EM Distillation (EMD) proposes a maximum likelihood-based approach to distill diffusion models into efficient one-step generators, outperforming existing methods in FID scores on ImageNet datasets.

https://arxiv.org/abs//2405.16852

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers