@misc{cho2024docrag, title={M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding}, author={Jaemin Cho and Debanjan Mahata and Ozan Irsoy and Yujie He and Mohit Bansal}, year={2024}, eprint={2411.04952}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2411.04952} }