activity
20242026
collaborators

6 papers

cs.CL2026

Shieldstral

Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +274

We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…

cs.CV2026

Accurate and Efficient Low-Rank Model Merging in Core Space

Aniello Panariello, Daniel Marczak, Simone Magistri +5

In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as…

cs.LG2025

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses

Stanisław Pawlak, Jan Dubiński, Daniel Marczak +1

Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks. Recent research shows that it is…

cs.LG2025

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

Daniel Marczak, Simone Magistri, Sebastian Cygert +3

Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between…

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

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head

Wojciech Łapacz, Daniel Marczak, Filip Szatkowski +1

Continual learning (CL) has emerged as a critical area in machine learning, enabling neural networks to learn from evolving data distributions while mitigating catastrophic forgett…