<ul><li>Researchers introduce Centaurus, a class of networks composed of generalized state-space model (SSM) blocks.</li><li>The SSM operations can be treated as tensor contractions during training.</li><li>The optimal order of tensor contractions is determined for every SSM block to maximize training efficiency.</li><li>The Centaurus network outperforms its counterparts in raw audio processing tasks and achieves competitive performance in automatic speech recognition (ASR).</li></ul>

Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions

Discover more