SAE-NOs extend sparse autoencoders to function spaces via Fourier neural operators with concept and domain sparsity, learning localized patterns more efficiently and generalizing across discretizations on vision data.
Unify- ing subsampling pattern variations for compressed sensing mri with neural operators,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mechanistic Interpretability with Sparse Autoencoder Neural Operators
SAE-NOs extend sparse autoencoders to function spaces via Fourier neural operators with concept and domain sparsity, learning localized patterns more efficiently and generalizing across discretizations on vision data.