@misc{bulatov2023scaling, title={Scaling Transformer to 1M tokens and beyond with RMT}, author={Aydar Bulatov and Yuri Kuratov and Mikhail S. Burtsev}, year={2023}, eprint={2304.11062}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2304.11062} }