Attention with Markov: A Curious Case of Single-layer Transformers.
Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
Browse the full ICLR paper archive.
Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
Browse the full ICLR paper archive.