Rethinking Cross-Layer Information Routing in Diffusion Transformers

by [unverified] · free · Last verified 2026-06-21T03:07:51.288Z

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited. The residual stream that governs how information ...