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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhuchenyang, Zhang, Yao, Xiao, Yu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!