11 papers
Let the Dynamics Flow: Stable Flow Matching Dynamical Systems
Rodrigo Pérez-Dattari, Francisco Leiva, Andrea Testa +3
Flow matching has recently emerged as a powerful approach for imitation learning, enabling scalable, expressive, and multimodal motion policies. However, when modeling these polici…
Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
Andrea Testa, Søren Hauberg, Tamim Asfour +1
The Schrödinger Bridge provides a principled framework for modeling stochastic processes between distributions; however, existing methods are limited by energy-conservation assump…
Taxonomy-aware Dynamic Motion Generation on Hyperbolic Manifolds
Luis Augenstein, Noémie Jaquier, Tamim Asfour +1
Human-like motion generation for robots often draws inspiration from biomechanical studies, which often categorize complex human motions into hierarchical taxonomies. While these t…
The GeometricKernels Package: Heat and Matérn Kernels for Geometric Learning on Manifolds, Meshes, and Graphs
Peter Mostowsky, Vincent Dutordoir, Iskander Azangulov +6
Kernels are a fundamental technical primitive in machine learning. In recent years, kernel-based methods such as Gaussian processes are becoming increasingly important in applicati…
Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions
Hadi Beik Mohammadi, Søren Hauberg, Georgios Arvanitidis +2
Stability guarantees are crucial when ensuring that a fully autonomous robot does not take undesirable or potentially harmful actions. We recently proposed the Neural Contractive D…
Towards Safe Imitation Learning via Potential Field-Guided Flow Matching
Haoran Ding, Anqing Duan, Zezhou Sun +4
Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However,…