@inproceedings{shen-etal-2023-scaling, title = "Scaling Vision-Language Models with Sparse Mixture of Experts", author = "Shen, Sheng and Yao, Zhewei and Li, Chunyuan and Darrell, Trevor and Keutzer, Kurt and He, Yuxiong", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.findings-emnlp.758/", doi = "10.18653/v1/2023.findings-emnlp.758", pages = "11329--11344" }