Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning 事件

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning arXiv:2605.25799v1 Announce Type: new Abstract: Vision-language models (VLMs) like CLIP have shown impressive generalization capabilities, yet their potential for Cross-Domain Few-Shot Learning (CDFSL) remains underexplored, where the model needs to transfer source-domain information to target domains with scarce training data. While the attention sink phenomenon has been observed in VLMs for certain tasks, its