Abstract: Unified multimodal models aim to support visual understanding and generation within a single framework. However, prevailing approaches often separate their visual representations or backbone computation to accommodate the different requirements of these two tasks, which limits the degree of unification. In this paper, we present HiUni, which
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
HiUni: Harmonizing Understanding and Generation in Shared Visual Space
