Saved in:
Bibliographic Details
Main Authors: Li, Yaqi, Chen, Peng, Han, Mingyang, Bu, Pi, Shi, Haoxiang, Zhao, Runzhou, Yao, Yang, Zhang, Xuan, Song, Jun, Zheng, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.18032
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911121384931328
author Li, Yaqi
Chen, Peng
Han, Mingyang
Bu, Pi
Shi, Haoxiang
Zhao, Runzhou
Yao, Yang
Zhang, Xuan
Song, Jun
Zheng, Bo
author_facet Li, Yaqi
Chen, Peng
Han, Mingyang
Bu, Pi
Shi, Haoxiang
Zhao, Runzhou
Yao, Yang
Zhang, Xuan
Song, Jun
Zheng, Bo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
Li, Yaqi
Chen, Peng
Han, Mingyang
Bu, Pi
Shi, Haoxiang
Zhao, Runzhou
Yao, Yang
Zhang, Xuan
Song, Jun
Zheng, Bo
Computer Vision and Pattern Recognition
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.
title Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.18032