arXiv AI By Evelyn Turri, Davide Bucciarelli, Sara Sarto, Lorenzo Baraldi, Marcella Cornia

Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

Read the original on arXiv AI →

arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.