@article{mixtureoftransformersasparseandscalable, title = {Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models}, author = {Weixin Liang and Lili Yu and Liang Luo and Srinivasan Iyer and Ning Dong and Chunting Zhou and Gargi Ghosh and Mike Lewis and Wen-tau Yih and Luke Zettlemoyer and Xi Victoria Lin}, year = {2024}, eprint = {2411.04996}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.04996v2}, }