ACT blocks enable neural operators to learn adaptive coordinate systems via differentiable sampling, yielding consistent accuracy gains on PDE benchmarks by reducing spatial misalignment and operator complexity.
Forty-second International Conference on Machine Learning , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Coordinate Transforms for Neural Operators
ACT blocks enable neural operators to learn adaptive coordinate systems via differentiable sampling, yielding consistent accuracy gains on PDE benchmarks by reducing spatial misalignment and operator complexity.