🥳 About Me

I am a first-year Ph.D student of SILab at The Chinese University of Hong Kong, Shenzhen (CUHKSZ), under the supervision of Prof. Li Jiang – homepage. I obtained my M.S. in Computer Science at the University of Chinese Academy of Sciences (UCAS) in 2024 and B.S at Shandong University (SDU) in 2021. I was also fortunate to be an internship at Tsinghua AIR , Huawei , TeleAI .

My research interests lie in the intersection of Computer Vision and Machine Learning. Now, I focus on designing novel applications for image/video generation, World model, autoregressive-generation and other downstream AIGC tasks.

I am actively looking for internship opportunities and coauthors!

📖 Educations

• 2024.10 - up-to-now, Phd, School of Data Science, The Chinese University of Hong Kong, Shenzhen.
• 2021.09 - 2024.06, M.S. degree, School of Computer Science and Technology, University of Chinese Academy of Sciences.
• 2017.09 - 2021.06, B.S. degree, School of Mechanical, Electrical & Information Engineering, Shandong University.

📝 Publications/Preprints - main contribution

*Equal contribution

SIGGRAPH Asia 2025

Proteus-ID: ID-Consistent and Motion-Enhanced Video Customization

Guiyu Zhang, Chen Shi, Zijian Jiang, Xunzhi Xiang, Jingjing Qian, Shaoshuai Shi, Li Jiang.

Paper Project Code

ICLR 2025

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

Guiyu Zhang, Huan-ang Gao, Zijian Jiang, Hao Zhao, Zhedong Zheng

Paper Project Code

ArXiv 2025

Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation

Xunzhi Xiang^*, Yabo Chen^*, Guiyu Zhang^*, Zhongyu Wang, Zhe Gao, Quanming Xiang, Gonghu Shang, Junqi Liu, Haibin Huang, Yang Gao, Chi Zhang, Qi Fan, et al.

Paper Project Code

MICCAI 2024 (Spotlight)

FairDiff: Fair Segmentation with Point-Image Diffusion

Wenyi Li^*, Haoran Xu^*, Guiyu Zhang^*, Huan-ang Gao, Mingju Gao, Mengyu Wang, Hao Zhao

Paper Code

🔥 Publications/Preprints - participating contribution

ArXiv 2026

Few-Step Video Diffusion Plans Semantics Early: Pathwise Test-Time Optimization along the Sampling Trajectory

Xunzhi Xiang, Zixuan Duan, Guiyu Zhang, Haiyu Zhang, Zhe Gao, Junta Wu, Shaofeng Zhang, Tengfei Wang, Qi Fan, Chunchao Guo.

Paper

ArXiv 2025

Denoising Vision Transformer Autoencoder with Spectral Regularization

Xunzhi Xiang, Xingye Tian, Guiyu Zhang, Yabo Chen, Shaofeng Zhang, Xuebo Wang, Xin Tao, Qi Fan.

Paper

🎖 Honors and Awards

• 2020.8 Nation College Student Intelligent Car Competition First Prize.
• 2020.8 National University Student Contest on Energy Saving & Emission Reduction Second Prize.