Ming-Yu Liu is a Distinguished Research Scientist and a Manager with NVIDIA Research, Santa Clara, CA, USA. He was a Principal Research Scientist with Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA. His goal is to enable machines human-like imagination capability. His research interest is in generative image modeling.

Ming-Yu Liu received the Ph.D. degree from the University of Maryland, College Park, MD, USA, in 2012, advised by Prof. Rama Chellappa.

Dr. Liu won the R&D 100 Award for his contribution to a commercial robotic bin picking system. His layered streetview semantic labeling paper was in the best paper finalists in RSS in 2015. He won the first place in both the Domain Adaptation for Semantic Segmentation Competition and the Robust Optical Flow Estimation Challenge in CVPR in 2018. His SPADE paper was in the best paper finalists in CVPR in 2019. In SIGGRAPH Real-Time Live 2019, he won both the Best in Show Award and the Audience Choice Award for his GauGAN demo. His GauGAN App further won the Best of What’s New Award by the Popular Science Magazine in 2019. In 2021, his GAN for video compression work helps NVIDIA win the most disruptive innovator award by Forbes. He has served as the Area Chair for various computer vision and machine learning conferences, including NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, BMVC, and WACV. He has served as the Program Chair of WACV in 2020.