activity
20242026
collaborators

6 papers

cs.LG2026

Approximate Equivariance via Projection-based Regularisation

Torben Berndt, Jan Stühmer

Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention,…

q-bio.BM2025

Learning conformational ensembles of proteins based on backbone geometry

Nicolas Wolf, Leif Seute, Vsevolod Viliuga +3

Deep generative models have recently been proposed for sampling protein conformations from the Boltzmann distribution, as an alternative to often prohibitively expensive Molecular…

cs.LG2025

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning

Torben Berndt, Benjamin Walker, Tiexin Qin +2

Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential…

q-bio.BM2025

Flexibility-Conditioned Protein Structure Design with Flow Matching

Vsevolod Viliuga, Leif Seute, Nicolas Wolf +4

Recent advances in geometric deep learning and generative modeling have enabled the design of novel proteins with a wide range of desired properties. However, current state-of-the-…

cs.LG2025

Set-LLM: A Permutation-Invariant LLM

Beni Egressy, Jan Stühmer

While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a speci…

cs.LG2024

Generating Highly Designable Proteins with Geometric Algebra Flow Matching

Simon Wagner, Leif Seute, Vsevolod Viliuga +3

We introduce a generative model for protein backbone design utilizing geometric products and higher order message passing. In particular, we propose Clifford Frame Attention (CFA),…