@article{msamemorysparseattentionforefficientendt,
  title = {MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens},
  author = {Yu Chen and Runkai Chen and Sheng Yi and Xinda Zhao and Xiaohong Li and Jianjin Zhang and Jun Sun and Chuanrui Hu and Yunyun Han and Lidong Bing and Yafeng Deng and Tianqiao Chen},
  year = {2026},
  eprint = {2603.23516},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.23516},
}