@article{improvingmultimodallargelanguagemodel,
  title = {Improving Multi-modal Large Language Model through Boosting Vision Capabilities},
  author = {Yanpeng Sun and Huaxin Zhang and Qiang Chen and Xinyu Zhang and Nong Sang and Gang Zhang and Jingdong Wang and Zechao Li},
  year = {2024},
  eprint = {2410.13733},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.13733v1},
}