Better Pre-Training by Reducing Representation Confusion
BetterPre-TrainingbyReducingRepresentationConfusionHaojieZhang1,2,MingfeiLiang1,RuobingXie1,ZhenlongSun1,BoZhang1,LeyuLin11WeChatSearchApplicationDepartment,Tencent,China2PekingUniversity,China1{coldhjzhang,aesopliang,ruobingxie,richardsun,nevinzhang,goshawklin}@tencent.com2zhanghaojie@stu.pku.ed...
2025-04-22
459.62KB 12 页 3
0
10玖币