Diffusion models for image generation were independently invented at least twice: in a discrete-time variational inference framework…
Generates images from captions by combining [ CLIP ]-style representation learning with a [ diffusion model ] model to construct images from…
A technique for [ representation ] learning in which semantically similar datapoints are encouraged to have similar representations, and…
Current (2021) deep networks require huge datasets in order to [ generalization|generalize ]. But we know that humans can do one-shot…
As of April 2021: Giant [ transformer ]s work better than anyone has a right to expect. GPT3 is fucking amazing. [ DALL-E ] clearly has some…