Research Scientist, Adobe Research, San Francisco, USA
Scaling Up Generative Models For Image Synthesis
The quality of AI-generated images has drastically improved in recent years. The advancement was mainly driven by the success of training large capacity models on large scale Internet datasets. The phenomenon begs the question, is scaling up everything? Can any model be scaled up equally? In this talk, I will provide an overview of popular image generative models and discuss their strengths and challenges.
Taesung is a Research Scientist at Adobe Research, focusing on image editing using generative models. He is a core contributor to Adobe Firefly, a text-to-image generative model that is faster in generating high-resolution images and trained on ethically sourced data. He received Ph.D. in Computer Science at UC Berkeley, advised by Prof. Alexei Efros. Previously he interned at Adobe in 2019, working with Richard Zhang, and at NVIDIA, working with Ming-Yu Liu in summer 2018. He received B.S. in Mathematics and M.S. in Computer Science, both at Stanford University.