谷歌浏览器插件
订阅小程序
在清言上使用
VIPCreated with Sketch.

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

Ganesh Jawahar,Haichuan Yang,Yunyang Xiong,Zechun Liu,Dilin Wang,Fei Sun,Meng Li,Aasish Pappu,Barlas Oguz,Muhammad Abdul-Mageed,Laks V. S. Lakshmanan,Raghuraman Krishnamoorthi,Vikas Chandra

ICLR 2024（2024）

引用 5|浏览138
关键词
Neural architecture search,Supernet,Machine Translation,Language models
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要