@misc{zhang2023meta, title={Meta-Transformer: A Unified Framework for Multimodal Learning}, author={Yiyuan Zhang and Kaixiong Gong and Kaipeng Zhang and Hongsheng Li and Yu Qiao and Wanli Ouyang and Xiangyu Yue}, year={2023}, eprint={2307.10802}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2307.10802} }