22 citations · 52 across the 12 of their papers we have counts for
14 papers
Unified all-atom molecule generation with neural fields
Matthieu Kirchmeyer, Pedro O. Pinheiro, Emma Willett +7
Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBin…
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
Frédéric A. Dreyer, Jan Ludwiczak, Karolis Martinkus +8
We introduce Ibex, a pan-immunoglobulin structure prediction model that achieves state-of-the-art accuracy in modeling the variable domains of antibodies, nanobodies, and T-cell re…
Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing
Andreas Loukas, Karolis Martinkus, Ed Wagstaff +1
As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training dat…
Efficient and Scalable Graph Generation through Iterative Local Expansion
Andreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin +1
In the realm of generative models for graphs, extensive research has been conducted. However, most existing methods struggle with large graphs due to the complexity of representing…
AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodies
Karolis Martinkus, Jan Ludwiczak, Kyunghyun Cho +8
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences. AbDiffuser is built on top of a new r…
Discovering Graph Generation Algorithms
Mihai Babiac, Karolis Martinkus, Roger Wattenhofer
We provide a novel approach to construct generative models for graphs. Instead of using the traditional probabilistic models or deep generative models, we propose to instead find a…
Automating Rigid Origami Design
Jeremia Geiger, Karolis Martinkus, Oliver Richter +1
Rigid origami has shown potential in large diversity of practical applications. However, current rigid origami crease pattern design mostly relies on known tessellations. This stro…
Diffusion Models for Graphs Benefit From Discrete State Spaces
Kilian Konstantin Haefeli, Karolis Martinkus, Nathanaël Perraudin +1
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the genera…
Agent-based Graph Neural Networks
Karolis Martinkus, Pál András Papp, Benedikt Schesch +1
We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computatio…
DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees
Peter Müller, Lukas Faber, Karolis Martinkus +1
We propose the fully explainable Decision Tree Graph Neural Network (DT+GNN) architecture. In contrast to existing black-box GNNs and post-hoc explanation methods, the reasoning of…
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
Karolis Martinkus, Andreas Loukas, Nathanaël Perraudin +1
We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these…
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Pál András Papp, Karolis Martinkus, Lukas Faber +1
This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs…
On Isotropy Calibration of Transformers
Yue Ding, Karolis Martinkus, Damian Pascual +2
Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in…
Scalable Graph Networks for Particle Simulations
Karolis Martinkus, Aurelien Lucchi, Nathanaël Perraudin
Learning system dynamics directly from observations is a promising direction in machine learning due to its potential to significantly enhance our ability to understand physical sy…