Repeat After Me: Transformers are Better than State Space Models at Copying.
Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
Browse the full ICML paper archive.
Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
Browse the full ICML paper archive.