sliding-window-attention

linear-attention ,  sliding-window-attention ,  spikingbrain ,  spike-coding ,  adaptive-threshold-spiking-neuron ,  brain-inspired ,  bic-lab ,  attention-map ,  conversion-based-training ,  moe-upcycling ,  neuromorphic

microsoft ,  long-context ,  small-llm ,  mamba ,  samba ,  sliding-window-attention ,  mlp-stacking