Yuze Zhu 朱昱泽

Visiting Student, Computer Science, UC Berkeley · School of Artificial Intelligence, UCAS.

prof_pic.jpg

I am a fourth-year undergraduate student at the School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS). Since August 2026, I have been a visiting student in Computer Science at the University of California, Berkeley. My research interests lie in Embodied AI, with a specific focus on Vision-Language Action (VLA).

Beyond research, I am a passionate photographer. Born and raised in Hangzhou, I spent three years in Beijing for my studies and am now based in Berkeley, California, and I always enjoy meeting friends from around the world. If you would like to chat about research, daily life, or anything culturally Chinese, please feel free to reach out. Emails from anywhere are warmly welcome!

Experience

full CV
UC Berkeley logo

Berkeley AI Research (BAIR) · UC Berkeley

Sep 2026 - Present
Berkeley, California · Advised by Roei Herzig

Investigating World-Action Model (WAM) representations and in-context learning for embodied agents, developing one-shot activation mechanisms that exploit a single demonstration to steer robot video generation and the resulting action prediction.

FiveAges logo

FiveAges

Mar 2026 - Aug 2026
Beijing, China · Advised by Yan Huang and Liang Wang

Worked on embodied intelligence algorithms, with a focus on Vision-Language-Action (VLA) models and bridging academic research with real-world robotic deployment.

CASIA logo
Beijing, China · Advised by Junyu Gao and Changsheng Xu

Conducted research on Vision-Language Navigation (VLN) with a focus on self-correction, leading the full research cycle from idea proposal and codebase development to data analysis and manuscript writing. Co-authored a paper (second author) accepted by ICML 2026.

Aug 20, 2026 Started as a visiting student in Computer Science at the University of California, Berkeley.
May 01, 2026 Our paper “SC²-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments” has been accepted by ICML 2026!
Mar 04, 2026 Started my internship at FiveAges (中科第五纪) as an Embodied AI Algorithm Intern.
Feb 08, 2026 Setting up my personal site as a new beginning. Looking forward to the future with great anticipation.

Selected Publications

all publications
  1. arXiv
    bridgevla_plus.png
    BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
    Peiyan Li*, Yuze Zhu*, Yixiang Chen, Qisen Ma, Yuan Xu, Jiabing Yang, He Guan, Yan Huang, Hongtao Wu, Xiao Ma, Tao Kong, Liang Wang, and Tieniu Tan
    arXiv preprint arXiv:2608.05042, 2026
  2. SC^2-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
    Xuan Yao, Yuze Zhu, Junyu Gao, Zongmeng Wang, and Changsheng Xu
    ICML, 2026