LaMO replaces attention in latent-token neural operators with bidirectional state-space models and reports consistent accuracy gains on six PDE benchmarks.
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic self-attention cost presents an appealing direction. Recently, state space models (SSMs), such as Mamba, have demonstrated potential in language and vision tasks in this regard. In this study, we explore whether reliance on self-attention is necessary for audio classification tasks. By introducing Audio Mamba (AuM), the first self-attention-free, purely SSM-based model for audio classification, we aim to address this question. We evaluate AuM on various audio datasets - comprising six different benchmarks - where it achieves comparable or better performance compared to well-established AST model.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent Mamba Operator for Partial Differential Equations
LaMO replaces attention in latent-token neural operators with bidirectional state-space models and reports consistent accuracy gains on six PDE benchmarks.