S-GRPO: Unified Post-Training for Large Vision-Language Models

@misc{yan2026sgrpo,
  title = {S-GRPO: Unified Post-Training for Large Vision-Language Models},
  author = {Yu-Ming Yan and Kai Tang and Sihong Chen and Ke Xu and Dan Hu and Qun Yu and Pengfei Hu},
  year = {2026},
  eprint = {2604.16557},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.16557},
}