BIOGRAPHY
I am a Postdoctoral Researcher at MIT EECS, advised by Prof. Tess Smidt. I completed my Doctorate in Computer Science at UC San Diego with Prof. Rose Yu, and here is my thesis.
My research primarily lies in deep learning, especially for spatiotemporal data. In particular, I’m interested in building accurate, interpretable, and generalizable deep forecasting models for large-scale real-world data. My works have been applied to forecasting spatiotemporal systems in finance, epidemiology, healthcare, traffic and physical sciences.
Currently, I’m actively working on designing equivariant neural nets that preserve (approximate) symmetries as well as symmetry-breaking factor discovery problems.
For more details, please see my Resume and Google Scholar.