Tag: RNN
All the articles with the tag "RNN".
Kimi Linear: An Expressive, Efficient Attention Architecture
Updated: at 19:10Published: at 13:55Kimi 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
Published: at 15:25CVPR2018, DiffEncode + 稀疏加速,但感觉太老了。
Were RNNs All We Needed?
Updated: at 15:06Published: at 16:07改进RNN,便于scale up