Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …

Diffusion models are recent state-of-the-art methods for image generation and likelihood
estimation. In this work, we generalize continuous-time diffusion models to arbitrary …

We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training
continuous normalizing flows on manifolds. Existing methods for generative modeling on …

We propose a new class of parameterizations for spatio-temporal point processes which
leverage Neural ODEs as a computational method and enable flexible, high-fidelity models …

Normalizing flows have shown great promise for modelling flexible probability distributions
in a computationally tractable way. However, whilst data is often naturally described on …

Normalizing flows are a promising tool for modeling probability distributions in physical
systems. While state-of-the-art flows accurately approximate distributions and energies …

Normalizing flows (NF) are a class of powerful generative models that have gained
popularity in recent years due to their ability to model complex distributions with high …

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud
Representations of dynamically moving or evolving objects. Our goal is to enable …

Recent methods in geometric deep learning have introduced various neural networks to
operate over data that lie on Riemannian manifolds. Such networks are often necessary to …