"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and ..."

Yuandong Tian et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2310.00535

access: open

type: Informal or Other Publication

metadata version: 2023-12-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics