"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning."

Brandon Huang et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2406.15334

access: open

type: Informal or Other Publication

metadata version: 2024-07-16

a service of  Schloss Dagstuhl - Leibniz Center for Informatics