Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement 文章

ArXiv CS.CV2026-06-03NEWSen作者: Qianhan Feng, Wenshuo Li, Tong Lin, Xinghao Chen
大语言模型
查看原文 →
关系图谱

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement · 相关人物

暂无数据