Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation 文章

ArXiv CS.CL2026-05-29NEWSen作者: Aditi Khandelwal, Marius Mosbach, Verna Dankers, Siva Reddy, Golnoosh Farnadi
查看原文 →
关系图谱

Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation · 相关技术

相关技术

continual pre-trainingMixture-of-Experts