SpanNorm: Reconciling Training Stability and Performance in Deep Transformers 文章

ArXiv CS.CL2026-06-05NEWSen作者: Chao Wang, Bei Li, Jiaqi Zhang, Xinyu Liu, Yuchun Fan, Linkun Lyu, Xin Chen, Jingang Wang, Tong Xiao, Peng Pei, Xunliang Cai

SpanNorm: Reconciling Training Stability and Performance in Deep Transformers · 相关技术