论文11:28TANGO: Token-Aggregated Nonlinear Gating Operators for Natural and Formal Language ModelingTANGO模型在自然和形式语言建模中表现出色,计算效率高,值得关注。与WANGO相比,在序列长度线性复杂度下表现更优。#TANGO#Transformer#自然语言建模#形式语言建模aarXiv: Google DeepMind@Joshua Nunley原文稍后读已读值得跟进有用关注 TANGO