"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual ..."

Wenbo Hu et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2308.09936

access: open

type: Informal or Other Publication

metadata version: 2023-08-28

a service of  Schloss Dagstuhl - Leibniz Center for Informatics