"Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient ..."

Muhammad N. ElNokrashy, Badr AlKhamissi, Mona T. Diab (2022)

Details and statistics

DOI: 10.48550/ARXIV.2209.15168

access: open

type: Informal or Other Publication

metadata version: 2022-10-06

a service of  Schloss Dagstuhl - Leibniz Center for Informatics