Approximates manifold heat kernels via PINNs solving the heat equation to enable diffusion models on arbitrary manifolds including S2, SO(3), and SPD(n).
and Thirion, B
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces Off-log metric for correlation matrices and Grassmannian subspace distances to improve sensitivity and classification in fMRI brain network analysis across clinical and ageing datasets.
citing papers explorer
-
Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks
Approximates manifold heat kernels via PINNs solving the heat equation to enable diffusion models on arbitrary manifolds including S2, SO(3), and SPD(n).
-
Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
Introduces Off-log metric for correlation matrices and Grassmannian subspace distances to improve sensitivity and classification in fMRI brain network analysis across clinical and ageing datasets.