Zhengze Yu
B.E. in Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)
✨Welcome to my page!
I work on Video Generation, with a focus on Video Editing and Vision-Language Alignment for controllable video transformation.
I have been fortunate to complete a research internship at the Institute of Automation, Chinese Academy of Sciences (CASIA), where I explore multimodal generation and video understanding. My recent research involve attention-injection-based video editing and cross-modal alignment frameworks.
I am very grateful to be advised by 🎓Prof. Changsheng Xu and 🎓Prof. Junyu Gao, whose guidance has greatly shaped my research in video generation and alignment methods.
For more details, please check the Research and Projects on my website.
