Tobias Höppe

Visiteur de recherche indépendant - Helmholtz Zentrum München

Superviseur⋅e principal⋅e

Kirill Neklyudov

Sujets de recherche

Apprentissage de représentations

Modèles de diffusion

Google Scholar

GitHub

Publications

On Closed-Form Couplings

Tobias Höppe

Stefan Bauer

Qiang Liu

Andrea Dittadi

Kirill Neklyudov

Few-step generative modelling is an open challenge for flow models. Rectified flows tackle it by distilling a pre-trained “teacher” into… (voir plus) a few-step “student”, using strong noise–data couplings supplied by the teacher. For a finite dataset and a Gaussian probability path, the probability-flow vector field induced by the empirical distribution is available in closed form, which would allow us to skip training a teacher model. Surprisingly, these couplings turn out to be poor teachers and significantly reduce the performance of the student. We analyse this phenomenon empirically and theoretically, arguing that it stems from intrinsic ambiguity in the induced couplings caused by the strong sensitivity of terminal states to small initialisation perturbations. Under symmetry assumptions, we further prove that the closed-form probability-flow vector field preserves dataset symmetries and induces invariant Voronoi partitions.

2026-03-02

DeLTa @ International Conference on Learning Representations (poster)

openreview.net