Bobby He, James Martens, Guodong Zhang, Aleksandar Botev, Andrew Brock, Samuel L. Smith, Yee Whye Teh. Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [doi]
@inproceedings{HeMZBBST23,
title = {Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation},
author = {Bobby He and James Martens and Guodong Zhang and Aleksandar Botev and Andrew Brock and Samuel L. Smith and Yee Whye Teh},
year = {2023},
url = {https://openreview.net/pdf?id=NPrsUQgMjKK},
researchr = {https://researchr.org/publication/HeMZBBST23},
cites = {0},
citedby = {0},
booktitle = {The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
}