A new neural operator architecture, SKNO, models embedding evolution along an added auxiliary dimension with Fourier kernels and reports state-of-the-art errors on PDE benchmarks.
01") denotes the output after theL0 and before theσ0 betweenv0 andv1, whereas a single-digit index (e.g.,
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
-
Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution
A new neural operator architecture, SKNO, models embedding evolution along an added auxiliary dimension with Fourier kernels and reports state-of-the-art errors on PDE benchmarks.