Length Generalization

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While existing …
Ermo Hua, Che Jiang, Xingtai Lv, Kaiyan Zhang, Ning Ding, Youbang Sun, Biqing Qi, Yuchen Fan, Xuekai Zhu, Bowen Zhou
PDF Cite Code
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization