Picture for Mario Geiger

Mario Geiger

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for Molecule Generation

Add code
Nov 27, 2023
Viaarxiv icon

Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoders

Add code
Oct 04, 2023
Viaarxiv icon

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

Add code
May 31, 2023
Viaarxiv icon

An end-to-end SE-equivariant segmentation network

Add code
Mar 02, 2023
Viaarxiv icon

Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning

Add code
Jan 31, 2023
Viaarxiv icon

e3nn: Euclidean Neural Networks

Add code
Jul 18, 2022
Figure 1 for e3nn: Euclidean Neural Networks
Figure 2 for e3nn: Euclidean Neural Networks
Figure 3 for e3nn: Euclidean Neural Networks
Figure 4 for e3nn: Euclidean Neural Networks
Viaarxiv icon

How memory architecture affects performance and learning in simple POMDPs

Add code
Jun 16, 2021
Figure 1 for How memory architecture affects performance and learning in simple POMDPs
Figure 2 for How memory architecture affects performance and learning in simple POMDPs
Figure 3 for How memory architecture affects performance and learning in simple POMDPs
Figure 4 for How memory architecture affects performance and learning in simple POMDPs
Viaarxiv icon

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

Add code
Jun 04, 2021
Figure 1 for SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
Figure 2 for SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
Viaarxiv icon

Relative stability toward diffeomorphisms in deep nets indicates performance

Add code
May 06, 2021
Figure 1 for Relative stability toward diffeomorphisms in deep nets indicates performance
Figure 2 for Relative stability toward diffeomorphisms in deep nets indicates performance
Figure 3 for Relative stability toward diffeomorphisms in deep nets indicates performance
Figure 4 for Relative stability toward diffeomorphisms in deep nets indicates performance
Viaarxiv icon

Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training

Add code
Dec 30, 2020
Figure 1 for Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training
Figure 2 for Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training
Figure 3 for Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training
Figure 4 for Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training
Viaarxiv icon