@article{gvpogroupvariancepolicyoptimizationfor,
  title = {GVPO: Group Variance Policy Optimization for Large Language Model Post-Training},
  author = {Kaichen Zhang and Yuzhong Hong and Junwei Bao and Hongfei Jiang and Yang song and Dingqian Hong and Hui Xiong},
  year = {2025},
  eprint = {2504.19599},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.19599v2},
}