Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective
- 2024-10-08
- 2
@misc{bai2024does,
title = {Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective},
author = {Xueying Bai and Yifan Sun and Niranjan Balasubramanian},
year = {2024},
eprint = {2410.05648},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2410.05648},
}