12 citations · 27 across the 14 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
Johannes von Oswald, Nino Scherrer, Seijin Kobayashi +14
Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compu…
cs.LG2020★ 2 cited
Intelligent Matrix Exponentiation
Thomas Fischbacher, Iulia M. Comsa, Krzysztof Potempa +3
We present a novel machine learning architecture that uses the exponential of a single input-dependent matrix as its only nonlinearity. The mathematical simplicity of this architec…