1 citations · 2 across the 9 of their papers we have counts for
10 papers
Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks
Tomáš Kolárik, Faezeh Labbaf, Fabrizio Leopardi +3
Formal explainability of classifying neural networks (NNs) is an active area of research, providing explanations with provable guarantees of the classification within continuous re…
Ab initio parametrization of distributed polarizable force fields
Felix Post, Jean-Philip Filling, Toulik Maitra +3
Polarizable force fields offer superior transferability and accuracy compared to classical force fields, enabling access to electronic response properties such as refractive index…
Tensor Channel Equivariant Graph Neural Networks for Molecular Polarizability Prediction
Jean Philip Filling, Daniel Franzen, Michael Wand
We introduce a tensor-channel equivariant graph neural network for direct prediction of molecular polarizability tensors. Building on the efficient PaiNN architecture, we augment t…
Reconstruction of spin structures from topological charge distributions via generative neural network systems
Kyra H. M. Klos, Jan Disselhoff, Michael Wand +2
Localized topological defects inherently possess a multiscale character. While their microstructure configuration depends on the specific physical system, their topological feature…
Multiple Token Divergence: Measuring and Steering In-Context Computation Density
Vincent Herrmann, Eric Alcaide, Michael Wand +1
Measuring the in-context computational effort of language models is a key challenge, as metrics like next-token loss fail to capture reasoning complexity. Prior methods based on la…
Space Explanations of Neural Network Classification
Faezeh Labbaf, Tomáš Kolárik, Martin Blicha +3
We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas o…
Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs
Jean Philip Filling, Felix Post, Michael Wand +1
We introduce a novel equivariant graph neural network (GNN) architecture designed to predict the tensorial response properties of molecules. Unlike traditional frameworks that focu…
Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
Mikhail Andronov, Natalia Andronova, Michael Wand +2
AI-based computer-aided synthesis planning (CASP) systems are in demand as components of AI-driven drug discovery workflows. However, the high latency of such CASP systems limits t…
ResNets Are Deeper Than You Think
Christian H. X. Ali Mehmeti-Göpel, Michael Wand
Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramati…
Accelerating the inference of string generation-based chemical reaction models for industrial applications
Mikhail Andronov, Natalia Andronova, Michael Wand +2
Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis pla…