@article{feng2023docpedia, title={DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding}, author={Feng, Hao and Liu, Qi and Liu, Hao and Zhou, Wengang and Li, Houqiang and Huang, Can}, journal={arXiv preprint arXiv:2311.11810}, year={2023} }