5 papers
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…
Explaining Concept Drift through the Evolution of Group Counterfactuals
Ignacy StÄpka, 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…
Mitigating Persistent Client Dropout in Asynchronous Decentralized Federated Learning
Ignacy StÄpka, Nicholas Gisolfi, Kacper TrÄbacz +1
We consider the problem of persistent client dropout in asynchronous Decentralized Federated Learning (DFL). Asynchronicity and decentralization obfuscate information about model u…
DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision
Ignacy StÄpka, Lukasz Sztukiewicz, MichaÅ WiliÅski +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…
Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change
Ignacy StÄpka, 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…