Kirill Bykov

Berlin Institute for the Foundations of Learning and Data

Computer Science · Physical Sciences

5h-index72citations17works1.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Adversarial Robustness in Machine Learning(8), Explainable Artificial Intelligence (XAI)(8), Anomaly Detection Techniques and Applications(4), Machine Learning and Data Classification(3), Advanced Steganography and Watermarking Techniques(2)

Publications17 total

Deep learning meets teleconnections: improving S2S predictions for European winter weather
Machine Learning Earth·2025· 5 citedOpen Access
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arXiv (Cornell University)·2025Open Access
Combining spatio-temporal neural networks with mechanistic interpretability to investigate teleconnections in S2S forecasts
2025Open Access
On Implementation of the Law Enforcement Function by Territorial Police Authorities on the District Level (on the Example of the Migration Sphere)
Administrative law and procedure·2024
CoSy: Evaluating Textual Explanations of Neurons
arXiv (Cornell University)·2024Open Access
Manipulating Feature Visualizations with Gradient Slingshots
arXiv (Cornell University)·2024Open Access
Mark My Words: Dangers of Watermarked Images in ImageNet
Communications in computer and information science·2024· 3 cited
CoSy: Evaluating Textual Explanations of Neurons
2024
Labeling Neural Representations with Inverse Recognition
arXiv (Cornell University)·2023· 1 citedOpen Access
Mark My Words: Dangers of Watermarked Images in ImageNet
arXiv (Cornell University)·2023· 1 citedOpen Access
Finding Spurious Correlations with Function-Semantic Contrast Analysis
Communications in computer and information science·2023Open Access
NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights
Proceedings of the AAAI Conference on Artificial Intelligence·2022· 20 citedOpen Access
DORA: Exploring Outlier Representations in Deep Neural Networks
arXiv (Cornell University)·2022· 6 citedOpen Access
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
arXiv (Cornell University)·2022· 2 citedOpen Access
Explaining Bayesian Neural Networks
arXiv (Cornell University)·2021· 15 citedOpen Access
NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights
arXiv (Cornell University)·2021· 1 citedOpen Access
How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
arXiv (Cornell University)·2020· 18 citedOpen Access

Frequent Co-authors

Marina M. -C. Höhne(8), Marina Höhne(7), Shinichi Nakajima(6), Klaus‐Robert Müller(6), Anna Karin Hedström(5), Philine Lou Bommer(5), Laura Kopf(5), Marius Kloft(3), Dennis Grinwald(2), Marlene Kretschmer(2), Fiona R. Spuler(2), Sebastian Lapuschkin(2), Adelaida Creosteanu(1), Frederick Klauschen(1), Mayukh Deb(1), Dilyara Bareeva(1), Alexander Warnecke(1), Lukas Pirch(1), Konrad Rieck(1), Nils Feldhus(1)