2 papers
cs.LG2026
Topological Flow Matching
Kacper Wyrwal, Ä°smail Ä°lkan Ceylan, Alexander Tong
Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance. However, its standard formulation treats signals on structure…
stat.ML2025
Residual Deep Gaussian Processes on Manifolds
Kacper Wyrwal, Andreas Krause, Viacheslav Borovitskiy
We propose practical deep Gaussian process models on Riemannian manifolds, similar in spirit to residual neural networks. With manifold-to-manifold hidden layers and an arbitrary l…