Author

Vincent Souveton

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Riemannian Neural Hamiltonian Flows: Geodesic Symplectic Transport and Interpretability

Riemannian Neural Hamiltonian Flows are introduced, which combine the fixed kinetic energy of a Riemannian manifold, a learned scalar potential, and an explicit geodesic leapfrog integrator to explain how the learned Hamiltonian can be made interpretable.

Vincent Souveton · 0 citations