"COLA: How to adapt vision-language models to Compose Objects Localized ..."

Arijit Ray et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2305.03689

access: open

type: Informal or Other Publication

metadata version: 2023-05-10

a service of  Schloss Dagstuhl - Leibniz Center for Informatics