1 code implementation • 11 May 2023 • Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali, Andreas Loukas, Kyunghyun Cho, Tommaso Biancalani
We investigate how to learn better flows, and propose (i) prioritized replay training of high-reward $x$, (ii) relative edge flow policy parametrization, and (iii) a novel guided trajectory balance objective, and show how it can solve a substructure credit assignment problem.
no code implementations • 21 Oct 2022 • Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia, Alex Tseng, Nathaniel Diamant, Tommaso Biancalani, Andreas Loukas
How much explicit guidance is necessary for conditional diffusion?
no code implementations • 10 Feb 2022 • Max W. Shen
We clarify the role of interpretability in trust with a ladder of model access.