Research (* indicates equal contribution)
I'm interested in machine learning (theory), optimization and interpretability.
|
How Transformers Learn to Plan via Multi-Token Prediction
Jianhao Huang*, Zhanpeng Zhou*, Renqiu Xia, Baharan Mirzasoleiman, Weijie Su, Wei Huang
in submission, 2026
arxiv /
|
Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai, Baharan Mirzasoleiman
in submission, 2026
arxiv /
|
Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from k-Parity
Jianhao Huang, Baharan Mirzasoleiman
ICML (poster), 2026
arxiv /
|
Scaling Point-based Differentiable Rendering for Large Scale 3D Reconstruction
Hexu Zhao, Xiaoteng Liu, Xiwen Min, Jianhao Huang, Youming Deng, Yanfei Li, Ang Li, Jinyang Li, Aurojit Panda
in submission, 2025
arxiv /
|
Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
Jianhao Huang*, Zixuan Wang*, Jason D. Lee
ICLR (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 (poster), 2025
pdf /
|
Service
I have served as a reviewer for ICLR 25'-26', ICML 26', COLM 26'.
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.
|
|