Mario Geiger
11 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (6) π Conference Polyglot (3) π Academic Marathon (7) πΊοΈ Taxonomy Completionist (16)
π
Conference Polyglot
(3)
π
Academic Marathon
(7)
π
Renaissance Researcher
(6)
π
Triple Crown
π
Conference Pioneer
π
Century Club
(11)
π
Trend Setter
Conferences
NIPS (5)
ICLR (3)
ICML (3)
Top co-authors
Keywords
geometric deep learning
(2)
stochastic gradient descent
(1)
feature learning
(1)
transfer learning
(1)
point cloud
(1)
irreducible representations
(1)
group theory
(1)
deep learning
(1)
neural network optimization
(1)
loss landscape
(1)
generalization error
(1)
feature map
(1)
deep neural network
(1)
convolutional network
(1)
quantum chemistry
(1)
test error
(1)
training dynamics
(1)
group equivariance
(1)
equivariant neural network
(1)
protein structure
(1)
Papers
Proteina: Scaling Flow-based Protein Structure Generative Models
ICLR 2025
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
ICML 2025
Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
ICLR 2024
A General Framework for Equivariant Neural Networks on Reductive Lie Groups
NIPS 2023
Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
ICML 2023
Relative stability toward diffeomorphisms indicates performance in deep nets
NIPS 2021
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
NIPS 2021
A General Theory of Equivariant CNNs on Homogeneous Spaces
NIPS 2019
Spherical CNNs
ICLR 2018
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
NIPS 2018
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
ICML 2018