1
Parallax: Parameterized Local Linear Attention for Language Modeling
提出参数化局部线性注意力机制，在语言建模中兼顾效率与性能，为Transformer改进提供新思路。
arXiv:2605.29157v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the co…