AudioRWKV, an RWKV7-based audio backbone with 2D convolution and bidirectional WKV, beats AST and AuM baselines on five benchmarks at linear complexity.
The foundational principle is the systematic replacement of the original 1D token shift operation with a 2D depthwise sep- arable convolution (DWConv2D)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition
AudioRWKV, an RWKV7-based audio backbone with 2D convolution and bidirectional WKV, beats AST and AuM baselines on five benchmarks at linear complexity.