AI is broken, and we are here to fix it

Mission

My personal mission is to enhance human capabilities by supporting them through access to data-driven and knowledge-based predictions. I execute it by developing methods and tools for responsible machine learning, trustworthy artificial intelligence and reliable software engineering.

MI^2 research group

I lead MI2.AI (read “M-I-square”) group of model science enthusiasts, mostly from Math and Computer Science departments from University of Warsaw or Warsaw University of Technology. Together we create tools, try new methods and look for interesting opportunities to squeeze useful information from vast amount of data.

Current and former senior members (see the team’s website for a complete current list):

• Hubert Baniecki expected PhD defense in 2026
• Paulina Tomaszewska expected PhD defense in 2026
• Wiktoria Mieleszczenko-Kowszewicz postdoc in HOMER
• Katarzyna Woznica completed PhD in 2025 “Towards Trustworthy Automated Data Science”
• Katarzyna Kobylińska completed PhD in 2025 “Explainable machine learning for tabular data with examples of medical applications”
• Krzysztof Kotlarz completed PhD in 2025 “The application of deep learning methods in the analysis of livestock genomes”
• Weronika Hryniewska-Guzik completed PhD in 2025 “A multi-level perspective on the deep learning models and human-oriented explanations with applications to medical images”
• Mustafa Cavus postdoc in HOMER
• Barbara Rychalska completed PhD in 2023 “A Multimodal and Interpretable Recommender System for Massive Datasets”
• Tomasz Stanislawek completed PhD in 2021 “Extraction of information from graphic-rich documents”

Short Bio

Przemysław Biecek, PhD, is Director of the Centre for Credible AI at the Warsaw University of Technology and a Full Professor in the Faculty of Mathematics, Informatics and Mechanics at the University of Warsaw. His research focuses on Model Science—responsible and explainable artificial intelligence—with emphasis on model interpretability, controllability, and verifiability. He has authored or co-authored more than 200 scientific publications, including books and monographs, and has led numerous research and applied projects on interpretable predictive modelling.

He is internationally recognized as one of the top 2% most influential scientists (Stanford ranking) and a laureate of the prestigious Fulbright IMPACT Award. He received the “Frontiers in AI” distinction from Adam Mickiewicz University for his contributions to transparent and socially responsible AI. His work has appeared in leading venues such as Nature Machine Intelligence, NeurIPS, ICML, ECCV, CVPR, and AAAI. He has delivered invited talks at major conferences including ECML and ECAI and has co-organized workshops on explainable and trustworthy AI at NeurIPS, AAAI, ECAI, and ECML-PKDD.

Prof. Biecek is the creator and maintainer of widely used open-source packages for model interpretability (e.g., DALEX, auditor) and an active contributor to standardization efforts in credible AI. He has served on program committees of top-tier conferences, advised European institutions on AI safety and ethics, and collaborated with industry partners on deploying interpretable models in high-stakes domains.

Beyond research, he is strongly engaged in education and outreach. He founded the Smarter Poland Foundation and promotes AI literacy through comic books, courses, and science communication. His interdisciplinary work at the interface of statistics and computer science has established him as a leading voice in the global debate on reliable and responsible AI.

More in the CV (may not be up to date).

Solutions42.ai

Over the last 15 years I have carried out research and development for a number of public (University of Warsaw, Warsaw University of Technology) and private organisations (Samsung, Netezza, IBM, PositiveSolutions, Disney, iQor, LekSeek). In 2021 I founded Solutions42 to share this experience with other companies.

Solutions42.ai is an agile company helping large and small partners to design, implement and deploy Responsible Artificial Intelligence solutions.

We take an individual approach to each customer. We provide trainings, develop software, validate existing models or create new ones.

If you would like to discuss a possible collaboration, feel free to contact me.

Attitude

I am a data-driven person got it from my mentors. My PhD advisor in math was Witold Klonecki. His PhD advisor was Julian Perkal. And his PhD advisor was Hugo Steinhaus. And his advisor was David Hilbert. My PhD advisor in biology was Stanislaw Cebrat.