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.

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.