ExFusion: Efficient Transformer Training via Multi-Experts Fusion
ExFusion:通过多专家融合实现高效的Transformer训练
机构 * School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院) ; Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ; Huazhong University of Science and Technology(华中科技大学) ; Soochow University(苏州大学) ; Chinese University of Hong Kong(香港中文大学) ; School of Biomedical Engineering, Shanghai Jiao Tong University(上海交通大学生物医学工程学院)
AI总结 ExFusion通过多专家融合提升Transformer训练效率,在保持性能的同时降低计算成本。
Comments Accepted by IEEE TMM2026