Scholar
Kangfu Mei
Google Scholar ID: e_nu_TIAAAAJ
Google DeepMind
Citations & Impact
Citations
2,076
H-index
15
i10-index
17
Publications
20
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including but not limited to 'Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration', 'Reference-Guided Identity Preserving Face Restoration' in various international conferences and journals; served as an Area Chair for WACV 2026; contributed to several projects such as MMSR accepted by CVPR 2025, Field-DiT accepted by ICLR 2025.
Research Experience
- Research Scientist at Google DeepMind, working on the GenAI Veo team for video generation; has focused on improving the controllability and sampling speed of generative models like GANs and diffusion models over the past few years.
Education
- Ph.D. from ECE, Johns Hopkins University, advised by Prof. Vishal M. Patel; M.S. from The Chinese University of Hong Kong, Shenzhen, under the guidance of Prof. Rui Huang.
Background
- Research interests lie at the intersection of Multimodal Generative AI and World Model, aiming to build AI systems that can simulate our dynamic world for creative control, with applications in robust autonomous systems or entertainment.
Miscellany
- Looking for motivated and talented students for collaboration or internships.
