Michael Albergo

Michael Albergo is a Junior Fellow at the Harvard Society of Fellows. Starting in 2026, he will be an Assistant Professor of Applied Mathematics and Kempner Institute Investigator at the university. His research focuses on the methodological development of highly scalable generative models, emphasizing their construction for—and drawing mathematical inspiration from—the natural phenomena of the world we inhabit. He then uses these tools to push forward fundamental discoveries in the natural sciences. He completed his PhD at New York University in 2024. 

AI2050 Project

Generative modeling is the backbone of the large scale machine learning tools that are a growingly central part of our lives. Albergo’s project studies the mathematics of a class of generative modeling techniques, known as flow and diffusion models, that work by building maps between probability distributions. In particular, it investigates how to make these techniques more efficient, general, and controllable, and seeks to devise methods of using them for generative control of dynamical, living matter. They will then use their developments to construct a generative model of cellular development.