1
Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning
面向3D CT的视觉语言对比学习新方法，概念级对齐提升医学基础模型性能，值得关注。
arXiv:2606.24570v1 Announce Type: new Abstract: Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation model…