Ming-Yu Liu

Ming-Yu Liu is a vice president of research at NVIDIA and an IEEE fellow. He leads the deep imagination research group at NVIDIA, which focuses on deep generative models for physical AI. His research team has brought up several generative AI services, including NVIDIA Edify, which powers generative AI offerings by Getty Images and Shutterstock; NVIDIA Canvas (GauGAN); and NVIDIA Maxine (LivePortrait). His research group regularly publishes scientific papers in top-tier AI conferences, including NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, and SIGGRAPH. Several of their papers have received prestigious awards.

Comment Cosmos 3 aide l’IA physique à réfléchir avant d’agir

Le monde réel est toujours en mouvement. Pour fonctionner de manière autonome, les systèmes d’IA physique, notamment les robots, les véhicules autonomes et les espaces intelligents, doivent comprendre non seulement… Lire l’article