Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

@inproceedings{luo2024monointernvl,
  title = {Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training},
  author = {G. Luo and Xue Yang and Wenhan Dou and Zhaokai Wang and Jifeng Dai and Yu Qiao and Xizhou Zhu},
  year = {2024},
  booktitle = {Computer Vision and Pattern Recognition},
  eprint = {2410.08202},
  archivePrefix = {arXiv},
  doi = {10.1109/CVPR52734.2025.02324},
  url = {https://arxiv.org/abs/2410.08202},
}