SODA is a self-supervised diffusion model that uses an image encoder to generate novel views. It achieves strong representation learning and disentangled latent space, making it promising for image generation and robust representations.

https://arxiv.org/abs//2311.17901

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