encouraged that reviewers find our paper clear and well written (R1, R2, R3) and our method to be theoretically sound

We would like to thank the reviewers for their helpful comments and their thorough evaluation of our work. Reversible layers is a technique introduced by Gomez et al. (2017) and is orthogonal and In contrast, clustered attention places no such restriction. We will also add Set Transformers to the related work section. Is speech favorable to clustering? We would like to mention that our NLP approximation experiment for GLUE and SQuAD tasks in 4.3 shows that NLP/vision tasks in the long context setting, as suggested.