2 articles
University of Hong Kong and Adobe Research have unveiled Self-E, a breakthrough self-evaluation training method that delivers high-quality text-to-image generation whether you need 1 step or 100.
Adobe-affiliated researchers reveal that spatial structure, not teacher model accuracy, drives faster generative AI training. A minimal update called iREPA delivers quicker convergence and stronger results across models.
We use cookies to improve your experience on our site and to show you relevant advertising. To find our more, read our privacy policy and cookie policy
Eseandre Mordi
Alex Dudov
