GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914465345175552 |
|---|---|
| author | Duan, Chengqi Fang, Rongyao Wang, Yuqing Wang, Kun Huang, Linjiang Zeng, Xingyu Li, Hongsheng Liu, Xihui |
| author_facet | Duan, Chengqi Fang, Rongyao Wang, Yuqing Wang, Kun Huang, Linjiang Zeng, Xingyu Li, Hongsheng Liu, Xihui |
| contents | Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of such prompts requires explicit reasoning about the semantic content and spatial layout. We present GoT-R1, a framework that applies reinforcement learning to enhance semantic-spatial reasoning in visual generation. Building upon the Generation Chain-of-Thought approach, GoT-R1 enables models to autonomously discover effective reasoning strategies beyond predefined templates through carefully designed reinforcement learning. To achieve this, we propose a dual-stage multi-dimensional reward framework that leverages MLLMs to evaluate both the reasoning process and final output, enabling effective supervision across the entire generation pipeline. The reward system assesses semantic alignment, spatial accuracy, and visual quality in a unified approach. Experimental results demonstrate significant improvements on T2I-CompBench benchmark, particularly in compositional tasks involving precise spatial relationships and attribute binding. GoT-R1 advances the state-of-the-art in image generation by successfully transferring sophisticated reasoning capabilities to the visual generation domain. To facilitate future research, we make our code and pretrained models publicly available at https://github.com/gogoduan/GoT-R1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17022 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning Duan, Chengqi Fang, Rongyao Wang, Yuqing Wang, Kun Huang, Linjiang Zeng, Xingyu Li, Hongsheng Liu, Xihui Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Multimedia Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of such prompts requires explicit reasoning about the semantic content and spatial layout. We present GoT-R1, a framework that applies reinforcement learning to enhance semantic-spatial reasoning in visual generation. Building upon the Generation Chain-of-Thought approach, GoT-R1 enables models to autonomously discover effective reasoning strategies beyond predefined templates through carefully designed reinforcement learning. To achieve this, we propose a dual-stage multi-dimensional reward framework that leverages MLLMs to evaluate both the reasoning process and final output, enabling effective supervision across the entire generation pipeline. The reward system assesses semantic alignment, spatial accuracy, and visual quality in a unified approach. Experimental results demonstrate significant improvements on T2I-CompBench benchmark, particularly in compositional tasks involving precise spatial relationships and attribute binding. GoT-R1 advances the state-of-the-art in image generation by successfully transferring sophisticated reasoning capabilities to the visual generation domain. To facilitate future research, we make our code and pretrained models publicly available at https://github.com/gogoduan/GoT-R1. |
| title | GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Multimedia |
| url | https://arxiv.org/abs/2505.17022 |