CV Download PDF

Ph.D. Student in Computer Science

University of Illinois Urbana-Champaign

Computer Science

• Advisor: Prof. Tarek Abdelzaher
• Research Interests: i) Physics-informed machine learning for Cyber-Physical Systems, ii) The intersection of AI and Control

B.Eng. in Automation

Zhejiang University

Automation

• Received an Honor Degree in Chu Kochen Honors College
• Overall GPA: 3.93/4.0 (88.39/100). The last two years GPA: 3.98/4.0 (89.33/100)

Research Assistant

Zhejiang University

Advisor: Prof. Zhi Wang

• Focused research about the intersection of AI and Control.

Research Intern

William & Mary

Advisor: Prof. Huajie Shao

• Focused on research about polynomial neural networks and Neural ODEs.

WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems

ICML 2026 Spotlight

Yuchen Wang, Jiangtao Kong, Sizhe Wei, Xiaochang Li, Haohong Lin, Hongjue Zhao, Tianyi Zhou, Lu Gan, Huajie Shao

Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals

ICML 2026

Tomoyoshi Kimura, Denizhan Kara, Jinyang Li, Hongjue Zhao, Yigong Hu, Yizhuo Chen, Xiaomin Ouyang, Shengzhong Liu, Tarek Abdelzaher

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

ICLR 2026

Hongjue Zhao, Haosen Sun, Jiangtao Kong, Xiaochang Li, Qineng Wang, Liwei Jiang, Qi Zhu, Tarek Abdelzaher, Yejin Choi, Manling Li, Huajie Shao

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments

ICML 2025

Yuchen Wang, Hongjue Zhao, Haohong Lin, Enze Xu, Lifang He, Huajie Shao

RestoreML: Practical Unsupervised Tuning of Deployed Intelligent IoT Systems

DCOSS-IoT 2025 Best Paper

Jinyang Li, Yizhuo Chen, Ruijie Wang, Tomoyoshi Kimura, Tianshi Wang, You Lyu, Hongjue Zhao, Binqi Sun, Shangchen Wu, Yigong Hu, Denizhan Kara, Beitong Tian, Klara Nahrstedt, Suhas Diggavi, Jae H Kim, Greg Kimberly, Guijun Wang, Maggie Wigness, Tarek Abdelzaher

Accelerating Neural ODEs: A Variational Formulation-based Approach

ICLR 2025

Hongjue Zhao, Yuchen Wang, Hairong Qi, Zijie Huang, Han Zhao, Lui Sha, Huajie Shao

CAT: Interpretable Concept-based Taylor Additive Models

KDD 2024 Best Paper

Viet Duong, Qiong Wu, Zhengyi Zhou, Hongjue Zhao, Chenxiang Luo, Eric Zavesky, Huaxiu Yao, Huajie Shao

Gold Reviewer

International Conference on Machine Learning (ICML)

Spotlight Paper Award

International Conference on Machine Learning (ICML)

WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems

Best Paper Award

International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)

RestoreML: Practical Unsupervised Tuning of Deployed Intelligent IoT Systems

Best Paper Award

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

CAT: Interpretable Concept-based Taylor Additive Models

ODESteer

Corresponding Paper: ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

• Proposed a unified framework for activation steering in LLM alignment based on ODEs and barrier functions in control theory
• Proposed a new steering method called ODESteer derived from our ODE-based unified framework
• Tool used: Python (Pytorch)

VF-NODE

Corresponding Paper: Accelerating Neural ODEs: A Variational Formulation-based Approach

• Proposed a kind of accelerating technique for Neural ODEs based on the variational formulation of ODEs
• Significantly accelerated the training of Neural ODEs about 10 to 1000 times
• Tool used: Python (JAX)

TaylorNet

Corresponding Paper: CAT: Interpretable Concept-based Taylor Additive Models

• Designed a novel polynomial-based neural architecture
• Utilized Tucker decomposition to reduce the computational complexity
• Tool used: Python (Pytorch)