@article{docgenomeanopenlargescalescientific, title = {DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models}, author = {Renqiu Xia and Song Mao and Xiangchao Yan and Hongbin Zhou and Bo Zhang and Haoyang Peng and Jiahao Pi and Daocheng Fu and Wenjie Wu and Hancheng Ye and Shiyang Feng and Chao Xu and Conghui He and Pinlong Cai and Min Dou and Botian Shi and Sheng Zhou and Yongwei Wang and Bin Wang and Junchi Yan and Fei Wu and Yu Qiao}, year = {2024}, eprint = {2406.11633}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.11633v2}, }