Study

1. Generative Modeling by Transport I [Notes]

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

2. Generative Modeling by Transport II

   Part II extends the transport-theoretic foundations of Part I beyond continuous Euclidean domains.