LoLA: Low-Rank Linear Attention With Sparse Caching

@article{mcdermott2025lola,
  title = {LoLA: Low-Rank Linear Attention With Sparse Caching},
  author = {Luke McDermott and Robert W. Heath and Rahul Parhi},
  year = {2025},
  journal = {Trans. Mach. Learn. Res.},
  eprint = {2505.23666},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.23666},
}