Poisson Flow Generative Models — mentioned by c1ccccc1

Wed, 30 Nov 2022 23:57:41 GMT

Paper link: https://arxiv.org/pdf/2209.11178.pdf Lots of interesting things I'd want to try here. Eg, the formulation of thinking of your probability distribution as a charge distribution opens up the possibility of adding negative charges. So you could have a regular positive data examples, but also some negative examples that the generative model tries extra hard to avoid. I'd also be interested to see what happens when you "add the fields" for two different distributions over the same space. Seems like it would be interestingly different than regular superposition, and I'd really like to…

Paper and discussion history. A mention is not an endorsement.

Poisson Flow Generative Models · HackerPapers discussions

Poisson Flow Generative Models — mentioned by c1ccccc1