@article{udmgrpostableandefficientgrouprelativepo,
  title = {UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models},
  author = {Jiaqi Wang and Haoge Deng and Ting Pan and Yang Liu and Chengyuan Wang and Fan Zhang and Yonggang Qi and Xinlong Wang},
  year = {2026},
  eprint = {2604.18518},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.18518},
}