NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval 文章

ArXiv CS.CV2026-05-28NEWSen作者: Zhuchenyang Liu, Yao Zhang, Yu Xiao
查看原文 →
关系图谱

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval · 相关人物

暂无数据