@article{vecattentionvectorwisesparseattentionfor,
  title = {VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference},
  author = {Anmin Liu and Ruixuan Yang and Huiqiang Jiang and Bin Lin and Minmin Sun and Yong Li and Chen Zhang and Tao Xie},
  year = {2026},
  eprint = {2603.29494},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.29494},
}