113 citations · 188 across the 17 of their papers we have counts for
11 papers · 1 filter
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
Yuhui Ding, Thomas Hofmann
Equivariant diffusion models have achieved impressive performance in 3D molecule generation. These models incorporate Euclidean symmetries of 3D molecules by utilizing an SE(3)-equ…
Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
Amir Joudaki, Thomas Hofmann
Understanding how neural networks transform input data across layers is fundamental to unraveling their learning and generalization capabilities. Although prior work has used insig…
Local vs Global continual learning
Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe +1
Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent…
Landscaping Linear Mode Connectivity
Sidak Pal Singh, Linara Adilova, Michael Kamp +3
The presence of linear paths in parameter space between two different network solutions in certain cases, i.e., linear mode connectivity (LMC), has garnered interest from both theo…
How Good is a Single Basin?
Kai Lion, Lorenzo Noci, Thomas Hofmann +1
The multi-modal nature of neural loss landscapes is often considered to be the main driver behind the empirical success of deep ensembles. In this work, we probe this belief by con…
Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures
Michael Hersche, Francesco di Stefano, Thomas Hofmann +2
Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently sol…