"Visual Anchors Are Strong Information Aggregators For Multimodal Large ..."

Haogeng Liu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.17815

access: open

type: Informal or Other Publication

metadata version: 2024-06-21

a service of  Schloss Dagstuhl - Leibniz Center for Informatics