MobileMoE: Scaling On-Device Mixture of Experts 文章

ArXiv CS.CL2026-05-27NEWSen作者: Yanbei Chen, Hanxian Huang, Ernie Chang, Jacob Szwejbka, Digant Desai, Zechun Liu, Vikas Chandra, Raghuraman Krishnamoorthi
查看原文 →
关系图谱

MobileMoE: Scaling On-Device Mixture of Experts · 相关技术

相关技术

LLMORMODElanguage model递归自我改进远程代码执行（RCE）研究法辛烷值divide-and-conquer partitioningUCTScaling lawSPAReferring expression comprehension (REC)Quantization-Aware TrainingPre-trainingOTAMoEMixture-of-ExpertsLMMIMUHISGranular Alignment ParadigmForEffort Metric AttentionAnEARGANNICE