VLA-Mark: A cross modal watermark for large vision-language alignment model

v1v2 (latest)

VLA-Mark: A cross modal watermark for large vision-language alignment model

18 July 2025

ArXiv (abs)PDF HTML

Papers citing "VLA-Mark: A cross modal watermark for large vision-language alignment model"

1 / 1 papers shown

Title
DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning Yibo Yan Guangwei Xu Xin Zou Shuliang Liu James Kwok Xuming Hu 28 4 0 28 Sep 2025