基于中间层对齐的异构师生模型知识蒸馏(Knowledge distillation of heterogeneous teacher-student model with intermediate layer loss)

基于中间层对齐的异构师生模型知识蒸馏(Knowledge distillation of heterogeneous teacher-student model with intermediate layer loss) Feiyan Zhai author Renzhi Wang author Piji Li author 2024-07 text zho Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference) Sun Maosong editor Liang Jiye editor Han Xianpei editor Liu Zhiyuan editor He Yulan editor Chinese Information Processing Society of China Taiyuan, China conference publication feiyan-etal-2024-ji https://aclanthology.org/2024.ccl-1.71/ 2024-07 910 928