GoT-R1：通过强化学习提升MLLM的视觉生成推理能力
GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
AI总结：
GoT-R1通过强化学习提升视觉生成中的语义-空间推理能力，改进了复杂提示下的图像生成效果，实验表明在T2I-CompBench基准上表现优异。
摘要：
视觉生成模型在从文本提示生成逼真图像方面取得了显著进展，但在处理复杂提示时存在困难，尤其是涉及多个对象和精确空间关系的提示。本文提出GoT-R1框架，通过强化学习增强视觉生成的语义-空间推理能力。基于生成链式思维方法，GoT-R1使模型能够自主发现有效的推理策略。我们提出双阶段多维奖励框架，利用大规模语言模型评估推理过程和最终输出，实现整个生成流程的有效监督。奖励系统统一评估语义对齐、空间准确性和视觉质量。实验结果表明，在T2I-CompBench基准上，特别是在涉及精确空间关系和属性绑定的组合任务中，性能显著提升。GoT-R1通过将复杂的推理能力转移到视觉生成领域，推动了图像生成技术的发展。为促进未来研究，我们公开了代码和预训练模型，地址为https://github.com/gogoduan/GoT-R1。
英文摘要：
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.
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。
