| title | Steering Visual Generation in Unified Multimodal Models with Understanding Supervision |
|---|---|
| authors | Zeyu Liu, Zanlin Ni, Yang Yue, Cheng Da, Huan Yang, Di Zhang, Kun Gai, Gao Huang |
| date | 2026-05-07 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.05781 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to explicitly restore this synergy by introducing Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations. By incorporating objectives that encode semantic abstraction (captioning) and structural details (visual regression), we enable effective gradient flow from understanding to generation. Extensive experiments on image generation and editing demonstrate that understanding can serve as an effective catalyst for generation. |
cite
@misc{liu2026steering,
title={Steering Visual Generation in Unified Multimodal Models with Understanding Supervision},
author={Zeyu Liu and Zanlin Ni and Yang Yue and Cheng Da and Huan Yang and Di Zhang and Kun Gai and Gao Huang},
year={2026},
eprint={2605.05781},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.05781}
}