@article{gatedsparseattentioncombiningcomputation,
  title = {Gated Sparse Attention: Combining Computational Efficiency with Training Stability for Long-Context Language Models},
  author = {Alfred Shen and Aaron Shen},
  year = {2026},
  eprint = {2601.15305},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.15305},
}