FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation 事件

FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation arXiv:2604.13491v3 Announce Type: replace Abstract: With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs for self-reflection and self-refinement, their use in text-to-image generation remains largely underexplored. Meanwhile, existing multimoda