Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

@misc{zhangTue Apr 02 2024 12:47:49 GMT+0000 (Coordinated Universal Time)directpreferenceoptimization,
      title={Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward},
      author={Ruohong Zhang and Liangke Gui and Zhiqing Sun and Yihao Feng and Keyang Xu and Yuanhan Zhang and Di Fu and Chunyuan Li and Alexander Hauptmann and Yonatan Bisk and Yiming Yang},
      year={Tue Apr 02 2024 12:47:49 GMT+0000 (Coordinated Universal Time)},
      eprint={2404.01258},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2404.01258},
}