Surya Ganguli's work on diffusion models powers modern AI tools like DALL-E

Image-generating tools like DALL-E are powered by diffusion models, which generate a unique image from a text description starting from static noise. The first diffusion model was invented at Stanford in 2015 by Jascha Sohl-Dickstein, now a research scientist in the Brain group at Google. Seven years ago, when Sohl-Dickstein was a postdoc in the Neural Dynamics and Computation Lab, he and the lab’s director, neuroscientist Surya Ganguli, PhD, “were exploring ideas in non-equilibrium thermodynamics,” says Ganguli. “That work lead to the idea that one could reverse the flow of time in a diffusion process that turns data into noise by training a neural network, which could then turn noise into data,” Ganguli says.