[go: up one dir, main page]

Follow
Kirill Bykov
Title
Cited by
Cited by
Year
Explaining Bayesian Neural Networks
K Bykov, MMC Höhne, A Creosteanu, KR Müller, F Klauschen, ...
Transactions on Machine Learning Research, 2021
90*2021
NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights
K Bykov, A Hedström, S Nakajima, MMC Höhne
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6132-6140, 2022
552022
Labeling Neural Representations with Inverse Recognition
K Bykov, L Kopf, S Nakajima, M Kloft, M Höhne
Advances in Neural Information Processing Systems 36, 24804-24828, 2023
292023
DORA: Exploring Outlier Representations in Deep Neural Networks
K Bykov, M Deb, D Grinwald, KR Müller, MMC Höhne
Transactions on Machine Learning Research, 2023
212023
CoSy: Evaluating Textual Explanations of Neurons
L Kopf, PL Bommer, A Hedström, S Lapuschkin, MMC Höhne, K Bykov
Advances in Neural Information Processing Systems 37, 2024
15*2024
Mark My Words: Dangers of Watermarked Images in ImageNet
K Bykov, KR Müller, MMC Höhne
Communications in Computer and Information Science 1947, 426--434, 2024
102024
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
D Grinwald, K Bykov, S Nakajima, MMC Höhne
Transactions on Machine Learning Research, 2023
62023
Deep learning meets teleconnections: Improving S2S predictions for European winter weather
PL Bommer, M Kretschmer, FR Spuler, K Bykov, MMC Höhne
Machine Learning: Earth 1 (1), 015002, 2025
52025
Manipulating Feature Visualizations with Gradient Slingshots
D Bareeva, MMC Höhne, A Warnecke, L Pirch, KR Müller, K Rieck, ...
arXiv preprint arXiv:2401.06122, 2024
42024
Finding Spurious correlations with Function-Semantic Contrast Analysis
K Bykov, L Kopf, MMC Höhne
World Conference on Explainable Artificial Intelligence, 549-572, 2023
42023
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
L Kopf, N Feldhus, K Bykov, PL Bommer, A Hedström, MMC Höhne, ...
arXiv preprint arXiv:2506.15538, 2025
32025
Combining spatio-temporal neural networks with mechanistic interpretability to investigate teleconnections in S2S forecasts
PL Bommer, M Kretschmer, F Spurler, K Bykov, P Boehnke, MMC Hoehne
EGU General Assembly Conference Abstracts, EGU25-9753, 2025
2025
The system can't perform the operation now. Try again later.
Articles 1–12