Zixuan Ye

PhD Student in Artificial Intelligence, HKUST

About Me

Hi👋! I'm Zixuan Ye (叶紫璇), a first-year Ph.D. student at the Hong Kong University of Science and Technology, affiliated with the C4 Group, supervised by Wenhan Luo. I obtained both my Bachelor's and Master's degrees from Huazhong University of Science and Technology, supervised by Hao Lu and Zhiguo Cao. My research interests focus on GenAI, especially in video generation and editing.

I'm always open to new collaborations, so please feel free to get in touch🙋!

News

Jun. 2025
We release UNIC and FullDiT2, which explore the in-context conditioning potential in video editing and the accelaration of the framework.
Feb. 2025
StyleMaster accepted to CVPR 2025.

Education

Ph.D. in Artificial Intelligence

Hong Kong University of Science and Technology (HKUST)

Supervisor: Wenhan Luo

Sep 2025 - Present
Master in Intelligent Science and Technology

Huazhong University of Science and Technology (HUST)

Supervisors: Hao Lu and Zhiguo Cao

Sep 2022 - Jun 2025
B.Eng in Automation

Huazhong University of Science and Technology (HUST)

Sep 2018 - Jul 2022

Experience

Research Intern

Kuaishou Technology

Topic: Controllable video generation: video editing.

Advisors: Dr. Quande Liu and Dr. Xintao Wang.

Feb 2025 - present
Research Intern

Kuaishou Technology

Topic: Controllable video generation: video stylization.

Advisors: Dr. Huijuan Huang and Dr. Xintao Wang.

Jul 2024 - Feb 2025

Publications

Selected Preprint

UNIC: Unified In-Context Video Editing

Zixuan Ye*, Xuanhua He*, Quande Liu, Qiulin Wang, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Qifeng Chen, Wenhan Luo

arXiv:2506.04216

Project PDF
FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers

Xuanhua He, Quande Liu, Zixuan Ye, Weicai Ye, Qiulin Wang, Xintao Wang, Qifeng Chen, Pengfei Wan, Di Zhang, Kun Gai

arXiv:2506.04213

Project PDF

Conference Papers

StyleMaster: Stylize Your Video with Artistic Generation and Translation

Zixuan Ye, Huijuan Huang, Xintao Wang, Pengfei Wan, Di Zhang, Wenhan Luo

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Project PDF Code
Unifying Automatic and Interactive Matting with Pretrained ViTs

Zixuan Ye, Wenze Liu, He Guo, Yujia Liang, Chaoyi Hong, Hao Lu, Zhiguo Cao

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

PDF Code
Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting

Zixuan Ye*, Yutong Dai*, Chaoyi Hong, Zhiguo Cao, Hao Lu

AAAI Conference on Artificial Intelligence (AAAI), 2023

PDF Code
SCAPE: A Simple and Strong Category-Agnostic Pose Estimator

Yujia Liang*, Zixuan Ye*, Wenze Liu, Hao Lu

European Conference on Computer Vision (ECCV), 2024

PDF Code
In-Context Matting

He Guo, Zixuan Ye, Zhiguo Cao, Hao Lu

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Highlight)

PDF Code
Training Matting Models without Alpha Labels

Wenze Liu, Zixuan Ye, Hao Lu, Zhiguo Cao, Xiangyu Yue

AAAI Conference on Artificial Intelligence (AAAI), 2025

PDF Code
SAPA: Similarity-Aware Point Affiliation for Feature Upsampling

Hao Lu, Wenze Liu, Zixuan Ye, Hongtao Fu, Yuliang Liu, Zhiguo Cao

Neural Information Processing Systems (NeurIPS), 2022 (Spotlight)

PDF Code
Video Bokeh Rendering: Make Casual Videography Cinematic

Yawen Luo, Min Shi, Liao Shen, Yachuan Huang, Zixuan Ye, Juewen Peng, Zhiguo Cao

ACM International Conference on Multimedia (ACM MM), 2024 (Oral, Best Paper Candidate)

PDF