15 citations
- Technische Universität BerlinDE10 papers
- Max Planck Institute for InformaticsDE3 papers
- Charité - Universitätsmedizin BerlinDE2 papers
- Korea UniversityKR2 papers
- University of TorontoCA2 papers
- Vector InstituteCA2 papers
- AstraZeneca (Australia)AU1 paper
- AstraZeneca (Brazil)BR1 paper
- BASF (Germany)DE1 paper
- Berlin Institute of Health at Charité - Universitätsmedizin BerlinDE1 paper
- Brain (Germany)DE1 paper
- Brown UniversityUS1 paper
15 papers
Distributed Sparse Interventions in Language Models
Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1
Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and se…
Gradient-Guided Furthest Point Sampling for Robust Training Set Selection
Morris Trestman, Stefan Gugler, Felix A. Faber +1
Training set sampling methods are used to improve model performance and lower data costs in machine learning problems relevant to chemistry. We introduce Gradient Guided Furthest P…
Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Florian Bley, Jacob Kauffmann, Simon León Krug +2
Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practic…
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker +5
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to b…
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Sidney Bender, Jan Herrmann, Klaus-Robert Müller +1
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations…
On the Role of Pre-trained Embeddings in Binary Code Analysis
Alwin Maier, Felix Weissberg, Konrad Rieck
Deep learning has enabled remarkable progress in binary code analysis. In particular, pre-trained embeddings of assembly code have become a gold standard for solving analysis tasks…