Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics
arXiv:2610.10626v1 Announce Type: new Abstract: Neural surrogates for vector-valued partial differential equations can fit training data yet change their predictions when the same physical state is expressed in a rotated coordinate frame. We study this failure on three-dimensional Navier--Stokes dy…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.LG
Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics