@misc{xu2024llava,
  title={LLaVA-o1: Let Vision Language Models Reason Step-by-Step},
  author={Guowei Xu and Peng Jin and Li Hao and Yibing Song and Lichao Sun and Li Yuan},
  year={2024},
  eprint={2411.10440},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2411.10440}
}