

[FA. 2022] Programming (CS1953), Teaching Assistant, SJTU.

[Reviewer] ICLR '25-'26, ICML '26, COLM '26, NeurIPS '26.

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