作者位次 #7/7ICML 2026Poster· Deep Learning / Large Language Models
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Zhendong Mi · Yixiao Chen · Pu Zhao · Xiaodong Yu · Hao Wang · Yanzhi Wang · Shaoyi Huang
效率与系统OpenReview