JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse

@misc{li2025jarvisvlaposttraininglargescale,
      title={JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play  Visual Games with Keyboards and Mouse},
      author={Muyao Li and Zihao Wang and Kaichen He and Xiaojian Ma and Yitao Liang},
      year={2025},
      eprint={2503.16365},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.16365},
}