Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

TL;DR

This paper introduces UNO, a post-training framework that enhances multimodal models by explicitly linking understanding and generation, leading to improved image generation and editing.

Contribution

The paper presents a novel understanding-oriented post-training method that directly uses understanding as supervision to improve generative capabilities in multimodal models.

Findings

Understanding improves image generation quality.

UNO enhances image editing performance.

Explicit understanding supervision boosts model synergy.

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.