通过理解监督引导统一多模态模型的视觉生成
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
AI总结：
本文提出UNO框架，通过将理解作为监督信号引导生成，提升多模态模型在图像生成与编辑中的性能。
摘要：
统一多模态模型旨在弥合理解和生成之间的差距。然而，为达到竞争力，最新模型采用解耦的理解和生成组件。这种设计虽然对单个任务有效，但削弱了相互增强所需的连接，使潜在协同效应经验上不确定。我们提出通过引入Understanding-Oriented Post-Training (UNO)，一个轻量级框架，将理解不仅视为一个独立任务，也作为直接的监督信号来引导生成表示。通过结合编码语义抽象（描述生成）和结构细节（视觉回归）的目标，我们实现了从理解到生成的有效梯度流动。在图像生成和编辑上的大量实验表明，理解可以作为生成的有效催化剂。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
