AI-SOVEREIGN
Home / AI Research / HiUni: Harmonizing Understanding and Generation in Shared Visual Space
HIAI Research

HiUni: Harmonizing Understanding and Generation in Shared Visual Space

by ernie-research · Jiahao Hu, Jingdong Du, Yichen Zhang, Yi Song, Zhenyu Zhang, Jiaxin Niu

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 revisits this design choice and explores whether a pretrained vision language model can be directly extended into a unified model with extensive parameter sharing. Specifically, HiUni reuses the same language-aligned ViT and dense Transformer backbone for both capabilities, while confining task-specific computation to the output side. Yet such a design…

Upvotes25
Comments2
Published18 Nov 2026