Hubert Baniecki
Research Assistant at University of Warsaw
Warsaw, Masovian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolHubert Baniecki is a PhD student and researcher in Warsaw with seven years of experience specializing in explainable and robust machine learning, currently available for postdoc positions starting in 2027. His work spans academia and collaborative visits to top European labs (LMU, Pisa), producing publications at NeurIPS, ICLR, ECML and applied papers in WACV and AIIM. He develops popular open-source tools for model explainability (DALEX, modelStudio, ingredients) with combined downloads ~25K/month and 2K GitHub stars, contributing both R backend and Python visualization fixes. His PhD project focuses on attack-resistant explanations for trustworthy AI, and he teaches explainable ML to MSc students. Unusually for a researcher, he blends deep theoretical contributions with hands-on engineering of widely used packages, making his work both scientifically rigorous and practically adopted.
7 years of coding experience
Master's degree, Data Science, Master's degree, Data Science at Warsaw University of Technology
English, Polish
Github Skills (11)
xai10
explainable-artificial-intelligence10
interpretation10
python10
data-science10
r10
machine-learning9
data-visualisation9
data-visualization9
pandas9
data-visualizations9
Programming languages (13)
Github contributions (5)
ModelOriented/DALEX
Aug 2019 - Jan 2023
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:2 releases, 55 reviews, 162 commits in 3 years 5 months
Contributions summary:Hubert primarily focused on updating and refining the `explain.R` file, indicating an involvement in the core functionalities of the package. Further contributions involved Python code, specifically in the `dalex` directory, with bug fixes, refactoring, and improvements in plots. These updates suggest a developer role with responsibilities in both the R backend and the Python data science components, focusing on model explainability and data visualization.
xaishapagnosticblack-boxexplainable-ml
MI2DataLab/fooling-partial-dependence
May 2021 - Jul 2022
Fooling Partial Dependence via Data Poisoning (ECML PKDD 2022)
Contributions:8 commits, 8 pushes, 1 branch in 1 year 1 month
poisoningpartialdependenceecml-pkdd
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.