activity
20242026
collaborators

5 papers

cs.CL2026

Revealing Hidden Model Behaviors with Task-Specific Self-Reports

Taras Kutsyk, Bartosz Zieliński

Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic. W…

cs.CV2025

Beyond [cls]: Exploring the true potential of Masked Image Modeling representations

Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński +2

Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typ…

cs.CV2024

Parameter-Efficient Interventions for Enhanced Model Merging

Marcin Osial, Daniel Marczak, Bartosz Zieliński

Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to…

cs.LG2024

OMENN: One Matrix to Explain Neural Networks

Adam Wróbel, Mikołaj Janusz, Bartosz Zieliński +1

Deep Learning (DL) models are often black boxes, making their decision-making processes difficult to interpret. This lack of transparency has driven advancements in eXplainable Art…

cs.CV2024

Revisiting FunnyBirds evaluation framework for prototypical parts networks

Szymon Opłatek, Dawid Rymarczyk, Bartosz Zieliński

Prototypical parts networks, such as ProtoPNet, became popular due to their potential to produce more genuine explanations than post-hoc methods. However, for a long time, this pot…