MiTA Attention: Efficient Fast-Weight Scaling via a Mixture of Top-k Activations

ArXi:2602.01219v4 Announce Type: replace The attention operator in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically instantiated from input tokens and whose width equals sequence length N. As the context extends, the expressive capacity of such an N-width MLP increases, but scaling its fast weights becomes prohibitively expensive for extremely long sequences. Recently, this fast-weight scaling perspective has motivated the Mixture-of-Experts (MoE) attention, which partitions the sequence into fast-weight experts and sparsely routes the tokens to them.