Model
xLSTM
A sequence modeling architecture improved upon LSTM, introducing exponential gating and matrix memory (mLSTM) to enhance long-range modeling capability.
Timeline (last 90 days)
Oct 14
Most SSM and linear attention models use a linear attention mechanism at the bottom layer, with Mamba-2 implemented through the SSD structure and xLSTM implemented through covariance updates.
Unverified50%