I have written an article on the concept of normalizing flows. It's the first in a series, that aims to build up intuition about conditional flow matching (which is the basis of many SoTA generative models, e.g. Google's Veo 2, Meta's Movie Gen, BFL's FLUX, etc).
I'm trying to improve my technical writing skills, so would be very happy with all feedback!
I have written an article on the concept of normalizing flows. It's the first in a series, that aims to build up intuition about conditional flow matching (which is the basis of many SoTA generative models, e.g. Google's Veo 2, Meta's Movie Gen, BFL's FLUX, etc).
I'm trying to improve my technical writing skills, so would be very happy with all feedback!