Hi there! I am Zhang Zhang, an incoming Ph.D. student in the Department of Automation at Tsinghua University, advised by Prof. Yueqi Duan and Prof. Jiwen Lu. I work closely with Shengjun Zhang and Chensheng Dai.
My research focuses on Embodied AI Systems and World Models. Recently, I have been particularly interested in building embodied agents that can continuously learn and evolve through interaction with their environments.
Outside of research, I enjoy photography, and a selection of my photographs can be found in the Gallery. I also occasionally share thoughts and writings on the Blog, with more to come.
I am always happy to chat about research, exchange ideas, and explore potential collaborations. If you are interested in working with us as a research intern, collaborating on Embodied AI or World Models, or simply grabbing a coffee and chatting about cool ideas, feel free to reach out!
🔥 News
- 2026.06: RhymeFlow is accepted to ECCV 2026!
- 2026.05: MBench is released on arXiv.
- 2026.02: E-GRPO is accepted to CVPR 2026 Findings.
📝 Publications
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
Shengjun Zhang*, Zhang Zhang*, Simin Huang, Zhenyu Tang, Hanyang Wang, Chensheng Dai, Min Chen, Yifan Li, Yuxin Li, Yingjie Chen, Hao Liu, Chen Li, Jing Lyu, Yueqi Duan
* Equal contribution
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Shengjun Zhang, Zhang Zhang, Chensheng Dai, Yueqi Duan
Chensheng Dai*, Shengjun Zhang*, Yifan Li, Zhang Zhang, Zheng Zhu, Yueqi Duan
* Equal contribution
📖 Educations
- 2023.09 - now, B.Eng. Department of Automation, Tsinghua University
💻 Internships
- 2025.07 - now, Research Intern at Prof. Yueqi Duan’s Lab.
- 2026.01 - 2026.06, Research Intern at WXG, tencent.