@article{rlhfuseefficientrlhftrainingforlarge,
  title = {Optimizing RLHF Training for Large Language Models with Stage Fusion},
  author = {Yinmin Zhong and Zili Zhang and Bingyang Wu and Shengyu Liu and Yukun Chen and Changyi Wan and Hanpeng Hu and Lei Xia and Ranchen Ming and Yibo Zhu and Xin Jin},
  year = {2024},
  eprint = {2409.13221},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.13221v3},
}