92 citations · 114 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 2 cited
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Thomas Schmied, Thomas Adler, Vihang Patil +6
In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Exist…
cs.LG2024★ 92 cited
xLSTM: Extended Long Short-Term Memory
Maximilian Beck, Korbinian Pöppel, Markus Spanring +6
In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and co…