标签: RNN
所有带有此标签的文章 "RNN".
-
Kimi Linear: An Expressive, Efficient Attention Architecture
更新于:Kimi Linear,有比较详细的实验&Scale Up。有Linear Attention可以去掉RoPE这个结论还是比较惊喜的。
-
Recurrent Residual Module for Fast Inference in Videos
更新于:CVPR2018, DiffEncode + 稀疏加速,但感觉太老了。
-
Were RNNs All We Needed?
更新于:改进RNN,便于scale up