Machine Learning at the Flatiron Institute Seminar: Michael Albergo

Date & Time


Location

160 Fifth Avenue, 4th Floor Classroom

Title: Frontiers of dynamical control of generative models

Abstract: Flow and diffusion models have become cornerstones of both scientific and industrial generative AI research. These methods work by construction of a dynamics that maps samples from a reference distribution to samples from a target distribution known empirically through data. An open question is how to best control and modify these dynamics so as to satisfy specified target sampling constraints, often specified by a reward or tilting function. I will provide an overview of the mathematics underlying this construction and discuss some of our recent efforts to make this sort of reward alignment highly scalable, both during training via fine-tuning and during inference via steering. Along the way, I will argue that the flow map — the solution operator of these dynamics — is essential to performing efficient and scalable alignment, and, time permitting, I will discuss recent efforts to bring these advances to language modeling.

Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates

privacy consent banner

Privacy preference

We use cookies to provide you with the best online experience. By clicking "Accept All," you help us understand how our site is used and enhance its performance. You can change your choice at any time here. To learn more, please visit our Privacy Policy.