Pawel Walkowiak

According to our database, Pawel Walkowiak authored at least 5 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights.

Pawel Walkowiak, Marek Klonowski, Marcin Oleksy, Arkadiusz Janz

CoRR, May, 2025

Is Heterogeneous Model Soup Tasty? A Multidimensional Evaluation of Diverse Model Soups in Language Model Alignment.

Dawid Motyka, Pawel Walkowiak, Julia Moska, Bartosz Zuk, Karolina Seweryn, Arkadiusz Janz

Proceedings of the Computational Science - ICCS 2025, 2025

An Empirical Assessment of LLM-Based Approaches to Malicious Webpage Detection.

Gracjan Mak, Mateusz Gniewkowski, Pawel Walkowiak, Arkadiusz Janz

Proceedings of the Computational Science - ICCS 2025, 2025

Precise Language Deception: XAI Driven Targeted Adversarial Examples with Restricted Knowledge.

Mateusz Gniewkowski, Pawel Walkowiak, Marek Klonowski, Tomasz Walkowiak

Proceedings of the Computational Science - ICCS 2025, 2025

2023

Do Not Trust Me: Explainability Against Text Classification.

Mateusz Gniewkowski, Pawel Walkowiak, Piotr Syga, Marek Klonowski, Tomasz Walkowiak

Proceedings of the ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland, 2023