9 citations
- Technische Universität BerlinDE4 papers
- École Normale Supérieure de LyonFR3 papers
- Fraunhofer Institute for Production Systems and Design TechnologyDE2 papers
- Lyon 1 UniversitéFR2 papers
- AGH University of KrakowPL1 paper
- Aligarh Muslim UniversityIN1 paper
- Banaras Hindu UniversityIN1 paper
- Beijing Haidian HospitalCN1 paper
- Berlin Institute for the Foundations of Learning and DataDE1 paper
- Bose InstituteIN1 paper
- Central China Normal UniversityCN1 paper
- Centre Inria de l'Université Grenoble AlpesFR1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026★ 9 cited
Riemannian Denoising Diffusion Probabilistic Models
Zichen Liu, Wei Zhang, Christof Schütte +1
We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including mo…
cs.LG2026★ 3 cited
Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
Martin Hanik, Gabriele Steidl, Christoph von Tycowicz
We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion l…