@misc{song2023bridge, title={How to Bridge the Gap between Modalities: A Comprehensive Survey on Multimodal Large Language Model}, author={Shezheng Song and Xiaopeng Li and Shasha Li}, year={2023}, eprint={2311.07594}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2311.07594} }