Hongjue Zhao

PhD Student in Computer Science at UIUC.

xixi.jpg

Hello there! I am Hongjue Zhao (赵泓珏), a second-year Ph.D. student in Computer Science at University of Illinois Urbana-Champaign (UIUC), under the supervision of Prof. Tarek Abdelzaher. I received my Bachelor’s degree in Automation from Zhejiang University, where I was affiliated with Chu Kochen Honor College and College of Control Science and Engineering.

My research interests lie in physics-informed machine learning for cyber-physical systems. Specifically, I aim to integrate AI with control theory to enhance the performance, robustness, and reliability of AI algorithms across various applications.

News

May 13, 2026 I am recognized as a Gold Reviewer for ICML 2026!
Apr 30, 2026 Our papers WestWorld and Dywave are accepted by ICML 2026, and WestWorld receives a Spotlight distinction. Congratulations to Yuchen and Tommy!
Mar 01, 2026 Our papers WestWorld is accepted by ICLR 2026 Workshop World Models.Congratulations to Yuchen!
Jan 26, 2026 Our paper ODESteer is accepted by ICLR 2026!
Sep 18, 2025 Our paper AdaTS is accepted by NeurIPS 2025. Congratulations to Deniz!

Selected Publications

  1. odesteer.png
    ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
    Hongjue Zhao, Haosen Sun, Jiangtao Kong, Xiaochang Li, Qineng Wang, Liwei Jiang, Qi Zhu, Tarek Abdelzaher, Yejin Choi, Manling Li, and Huajie Shao
    In The Fourteenth International Conference on Learning Representations, 2026
    arXiv Paper Code Website
  2. cat.png
    CAT: Interpretable concept-based taylor additive models
    Viet Duong, Qiong Wu, Zhengyi Zhou, Hongjue Zhao, Chenxiang Luo, Eric Zavesky, Huaxiu Yao, and Huajie Shao
    In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
    arXiv Paper Code
  3. vf-node.png
    Accelerating Neural ODEs: A Variational Formulation-based Approach
    Hongjue Zhao, Yuchen Wang, Hairong Qi, Zijie Huang, Han Zhao, Lui Sha, and Huajie Shao
    In The Thirteenth International Conference on Learning Representations, 2025
    Paper Code
  4. phy-ssm.png
    A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
    Yuchen Wang, Hongjue Zhao, Haohong Lin, Enze Xu, Lifang He, and Huajie Shao
    arXiv preprint arXiv:2507.10792, 2025
    arXiv Paper Code