I am a fourth-year Ph.D. student in the Amsterdam Machine Learning Lab (AMLab) and the AI4Science lab of the University of Amsterdam. I have also interned at Google Deepmind, Microsoft Research (AI4Science), and the Simon's Foundation's Flatiron Institute. My research interests include (3D) geometric deep learning, AI4Science, computer vision, generative models and time-series, often working at an intersection of these.

David Ruhe

David Ruhe

Ph.D. Student at the University of Amsterdam


Selected Publications

Clifford Group Equivariant Neural Networks (NeurIPS 2023 Oral)

Clifford Group Equivariant Neural Networks (NeurIPS 2023 Oral)

$\mathrm{E}(n)$ steerable equivariance using Clifford's geometric algebra.

David Ruhe, Johannes Brandstetter, Patrick Forré

Read More

Geometric Clifford Algebra Networks (Microsoft Research, ICML 2023)

Geometric Clifford Algebra Networks (Microsoft Research, ICML 2023)

Incorporating geometry into neural network transformations.

David Ruhe, Jayesh K. Gupta, Steven de Keninck, Max Welling, Johannes Brandstetter

Read More

Rolling Diffusion Models (Google Deepmind, ICML 2024)

Rolling Diffusion Models (Google Deepmind, ICML 2024)

A temporal prior for video diffusion.

David Ruhe, Jonathan Heek, Tim Salimans, Emiel Hoogeboom

Read More

Clifford-Steerable Convolutional Neural Networks (ICML 2024)

Clifford-Steerable Convolutional Neural Networks (ICML 2024)

Steerable $\mathrm{E}(p, q)$ convolutions on multivector fields.

Maxim Zhdanov, David Ruhe$^*$, Maurice Weiler$^*$, Ana Lucic, Johannes Brandstetter, Patrick Forré

Read More

Clifford Group Equivariant Simplicial Message Passing Networks (ICLR 2024)

Clifford Group Equivariant Simplicial Message Passing Networks (ICLR 2024)

Equivariant $\mathrm{E}(n)$ message passing on simplicial complexes.

Cong Liu$^*$, David Ruhe$^*$, Floor Eijkelboom, Patrick Forré

Read More

Self-Supervised Inference in State-Space Models (ICLR 2022)

Self-Supervised Inference in State-Space Models (ICLR 2022)

Learning Kalman filters with physics-informed models.

David Ruhe, Patrick Forré

Read More

Normalizing Flows for Hierarchical Bayesian Analysis (ML4PHYS 2022)

Normalizing Flows for Hierarchical Bayesian Analysis (ML4PHYS 2022)

Inferring gravitational wave parameters using normalizing flows.

David Ruhe, Kaze Wong, Miles Cranmer, Patrick Forré

Read More


Posts