Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| 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 |