Study

1. Generative Modeling by Transport [Notes]

   Modern generative modeling can be understood as the problem of transporting probability measures through continuous stochastic dynamics. We study a unified mathematical framework for diffusion models, flow matching, Schrödinger bridges, and related methods through the stochastic interpolants framework.

2. Human Intelligence [Notes]

   Exploring the nature intelligence from multiple perspectives including neuroscience, psychology, sociology, philosophy, and religion.