|
Haoyu Zhao I am a first-year Master's student at the College of Computer Science and Technology, Zhejiang University, advised by Prof. Bohan Zhuang and a member of ZIP Lab. My research interests lie in the fields of efficient video world models. Prior to that, I obtained my bachelor's degree from School of Computer Science in Wuhan University. |
|
ResearchI am interested in efficient large 3D models, world models, and spatial reasoning for embodied agents. |
|
Latent Spatial Memory for Video World Models
Weijie Wang*, Haoyu Zhao*, Yifan Yang, Feng Chen, Zeyu Zhang, Yefei He, Zicheng Duan, Donny Y. Chen, Yuqing Yang, Bohan Zhuang† arXiv, 2026 Paper / Project / Code We maintain the external 3D world memory directly in latent space for efficiency. |
|
CoV: Chain-of-View Prompting for Spatial Reasoning
Haoyu Zhao*, Akide Liu*, Zeyu Zhang*, Weijie Wang*, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang ACL, 2026 Project Page / Paper / Code Chain-of-View prompting is a training-free, test-time reasoning framework that enables vision-language models to actively acquire question-relevant viewpoints for embodied question answering and spatial reasoning. |
|
Website template based on Jon Barron's and Weijie Wang's . |