@misc{zhao2024omchat,
  title={OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding},
  author={Tiancheng Zhao and Qianqian Zhang and Kyusong Lee and Peng Liu and Lu Zhang and Chunxin Fang and Jiajia Liao and Kelei Jiang and Yibo Ma and Ruochen Xu},
  year={2024},
  eprint={2407.04923},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2407.04923}
}