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.
Transolver++: An Accurate Neural Solver for
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative 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.
- Inpainting physics: self-supervised learning for context-driven fluid simulation