@article{cfretdvqacoarsetofineretrievaland, title = {Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning}, author = {Jinxu Zhang}, year = {2024}, eprint = {2403.00816}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.00816v3}, }