1 citations · 1 across the 7 of their papers we have counts for
8 papers · 1 filter
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…
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…
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…
MagMax: Leveraging Model Merging for Seamless Continual Learning
Daniel Marczak, Bartłomiej Twardowski, Tomasz Trzciński +1
This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forget…
Revisiting Supervision for Continual Representation Learning
Daniel Marczak, Sebastian Cygert, Tomasz Trzciński +1
In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing in…
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert +2
Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend…