Yidan Zhang

School of Science and Engineering
The Chinese University of Hong Kong, Shenzhen

I am a Ph.D. student in Computer and Information Engineering at The Chinese University of Hong Kong, Shenzhen, advised by Prof. Xiaoguang Han. My research explores how multimodal models can understand and remember a physical world that changes over time. I focus on 4D spatial reasoning, long-video memory, and interactive multimodal agents, with experience in benchmark design, large-scale multimodal data construction, and video MLLM training.

Before starting my Ph.D., I completed my M.Phil. at CUHK-Shenzhen and my B.Eng. in Computer Science at Central China Normal University. I was also an exchange student at the University of California, Berkeley.

I am currently looking for a research internship in multimodal learning.

news

Jan 01, 2026	VC-Agent was accepted to ACM Multimedia 2026.
Jan 01, 2026	ReconViaGen was accepted to ICLR 2026.
Jul 01, 2024	Nominated for the WAIC 2024 Youth Outstanding Paper Award.
Jun 01, 2023	MVImgNet received the CCF CAD&CG 2023 Open-source Dataset of the Year.

selected publications

ACM MM

VC-Agent: An Interactive Agent for Customized Video Dataset Collection

Yidan Zhang, Mutian Xu, Yiming Hao, and 6 more authors

In ACM International Conference on Multimedia, 2026

Abs DOI arXiv Website

Customized video datasets are difficult to scale because users rarely know how to state every requirement in a single query. VC-Agent is the first interactive MLLM agent that turns lightweight feedback into an evolving collection policy, using template-based acceptance and attribute-aware rejection. Its end-to-end system combines a Web UI, video proposal, iterative criteria refinement, filtering, and automatic scale-up. In user studies, participants collected 335K videos across eight datasets with only minutes of interaction per dataset and 84–92% judged quality.
CVPR

MVImgNet: A Large-scale Dataset of Multi-view Images

Xianggang Yu, Mutian Xu, Yidan Zhang, and 10 more authors

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Abs Website

Large-scale real-world 3D data is expensive to collect, leaving 3D learning without an ImageNet-scale source of multi-view observations. MVImgNet contains 6.5M frames from 219,188 videos across 238 classes, with object masks, camera parameters, and point clouds. It supports radiance-field reconstruction, multi-view stereo, and view-consistent understanding, and further yields MVPNet, a real-world point-cloud dataset with 87,200 objects.