I work on principled modeling of inductive bias in machine learning. My research seeks to understand how inductive bias determines generalization, and to develop "light-yet-sweet" generalizable models: (i) light: conceptually simple in methodology and easy to implement in practice, (ii) sweet: having clear intuitions and non-trivial theoretical guarantees.

Over the years, I always find myself fascinated by geometric invariance, symmetry, structures (graph, causality) and how they can benefit generalization as a guiding principle. More recently, I become very passionate about foundation models (how to simulate human-level intelligence) and 3D/4D generative modeling (how to recreate and simulate the physical world).

I always believe in two principles in my research: (i) insight must precede application, and (ii) everything should be made as simple as possible, but not simpler. I try to follow certain research values.