统一多模态模型的免费午餐：通过内在理解的反思校正增强生成
UniRect-CoT: Enhancing Generation in Unified Multimodal Models via Reflective Rectification with Inherent Understanding
AI总结：
本文提出UniRect-CoT框架，通过反思校正提升统一多模态模型的生成能力，利用内部知识校正中间结果，增强生成质量。
摘要：
统一多模态模型（UMMs）旨在在一个结构中整合视觉理解和生成，但存在显著的能力不匹配，即理解能力远超生成能力。为此，我们受到人类“思考时绘画”范式的启发，提出UniRect-CoT，一种无需训练的统一校正链式思维框架。我们将UMMs的扩散去噪过程视为内在视觉推理过程，对中间结果进行对齐，作为自监督信号校正生成。实验表明，UniRect-CoT可轻松集成到现有UMMs中，显著提升多样化复杂任务的生成质量。
英文摘要：
Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capability mismatch, where their understanding capability often outperforms their generation capability. This mismatch suggests that the model's rich internal knowledge, while effective for understanding tasks, is not fully utilized during generation. To address this, we draw inspiration from the human ``Thinking-While-Drawing'' paradigm, where humans continuously reflect on intermediate results and revise them according to their understanding of the intended target. In this paper, we propose UniRect-CoT, a training-free unified rectification chain-of-thought framework. We regard the multi-step denoising process in UMMs as an intrinsic visual reasoning process, whose intermediate states provide opportunities for continuous reflection and rectification. By leveraging the UMM's inherent understanding to reflect on intermediate results in light of the target instruction and rectify them accordingly, our framework forms a reflective chain of thought within a single denoising trajectory, enabling the model's internal knowledge to guide generation throughout the process. Specifically, the UMM generates a state-conditioned reflection, whose autoregressive negative log-likelihood under the same model defines a model-native differentiable semantic loss that translates textual reflection into gradients for latent rectification. Extensive experiments demonstrate that UniRect-CoT generalizes across existing flow-based UMMs, consistently enhancing overall text-to-image generation performance.
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。
