Hubert Baniecki
@hbaniecki
About
PhD student, University of Warsaw
Skills & Technologies
Projects & Repositories
Recent public projects and repositories from this profile.
compress-then-explain
PythonEfficient and accurate explanation estimation with distribution compression (ICLR 2025 Spotlight)
adversarial-explainable-ai
💡 Adversarial attacks on explanations and how to defend them
metaexamples
No project description available.
fixlip
Jupyter NotebookExplaining similarity in vision-language encoders with weighted Banzhaf interactions (NeurIPS 2025)
adversarial-analysis-of-interpretable-dl
PythonBirds look like cars: Adversarial analysis of intrinsically interpretable deep learning (Machine Learning, 2025)
robust-feature-effects
Jupyter NotebookRobustness of Global Feature Effect Explanations (ECML PKDD 2024)