Cartan flow matching
cs.LG, cs.AI
Submitted: 2026-05-05
Updated: 2026-08-27
Comments: Major revision. Fixed a mistake in section 4. 14 pages, 1 figure
Code: https://github.com/noegroup/bgflow
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: We introduce Cartan flow matching, a general framework for training flow matching models on Riemannian symmetric spaces, i.e.
Terminology
Abstract
We introduce Cartan flow matching, a general framework for training flow matching models on Riemannian symmetric spaces, i.e. Riemannian manifolds with the property that at any point there exists a geodesic symmetry. This is a large class of manifolds that includes the sphere, hyperbolic space and Grassmannians. We exploit their algebraic structure to reformulate flow matching on symmetric spaces as flow matching on a subspace of the Lie algebra of their isometry group, thus linearizing the problem and avoiding the need to construct geodesic interpolation paths on the manifold. As an application, we showcase our framework on the real Grassmannians SO(n) / SO(k) times SO(n-k).
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Continuous normalizing flows on manifolds
- Normalizing Flows on Riemannian Manifolds
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks