Kang-Fu Mei 撅康倫

Research Scientist @ Google Research

Email / Google Scholar / Twitter / Service / Misc.

About Me

I am a Research Scientist at Google Research.

My research lies at the intersection of Multimodal Generative AI and World Model. I am interested in building AI systems that can simulate our dynamic world for creative control, leveraging these capabilities to enable more robust autonomous systems or advance entertainment applications.

At Google, I work on scalable text-to-image pretraining. I am a key contributor to Google's first launched fully on-device diffusion model, and my research has contributed to multiple Google products.

Over the past few years, I have worked on improving the controllability and sampling speed of generative models like GANs and diffusion mdoels on image and video generation.

I received my Ph.D. from ECE, Johns Hopkins University, where I worked with Prof. Vishal M. Patel I completed my M.S. at The Chinese University of Hong Kong, Shenzhen, where I was advised by Prof. Rui Huang.

Prospective collaborators: I am always looking for motivated and talented students! If you are interested in collaborating or intern, please don't hesiate to drop me a e-mail.


2023 - Present Summer 2022 2021 - 2024 Summer 2020 2019 - 2021

 

Recent News

  • NEW Jul 2025: I am serving as an Area Chair for WACV 2026. πŸ‘¨β€πŸ’»
  • NEW Feb 2025: MMSR is accepeted by CVPR25. πŸ“·
  • NEW Jan 2025: Field-DiT is accepted by ICLR25. 🧠
  • Jan 2025: I am now Dr. Mei! Thank you, Prof. Patel, for your guidance and tremendous support!

 

Research Projects

  (show selected / show by date)

 

Thesis


Efficient and Scalable Generative Model Control for High-Quality Multimodal Synthesis
Kangfu Mei
Ph.D. Thesis

Service

Misc.


Template