I currently work at Google, mainly focusing on improving the efficiency of large-scale text-to-image diffusion models, such as Imagen 3.

Previously I was an Applied Scientist at AWS AI. At AWS, I worked on training large diffusion-based generative models, which finally turned into Titan Image Generator.

I graduated from University of Chicago with a Ph.D. degree in Computational and Applied Mathematics in 2022. I did my Ph.D. studies under Prof. Yali Amit. During two wonderful summer internships at NVIDIA, I worked with Arash Vahdat and Karsten Kreis. My research mainly focuses on deep probablistic generative models and optimization. Here is a copy of my Ph.D. thesis.

I obtained my bachelor’s degrees in Applied Mathematics and Statistics from UC Berkeley in 2017.