Zhiwu Huang![]() I specialize in computer vision and machine learning for artificial general intelligence. My current research focuses on generative AI (GenAI) functions of generation, detection, emotion, and action in computers, devices, and robots, with the potential for broad impact in healthcare, art, and education. My research team has been exploring computer vision and machine learning approaches like diffusion generative modeling, geometric deep learning, and continual deep learning. Ultimately, we aim to make machines more capable and controllable, enabling them to better understand both the physical world and human beings. Workshops:"AIM 2020: Advances in Image Manipulation Workshop and Challenges on Image and Video manipulation" , In conjunction with ECCV 2020 "NTIRE 2020: New Trends in Image Restoration and Enhancement workshop" , In conjunction with CVPR 2020 "AIM 2019: Advances in Image Manipulation Workshop and Challenges on Image and Video manipulation" , In conjunction with ICCV 2019 "NTIRE 2019: New Trends in Image Restoration and Enhancement workshop" , In conjunction with CVPR 2019 |