Papers11:53Chinese contentGraph Machine:通过边实现更优预训练Graph Machine 用边对象替代传统状态,在 Qwen3-0.6B 上预训练时,稀疏层仅需少量检索就能保持性能。#Graph Machine#Qwen3-0.6B#Transformer#稀疏路由aarXiv cs.LG@Lintai HouSourceRead laterReadWorth followingUsefulFollow Graph Machine