@article{vlrmvisionlanguagemodelsactasreward,
  title = {VLRM: Vision-Language Models act as Reward Models for Image Captioning},
  author = {Maksim Dzabraev and Alexander Kunitsyn and Andrei Ivaniuta},
  year = {2024},
  eprint = {2404.01911},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.01911v1},
}