@article{yin2024survey,
  title={A survey on multimodal large language models},
  author={Yin, Shukang and Fu, Chaoyou and Zhao, Sirui and Li, Ke and Sun, Xing and Xu, Tong and Chen, Enhong},
  journal={National Science Review},
  pages={nwae403},
  year={2024},
  publisher={Oxford University Press}
}

@article{yin2024t2vid,
  title={T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs},
  author={Yin, Shukang and Fu, Chaoyou and Zhao, Sirui and Shen, Yunhang and Ge, Chunjiang and Yang, Yan and Long, Zuwei and Dai, Yuhan and Xu, Tong and Sun, Xing and others},
  journal={arXiv preprint arXiv:2411.19951},
  year={2024}
}