"ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens."

Yangyang Guo et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2309.16738

access: open

type: Informal or Other Publication

metadata version: 2023-10-18

a service of  Schloss Dagstuhl - Leibniz Center for Informatics