AIConfPaper
← Search

Mario Geiger

11 accepted papers

2025

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan Dos Santos Costa, Danny Reidenbach, Karsten Kreis, Tomas Geffner +3
ICML 2025poster

Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we bui…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Proteina: Scaling Flow-based Protein Structure Generative Models

Tomas Geffner, Kieran Didi, Zuobai Zhang, Danny Reidenbach, Zhonglin Cao, Jason Yim +5
ICLR 2025oral

Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop *Proteina*, a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a t…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Ameya Daigavane, Song Eun Kim, Mario Geiger, Tess Smidt
ICLR 2024poster

We present Symphony, an $E(3)$ equivariant autoregressive generative model for 3D molecular geometries that iteratively builds a molecule from molecular fragments. Existing autoregressive models such as G-SchNet and G-SphereNet for molecules utilize rotationally invariant features to respect the 3D…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2023

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

Ilyes Batatia, Mario Geiger, Jose M Munoz, Tess Smidt, Lior Silberman, Christoph Ortner
NeurIPS 2023poster

Reductive Lie Groups, such as the orthogonal groups, the Lorentz group, or the unitary groups, play essential roles across scientific fields as diverse as high energy physics, quantum mechanics, quantum chromodynamics, molecular dynamics, computer vision, and imaging. In this paper, we present a gen…

Cited by 9Source ↗PDF ↗Scholar ↗
2023

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

Antonio Sclocchi, Mario Geiger, Matthieu Wyart
ICML 2023poster

Understanding when the noise in stochastic gradient descent (SGD) affects generalization of deep neural networks remains a challenge, complicated by the fact that networks can operate in distinct training regimes. Here we study how the magnitude of this noise $T$ affects performance as the size of t…

Cited by 7Source ↗PDF ↗Scholar ↗
2021

Relative stability toward diffeomorphisms indicates performance in deep nets

Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart
NeurIPS 2021poster

Understanding why deep nets can classify data in large dimensions remains a challenge. It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empirical measurements support that it is often not the case. We revisit this question by defining a maximum-entropy distrib…

Cited by 16Source ↗PDF ↗Scholar ↗
2021

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

Oliver Thorsten Unke, Mihail Bogojeski, Michael Gastegger, Mario Geiger, Tess Smidt, Klaus Robert Muller
NeurIPS 2021poster

Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Instead of training on a fixed set of properties, more recent approaches attempt to learn the electronic wavefunction (or de…

Cited by 118Source ↗PDF ↗Scholar ↗
2018

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma, Taco S Cohen
NeurIPS 2018poster

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such representations. These SE(3)-equivariant convolutions utilize kernels which are…

Cited by 618Source ↗PDF ↗code ↗Scholar ↗
2018

Comparing Dynamics: Deep Neural Networks versus Glassy Systems

Marco Baity-Jesi, Levent Sagun, Mario Geiger, Stefano Spigler, Gerard Ben Arous, Chiara Cammarota +3
ICML 2018oral

We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are the complexity of the loss-landscape and of the dynamics within it, and to what extent DNNs share similarities with glass…

Cited by 138Source ↗PDF ↗Scholar ↗