视觉认知引导链：面向文本到图像生成的分阶段强化学习

摘要

尽管近期自回归模型在文本到图像（T2I）生成领域取得了显著进展，但其处理多属性和模糊提示的能力仍显不足。为应对这些局限，现有研究已采用思维链（CoT）实现阶段感知的视觉合成，并运用强化学习（RL）以增强推理能力。然而，多数模型仅在生成阶段结束时提供奖励信号。这种单一、仅最终阶段的指导方式难以识别哪些阶段对最终结果有积极贡献，可能导致策略次优。为解决此问题，我们提出了一种视觉指导链（Visual-CoG）范式，包含语义推理、过程优化和结果评估三个阶段，通过阶段感知的奖励在整个图像生成流程中提供即时指导。此外，我们构建了一个视觉认知基准测试VisCog-Bench，包含四个子任务，用于评估语义推理的有效性。在GenEval、T2I-CompBench及所提出的VisCog-Bench上的全面评估显示，改进幅度分别达到15%、5%和19%，充分证明了Visual-CoG的卓越性能。我们将尽快发布所有相关资源。

English

Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied chain-of-thought (CoT) to enable stage-aware visual synthesis and employed reinforcement learning (RL) to improve reasoning capabilities. However, most models provide reward signals only at the end of the generation stage. This monolithic final-only guidance makes it difficult to identify which stages contribute positively to the final outcome and may lead to suboptimal policies. To tackle this issue, we propose a Visual-Chain of Guidance (Visual-CoG) paradigm consisting of three stages: semantic reasoning, process refining, and outcome evaluation, with stage-aware rewards providing immediate guidance throughout the image generation pipeline. We further construct a visual cognition benchmark, VisCog-Bench, which comprises four subtasks to evaluate the effectiveness of semantic reasoning. Comprehensive evaluations on GenEval, T2I-CompBench, and the proposed VisCog-Bench show improvements of 15%, 5%, and 19%, respectively, demonstrating the superior performance of the proposed Visual-CoG. We will release all the resources soon.

视觉认知引导链：面向文本到图像生成的分阶段强化学习

Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

摘要

Support