Ignacy Stepka

ignacy_thumbnail.jpg

I am currently working as a research assistant at Carnegie Mellon University under Dr. Artur Dubrawski in AutonLab . My research focuses on adaptive strategies for handling persistent agent failures in decentralized federated learning. Previously, I worked on the formal verification of Bayesian Networks to ensure AI systems meet critical design specifications. Additionally, I contributed to the DARPA Triage Challenge, helping develop a Bayesian Network prototype in collaboration with medical experts to autonomously perform triage during mass casualty incidents.

I also work as a research assistant at the Machine Learning Laboratory, Poznan University of Technology, under Prof. Jerzy Stefanowski and Dr. Mateusz Lango. My research focuses on developing robust counterfactual explanations to enhance the interpretability of black-box models in dynamic environments. Currently, I am designing a statistical approach to generate explanations that remain reliable despite model changes, making them more actionable for end-users.

Previously, I was part of the R&D team at the Poznan Supercomputing and Networking Center (Polish Academy of Sciences), contributing to various EU-funded projects since 2021. My work involved analyzing black-box model behavior and implementing anomaly detection solutions in industrial automotive settings and HPC clusters.

news

selected publications

  1. Conference
    Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change
    Ignacy Stępka, Mateusz Lango, and Jerzy Stefanowski
    In 31st SIGKDD Conference on Knowledge Discovery and Data Mining - Research Track, 2025