@article{acceleratinglargescalereasoningmodelinfe,
  title = {Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding},
  author = {Yilong Zhao and Jiaming Tang and Kan Zhu and Zihao Ye and Chi-Chih Chang and Chaofan Lin and Jongseok Park and Guangxuan Xiao and Mohamed S. Abdelfattah and Mingyu Gao and Baris Kasikci and Song Han and Ion Stoica},
  year = {2025},
  eprint = {2512.01278},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.01278},
}