Kwang Moo Yi @kmyid.bsky.social · 06/10/2026Dahary and Sella et al., "Learning to Read the Contextual Tokens in Diffusion Transformers" Turns out you can already read out a LOT about the image that is being generated even before it becomes barely interpretable. 110
Kwang Moo Yi @kmyid.bsky.social · 06/10/2026omer11a.github.io/learning_to_...omer11a.github.ioLearning to Read the Contextual Tokens in Diffusion TransformersReading the visual semantics that emerge inside multimodal diffusion transformers, then strengthening them to improve generation. 000
