@misc{qin2025cockatielensemblingsynthetichuman,
      title={Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption}, 
      author={Luozheng Qin and Zhiyu Tan and Mengping Yang and Xiaomeng Yang and Hao Li},
      year={2025},
      eprint={2503.09279},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.09279}, 
}