论文Agent 与开发者11:04Looped Mixture of Experts扩展定律研究这篇论文提出了首个联合建模循环和稀疏性的扩展定律,万亿token规模实验显示其能实现2倍参数效率提升。#Looped Mixture of Experts#MoE#扩展定律#稀疏性aarXiv cs.AI@Yanbei Chen 等 3 人原文稍后读已读值得跟进有用关注 Looped Mixture of Experts