@article{vigorimprovingvisualgroundingoflarge,
  title = {ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling},
  author = {Siming Yan and Min Bai and Weifeng Chen and Xiong Zhou and QiXing Huang and Li Erran Li},
  year = {2024},
  eprint = {2402.06118},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.06118v3},
}