HouseMind: Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans
发表于:CVPR 2026, 2026
一种多模态大语言模型,通过离散房间实例token统一建筑平面图的理解、生成和编辑,实现可控且可解释的操作。
推荐引用格式: QIN S Z, WEBER R E, LU X Z. Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans[C/OL]. CVPR, 2026. https://arxiv.org/abs/2603.11640.
论文链接 | Project Page












