Zhengyang Liang (梁正扬)

I am a PhD student at the University of Toronto and affiliated with the Vector Institute, supervised by Prof. Shuang Li and Prof. Florian Shkurti. I obtained my B.Eng degree in the Software Engineering Department at Tongji University.

My research focuses on image and video generative models. I am particularly interested in post-training methods that extend and enhance the capabilities of pre-trained generative models.

Email  /  Github  /  Google Scholar  /  Twitter

Education

University of Toronto
PhD in Computer Science  ·  Vector Institute
Supervised by Prof. Shuang Li and Prof. Florian Shkurti. Research focus: Visual Generative Models.
Tongji University
B.Eng in Software Engineering

Industry Experience

Research Intern  ·  [Shanghai AI Lab]
[IDC Lab]
Supervised by Dr. Ceyuan Yang and Prof. Bo Dai. We worked on Video Generative Models. [Animatediff, Scaling Laws]

Publications

scaling_law
Scaling Laws for Diffusion Transformers
Zhengyang Liang, Hao He, Ceyuan Yang, Bo Dai
ICLR 2026
animatediff
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
ICLR 2024 (Spotlight)
swingnn
SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation
Qi Yan, Zhengyang Liang, Yang Song, Renjie Liao, Lele Wang
TMLR 2024

The website template is borrowed from John Barron.