7 papers
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
Patryk Marszałek, Tomasz Kuśmierczyk, Marek Śmieja
Anomaly detection for tabular data has been a long-standing unsupervised learning problem that remains a major challenge for current deep learning models. Recently, in-context lear…
CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
Oleksii Furman, Patryk Marszałek, Jan Masłowski +3
Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output…
DiCoFlex: Model-agnostic diverse counterfactuals with flexible control
Oleksii Furman, Ulvi Movsum-zada, Patryk Marszalek +2
Counterfactual explanations play a pivotal role in explainable artificial intelligence (XAI) by offering intuitive, human-understandable alternatives that elucidate machine learnin…
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Patryk Marszałek, Tomasz Kuśmierczyk, Witold Wydmański +2
Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across da…
HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
Patryk Marszałek, Kamil Książek, Oleksii Furman +3
In recent years, there has been a growing interest in explainable AI methods. In addition to making accurate predictions, we also want to understand what the model's decision is ba…
As Good as It KAN Get: High-Fidelity Audio Representation
Patryk Marszałek, Maciej Rut, Piotr Kawa +2
Implicit neural representations (INR) have gained prominence for efficiently encoding multimedia data, yet their applications in audio signals remain limited. This study introduces…