Self-Corrected Image Generation with Explainable Latent Rewards

TL;DR

This paper introduces xLARD, a self-correcting image generation framework that leverages explainable latent rewards and multimodal language models to improve alignment and fidelity in text-to-image synthesis.

Contribution

It proposes a novel self-correcting method using explainable latent rewards and a lightweight corrector to enhance image generation quality.

Findings

Improves semantic alignment in generated images

Enhances visual fidelity while preserving generative priors

Demonstrates effectiveness across diverse tasks

Abstract

Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of generation, which requires anticipating alignment without fully understanding the output. In contrast, evaluating generated images is more tractable. Motivated by this asymmetry, we propose xLARD, a self-correcting framework that uses multimodal large language models to guide generation through Explainable LAtent RewarDs. xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references. A key component is a differentiable mapping from latent edits to interpretable reward signals, enabling continuous latent-level guidance from non-differentiable image-level evaluations. This mechanism allows the model to understand, assess, and correct itself during generation. Experiments across diverse generation and editing tasks show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors. Code is available at https://yinyiluo.github.io/xLARD/.