How can embedding models bind concepts? 事件

How can embedding models bind concepts? arXiv:2605.31503v1 Announce Type: new Abstract: Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual concepts but fail to represent which concepts form which objects. Although CLIP behaves like a bag-of-concepts model in cross-modal retrieval, object information is recoverable from its image and