@misc{zhai2023stabilizing, title={Stabilizing Transformer Training by Preventing Attention Entropy Collapse}, author={Shuangfei Zhai and Tatiana Likhomanenko and Etai Littwin and Dan Busbridge and Jason Ramapuram and Yizhe Zhang and Jiatao Gu and Josh Susskind}, year={2023}, eprint={2303.06296}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2303.06296} }