1
Enhancing Part-Level Point Grounding for Any Open-Source MLLMs
提出无需额外训练即可增强任意开源多模态大模型对物体部件级点指向理解能力的新方法
arXiv:2606.29267v1 Announce Type: new Abstract: Visual grounding aims to associate free-form textual queries with specific regions in an image. While …