Mikolaj Kniejski

According to our database, Mikolaj Kniejski authored at least 3 papers in 2025.

Collaborative distances:

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

2025

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization.

Filip Sondej, Yushi Yang, Mikolaj Kniejski, Marcel Windys

CoRR, June, 2025

Personalized Interpretability - Interactive Alignment of Prototypical Parts Networks.

Tomasz Michalski, Adam Wróbel, Andrea Bontempelli, Jakub Lustyk, Mikolaj Kniejski, Stefano Teso, Andrea Passerini, Bartosz Zielinski, Dawid Rymarczyk

CoRR, June, 2025

Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems.

Pierre Peigné, Mikolaj Kniejski, Filip Sondej, Matthieu David, Jason Hoelscher-Obermaier, Christian Schröder de Witt, Esben Kran

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025