No Priors · Friday, September 18, 2026
Stefano Ermon explained that diffusion models originated from score-based generative models, a concept he and his PhD student Young Song developed in 2019. The core idea was to train a neural network to denoise images, which could then be used to generate new images by starting from noise and gradually refining it.
“And so we started working on score-based generative models, which are basically what eventually became diffusion models. Back in 2019 with, uh, with my PhD student Young Song, and so we kind of like came up with this idea of, let's train a neural network to denoise images. And if you can denoise an image, then you really understand enough about the structure of the image that it should be possible to build like a generative procedure based on this denoiser.”
“And that basically became the, the kind of like underlying technology of modern diffusion models, where instead of generating images, you know, left to right one pixel at a time, you kind of like start from pure noise and then you gradually refine the object until you get like a clean picture at the end.”