Personal Profile

Daquan Zhou, Ph.D., is an Assistant Professor and Doctoral Supervisor at the School of AI for Science, Peking University. He has been selected into the National High-Level Young Talent Program, awarded the Singapore Outstanding PhD (national level), and listed among the Top 100 Talent Portraits. He leads projects such as the National Science and Technology Major Project and the National Natural Science Foundation Youth Fund. His research focuses on robot and agent decision-making, efficient hardware-friendly image & video generation models, and understanding models. Representative academic works include the design and training of efficient network architectures such as MobileNeXT, Fully Attentional Network, MagicVideo, and StoryDiffusion. His single paper has been cited over 4,000 times, and he has received nominations for Best Paper at international academic conferences such as NeurIPS. Related works have been published in top computer science conferences and journals, including IEEE TPAMI, CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR, IJCAI, and DAC. He serves as a program committee member, reviewer, and Keynote Speaker for multiple conferences and journals. He was a recipient of the Singapore President’s Science and Technology Award (team award).

Research Fields

1.Robot and Agent Decision-Making

2.Efficient, Hardware-Friendly Multimodal Generation and Understanding Models

3.Edge Computing

Representative Academic Works

(For the complete list, please visithttps://scholar.google.com/citations?user=DdCAbWwAAAAJ&hl=en）：

1.Zhou, Daquan, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Zihang Jiang, Qibin Hou, and Jiashi Feng. "Deepvit: Towards deeper vision transformer.” (First Autor)

2.Zhou, Daquan, Weimin Wang, Hanshu Yan, Weiwei Lv, Yizhe Zhu, and Jiashi Feng. "Magicvideo: Efficient video generation with latent diffusion models."(First Autor)

3.Zhou, Daquan, Qibin Hou, Yunpeng Chen, Jiashi Feng, and Shuicheng Yan. "Rethinking bottleneck structure for efficient mobile network design.(First Autor)

4.Zhou, Daquan, Zhiding Yu, Enze Xie, Chaowei Xiao, Animashree Anandkumar, Jiashi Feng, and Jose M. Alvarez. "Understanding the robustness in vision transformers."(First Autor)

5.Zhou, Daquan, Kai Wang, Jianyang Gu, Xiangyu Peng, Dongze Lian, Yifan Zhang, Yang You, and Jiashi Feng. "Dataset quantization."(First Author)

6.Wang, Chenyu, Zhen Dong, Daquan Zhou, Zhenhua Zhu, Yu Wang, Jiashi Feng, and Kurt Keutzer. "Epim: Efficient processing-in-memory accelerators based on epitome."(Equal First Author)

7.Zhou, Yupeng, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, and Qibin Hou. "StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation."(Project Leader & Corresponding Author)

8.Kong, Weijie, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong et al. "Hunyuanvideo: A systematic framework for large video generative models."(Project Leader)

Basic Requirements for Prospective Graduate Students