Treating state-space layers as tensor networks with CNN-style connectivity and optimized contraction orders yields hybrid SSM networks that outperform homogeneous SSMs on raw audio tasks and enable competitive streaming ASR without attention.
• For the full SSM block, we initialize ∆in over the i dimension, and Ajin over the n dimen- sion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
Treating state-space layers as tensor networks with CNN-style connectivity and optimized contraction orders yields hybrid SSM networks that outperform homogeneous SSMs on raw audio tasks and enable competitive streaming ASR without attention.