Ze Liu (刘泽)

Ze Liu is currently a final-year joint Ph.D. candidate at the University of Science and Technology of China (USTC) and Microsoft Research Asia (MSRA), co-supervised by Prof. Baining Guo and Prof. Yong Wang. He received his B.S. degree from USTC in 2019 with the highest honor, the "Guo Moruo Scholarship". Currently, he is working as a research intern at the Visual Computing Group in MSRA, collaborating closely with Han Hu, Yue Cao and Zheng Zhang.

His primary research interests lie in computer vision and deep learning, with a specific focus on designing visual architectures and developing large-scale vision/multi-modality models. He also loves training large language models.

His work of Swin Transformer won the Best Paper Award (Marr Prize) of ICCV 2021. Additionally, he was selected as a recipient of the Microsoft Research PhD Fellowship in 2022.

He is currently seeking a research position to start in the winter of 2023 or the summer of 2024 (China, North America, Europe), please feel free to drop him an email if you are interested in his research.

Email / CV / Google Scholar / Github / LinkedIn

Recent News

[2023/03] Our work of Tutel-MoE was accepted by MLSys 2023.
[2023/03] One paper accepted by CVPR 2023.
[2022/11] One spotlight paper accepted by NeurIPS 2022.
[2022/03] Two papers accepted by CVPR 2022.
[2021/10] Our Swin Transformer won the Best Paper Award (Marr Prize) of ICCV 2021!
[2021/07] Two papers with one oral accepted by ICCV 2021.
[2021/06] Our Video Swin Transformer achieves new SOTA on Kinetics-400 , Kinetics-600 and Something-Something V2 .
[2021/04] Code available for Group-Free 3D Object Detection via Transformers
[2021/04] Code and pretrained models for Swin Transformer (object detection , semantic segmentation) are released.
[2021/03] Our Swin Transformer achieves new SOTA on COCO detection and ADE20K semantic segmentation .
[2020/07] One paper accepted by ECCV 2020.

Research Experience

[2019/08 ~ Present] Research Intern, Microsoft Research Asia (Mentor: Han Hu).
[2018/08 ~ 2019/08] Research Intern, Microsoft Research Asia (Mentor: Jifeng Dai ).

Selected Publications
(* indicates equal contribution)

	Could Giant Pretrained Image Models Extract Universal Representations? Yutong Lin, Ze Liu, Zheng Zhang, Han Hu, Nanning Zheng, Stephen Lin, Yue Cao Neural Information Processing Systems (NeurIPS), 2022 Spotlight paper
	Swin Transformer V2: Scaling Up Capacity and Resolution Ze Liu, Han Hu, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang, Li Dong, Furu Wei, Baining Guo IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 CVPR 2022 Top-10 Influential Papers (Rank 9) paper / code Star
	Video Swin Transformer Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, Han Hu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 CVPR 2022 Top-10 Influential Papers (Rank 4) paper / code Star
	Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo International Conference on Computer Vision(ICCV), 2021 Best Paper Award (Marr Prize)! paper / code Star
	Group-Free 3D Object Detection via Transformers Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong International Conference on Computer Vision(ICCV), 2021 paper / code Star
	A Closer Look at Local Aggregation Operators in Point Cloud Analysis Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong European Conference on Computer Vision(ECCV), 2020 paper / code Star

Selected Honors

Microsoft Research PhD Fellowship.
2022
ICCV Best Paper Award (Marr Prize).
2021
World Artificial Intelligence Conference Youth Outstanding Paper Award.
2021
Guo Moruo Scholarship (The highest honor in USTC , 33 graduates per year).
2019
National Scholarship.
2021, 2017
Outstanding graduates of USTC.
2019
Chinese Academy of Sciences Scholarship.
2017
First Prize, National Undergraduate Electronics Design Contest.
2017

Professional Services

Journal Reviewer: TPAMI, TIP, NEUCOM, PR, TNNLS.
Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS.

Modified from Jon Barron