Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation ModelsMixture-of-Transformers：—种用于多模态 Foundation Model 的稀疏且可扩展架构Weixin Liang* wxliang@stanford.edu Stanford University Lili Yu †, Liang Luo †, Srinivasan Iyer, Ning Dong, Chunting Zhou Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer Xi Victoria Lin victorialin@meta.com AI at MetaReviewed on OpenReview: https://openreview. net/forum? id=Nu6N69i8SB在 OpenReview 上评审：https://openreview. net/forum? id=Nu6N69i8SBAbstract摘要The development
