@article{efficientlongdecodinginferencewith,
  title = {Efficient Long-Decoding Inference with Reasoning-Aware Attention Sparsity},
  author = {Junhao Hu and Wenrui Huang and Weidong Wang and Zhenwen Li and Tiancheng Hu and Zhixia Liu and Xusheng Chen and Tao Xie and Yizhou Shan},
  year = {2025},
  eprint = {2502.11147},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.11147v1},
}