collaborators

5 papers

cs.RO2026

Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models

Li Wenjie, Yash Jangir, Ignacy Stepka +3

Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models (VLAs) are ty…

cs.LG2025

Explaining Concept Drift through the Evolution of Group Counterfactuals

Ignacy Stępka, Jerzy Stefanowski

Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-st…

cs.LG2025

Mitigating Persistent Client Dropout in Asynchronous Decentralized Federated Learning

Ignacy Stępka, Nicholas Gisolfi, Kacper Trębacz +1

We consider the problem of persistent client dropout in asynchronous Decentralized Federated Learning (DFL). Asynchronicity and decentralization obfuscate information about model u…

cs.CV2025

DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision

Ignacy Stępka, Lukasz Sztukiewicz, Michał Wiliński +1

While machine learning fairness has made significant progress in recent years, most existing solutions focus on tabular data and are poorly suited for vision-based classification t…

cs.LG2025

Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change

Ignacy Stępka, Mateusz Lango, Jerzy Stefanowski

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static sce…