Abstract
線上會議連結：https://asmeet.webex.com/asmeet/j.php?MTID=mb86d1c0aa859994ec425a6107ebe2a22
會議號： 2518 946 7575
密碼： viNXmy9mT73
Text-to-image and text-to-video generation have seen remarkable advancements. Yet, the current scope of textual control often falls short in various contexts. In our presentation, we explore enhancements to these models, unlocking new functionalities and broadening their practical applications.
會議號： 2518 946 7575
密碼： viNXmy9mT73
Text-to-image and text-to-video generation have seen remarkable advancements. Yet, the current scope of textual control often falls short in various contexts. In our presentation, we explore enhancements to these models, unlocking new functionalities and broadening their practical applications.
Bio
Dr. Yu-Chuan Su is a research scientist at Google. He works on both fundamental and applied research in computer vision, particularly focusing on content generation and intelligent photography. Before joining Google, he received his Ph.D. from the University of Texas at Austin in 2019 and M.S. from National Taiwan University in 2014.