Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models

TL;DR

This paper introduces a novel intrinsic reward mechanism and self-supervised reinforcement learning framework to enhance the generative capabilities of unified multimodal models by leveraging their understanding abilities.

Contribution

It proposes a token-level understanding-driven intrinsic reward (GvU) and a self-supervised RL framework to improve UMMs' generation quality without external supervision.

Findings

Significant improvement in UMMs' image generation quality.

Enhanced fine-grained visual understanding in UMMs.

Narrowing the capability gap between understanding and generation.

Abstract

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a persistent capability gap exists: UMMs typically exhibit superior visual understanding but comparatively weaker generative capabilities. This discrepancy arises largely from the intrinsic decoupling between the understanding and generation processes. While a UMM can accurately interpret fine-grained visual details, it often struggles to produce semantically coherent images from complex textual prompts. To address this challenge, we explore UMMs' internal understanding capability to enhance generation quality. We propose a token-level intrinsic text-image alignment reward mechanism, GvU, enabling the UMM to act simultaneously as teacher and student: it evaluates its own outputs using the understanding branch to guide the generations accordingly. Building upon this, we design a self-supervised reinforcement learning framework, allowing UMMs to iteratively improve their generation quality through understanding-based intrinsic reward signals--without reliance on external supervision. Experimental results show that our method substantially boosts UMMs' generation, which in turn strengthens their fine-grained visual understanding, narrowing the capability gap between UMMs' visual understanding and generation.