Author name: Hanbo Cheng, Limin Lin, Ruo Zhang, Yicheng Pan, Jun Du

arXiv:2605.14876v2 Announce Type: replace-cross
Abstract: Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from…

arXiv:2605.14876v1 Announce Type: cross
Abstract: Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from paramet…