@article{revapostabilizingreinforcementlearningfo,
  title = {REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation},
  author = {Li Guo and Anas M. Tahir and Z. Jane Wang},
  year = {2026},
  eprint = {2607.10147},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.10147},
}