Conference ProceedingTinyGPT-MoE: Scaling Multi-modal Large Language Model via Advanced Vision Encoder with Mixture-of-ExpertsYuan, Zhengqing; Wang, Yang; Li, Zhaoxu; Ye, Yanfang; Sun, LichaoWorkshop on Advancing Neural Network Training at International Conference on Machine Learning (WANT@ICML)2024-07-2110581235Proceedings of Machine Learning Research2640-3498https://doi.org/2203261National Science Foundation