About Me
Hi! I’m Han Zhao (赵晗). I hold my bachelor’s and master’s degrees in Control Science and Engineering from Beijing University of Posts and Telecommunications (BUPT) in 2020 and 2023, respectively. I am currently a second-year joint Ph.D. student in Computer Science and Technology at Zhejiang University and Westlake University (Machine Intelligence Lab, MiLAB), advised by Prof. Donglin Wang.
Research Interests
My current research interests include Embodied Artificial Intelligence, Foundation Models, Reinforcement Learning, and Robotics.
Specifically, I am interested in:
Foundation Models for Robotics: developing efficient and effective foundation models for robotics, including multi-modal large language models and vision-language-action models to enhance robots’ perception and decision-making capabilities.
Scalable Reinforcement Learning Algorithms: developing reinforcement learning algorithms that can effectively manage large-scale data and model capacity for robotic control. This includes methods such as offline reinforcement learning, imitation learning, and more, to enable robots to acquire scalable and generalizable skills.
Motion Planning and Control for Legged Robots: developing motion planning and control algorithms for legged robots, including bipedal and quadruped robots, to enable them to perform complex tasks in real-world environments.
News
[March 4, 2025] A new paper about accelerating the action decoding process of VLA has been online! Check out the paper and our model PD-VLA!
[January 28, 2025] Two papers (QUART-Online and MoRE) have been accepted for ICRA 2025!
[January 23, 2025] VLAS, a work about integrating speech instruction as a new modality into VLA, has been accepted for ICLR 2025!
[January 9, 2025] One paper about control theory with my former supervisor during the master’s program has been accepted for Neurocomputing!
[December 10, 2024] Cobra have been accepted for AAAI-25!
Publications
Preprint
Wenxuan Song, Jiayi Chen, Pengxiang Ding, Han Zhao, Wei Zhao, Zhide Zhong, Zongyuan Ge, Jun Ma, Haoang Li*, "Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding". [ArXiv]
Hongyin Zhang, Diyuan Shi, Zifeng Zhuang, Han Zhao, Zhenyu Wei, Feng Zhao, Sibo Gai, Shangke Lyu, Donglin Wang*, "Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph". [ArXiv]
2025
Xinyang Tong, Pengxiang Ding, Yiguo Fan, Donglin Wang*, Wenjie Zhang, Can Cui, Mingyang Sun, Han Zhao, Hongyin Zhang, Yonghao Dang, Siteng Huang, Shangke Lyu, "QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning". [ArXiv] [project page]
Han Zhao, Wenxuan Song, Donglin Wang*, Xinyang Tong, Pengxiang Ding, Xuelian Cheng, Zongyuan Ge, "MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models". [ArXiv]
Wei Zhao, Pengxiang Ding, Min Zhang, Zhefei Gong, Shuanghao Bai, Han Zhao, Donglin Wang*, "VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation". [ArXiv]
Lei Guo*, Wenbo Xiong, Han Zhao, Yuan Song, Dongming Gan, "A nearly optimal adaptive saturation function tuning method for quasi-sliding mode control based on integral reinforcement learning". [paper]
Han Zhao, Min Zhang, Wei Zhao, Pengxiang Ding, Siteng Huang, Donglin Wang*, "Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference". [ArXiv] [project page] [zhihu] [github] [demo] [twitter@AK]
2024
Pengxiang Ding, Han Zhao, Wenjie Zhang, Wenxuan Song, Min Zhang, Siteng Huang, Ningxi Yang, Donglin Wang*, "QUAR-VLA: Vision-Language-Action Model for Quadruped Robots". [ArXiv]
Yang Liu, Pengxiang Ding, Siteng Huang, Min Zhang, Han Zhao, Donglin Wang*, "PiTe: Pixel-Temporal Alignment for Large Video-Language Model". [ArXiv]
Wenxuan Song, Han Zhao, Pengxiang Ding, Can Cui, Shangke Lyu, Yaning Fan, Donglin Wang*, "GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot". [ArXiv] [project page] [video]
Shangke Lyu, Xin Lang, Han Zhao, Hongyin Zhang, Pengxiang Ding, Donglin Wang*, "RL2AC: Reinforcement Learning-based Rapid Online Adaptive Control for Legged Robot Robust Locomotion".
2023
Shangke Lyu, Han Zhao, Donglin Wang*, "A Composite Control Strategy for Quadruped Robot by Integrating Reinforcement Learning and Model-Based Control". [paper]
Lei Guo*, Han Zhao, "Online adaptive optimal control algorithm based on synchronous integral reinforcement learning with explorations". [paper]
Lei Guo*, Han Zhao, "Model‐free adaptive optimal control of continuous‐time nonlinear non‐zero‐sum games based on reinforcement learning". [paper]
2022
Han Zhao*, Lei Guo, Yuan Song, "System Modelling and Controller Design of a Variable Structure Two-Wheeled Robot Using Robust Adaptive Dynamic Programming". [paper]
Han Zhao*, Lei Guo, "Model-free Nearly Optimal Control of Constrained-Input Nonlinear Systems Based on Synchronous Reinforcement Learning". [paper]
Service
Reviewer for:
Journal
- Knowledge-Based Systems (KBS)
- IET Control Theory & Applications (IET-CTA)
Conference
- IEEE/CVF International Conference on Computer Vision (ICCV)
- IEEE International Conference on Robotics and Automation (ICRA)
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- IEEE Conference on Decision and Control (CDC)
