Kacper Wyrwal

2 accepted papers

2026

Topological Flow Matching

Kacper Wyrwal, Ismail Ilkan Ceylan, Alexander Tong

ICLR 2026poster

Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance. However, its standard formulation treats signals on structured spaces---such as fMRI data on brain graphs---as points in Euclidean space, overlooking the rich topological features o…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Residual Deep Gaussian Processes on Manifolds

Kacper Wyrwal, Andreas Krause, Viacheslav Borovitskiy

ICLR 2025oral

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 last layer, they can model manifold- and scalar-valued functions, as well as vector fields. We target data inherently sup…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗