@article{advancinglargemultimodalmodelswith,
  title = {Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation},
  author = {Kohei Uehara and Nabarun Goswami and Hanqin Wang and Toshiaki Baba and Kohtaro Tanaka and Tomohiro Hashimoto and Kai Wang and Rei Ito and Takagi Naoya and Ryo Umagami and Yingyi Wen and Tanachai Anakewat and Tatsuya Harada},
  year = {2024},
  eprint = {2401.10005},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.10005v2},
}