"Improving Transformers with Dynamically Composable Multi-Head Attention."

Da Xiao et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.08553

access: open

type: Informal or Other Publication

metadata version: 2024-06-15

a service of  Schloss Dagstuhl - Leibniz Center for Informatics