@article{cachedtransformersimprovingtransformers, title = {Cached Transformers: Improving Transformers with Differentiable Memory Cache}, author = {Zhaoyang Zhang and Wenqi Shao and Yixiao Ge and Xiaogang Wang and Jinwei Gu and Ping Luo}, year = {2023}, eprint = {2312.12742}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.12742v1}, }