註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Oliver Sieberling @ COLM
@osieberling
PhD student @MIT, pretraining large neural networks, rnn enjoyer
加入 January 2024
794 正在關注    950 粉絲
Linear attention is arguably the most naive RNN, but still massively outperforms traditional RNNs by maintaining a matrix state. So... what if we use a (triadic) outer product of three vectors and maintain a three-dimensional state? Introducing: Triadic Linear Attention 🧵
顯示更多
0
31
854
104
轉發到社區