This panel brings together the world’s leading experts in computer vision to discuss “Diffusion Models for
Image and Video Tasks”. Speakers are leaders from the various visual intelligence fields, ranging from
generative AI: image/video generation, compositional generation, generation for compression, generation
for autonomous driving, generation for security, and more. As we all know, diffusion models have
emerged as a powerful tool in the field of machine learning, particularly for generating high-quality images
and videos. This panel discussion brings together experts from academia and industry to explore the
cutting-edge applications and future directions of diffusion models, including but not limited to, Recent
breakthroughs in diffusion models, Challenges and opportunities in image and video generation,
Applications in creative industries, healthcare, and entertainment, and Ethical considerations and
responsible use of AI.

Speakers:

Chong Luo
Principal Researcher, Intelligent Multimedia Group (IMG)
Microsoft Research Asia, Microsoft Corporation, China
https://www.microsoft.com/en-us/research/people/cluo
https://scholar.google.com/citations?user=01iBf38AAAAJ&hl=en

Dongdong Chen
Principal Research Manager, Microsoft GenAI
Microsoft GenAI, Redmond, Washington, US
https://scholar.google.com/citations?hl=zh-CN&user=sYKpKqEAAAAJ

Xihui Liu
Assistant Professor, Department of Electrical and Electronic Engineering and Institute of Data Science (IDS)
University of Hong Kong, China
https://xh-liu.github.io

Shuai Yang
Assistant Professor, Wangxuan Institute of Computer Technology
Peking University, China
https://williamyang1991.github.io

Li Yuan
Tenure-track Assistant Professor, School of Electrical and Computer Engineering, Shenzhen Graduate School
Peking University, China
https://yuanli2333.github.io

Guo Lu
Assistant Professor, Media Lab of SJTU, Department of Electronic Engineering
Shanghai Jiao Tong University, China
https://guolusjtu.github.io/guoluhomepage/

Jiajun Deng
Research Fellow, Research Fellow
University of Adelaide (UoA), Australia
https://djiajunustc.github.io

Moderator:

Xin Jin
Assistant Professor, Director of Intelligent Media and Visual Computing Lab, College of Information Science &
Technology
Eastern Institute of Technology (EIT), Ningbo, China
https://www.eitech.edu.cn/?tid=40&p=teacher

Meeting Information:

Join Zoom Meeting:
https://polyu.zoom.us/j/81420165864?pwd=5CoL89OBrVU8aSkhwcWNPywQvu2XLC.1

Meeting ID: 814 2016 5864
Passcode: 460458