3 papers
cs.CV2026
Restoring Without Forgetting: Continual Learning Across Image Degradations
Alif Ashrafee, Bartosz Krawczyk
Recent progress in image restoration has converged on all-in-one architectures that jointly handle multiple degradations within a single network. These methods are effective on sta…
cs.LG2026
Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment
Alif Ashrafee, Jedrzej Kozal, Michal Wozniak +1
Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of p…
cs.LG2025
What is the role of memorization in Continual Learning?
JÄdrzej Kozal, Jan Wasilewski, Alif Ashrafee +2
Memorization impacts the performance of deep learning algorithms. Prior works have studied memorization primarily in the context of generalization and privacy. This work studies th…