Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models 文章

ArXiv CS.CL2026-05-28NEWSen作者: Guanzhi Deng, Kuan Wu, Haibo Wang, Shing Yin Wong, Sichun Luo, Linqi Song

Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models · 相关技术