Daniel Marczak

According to our database, Daniel Marczak authored at least 15 papers between 2021 and 2025.

Collaborative distances:

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

2025

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

Stanislaw Pawlak, Jan Dubinski, Daniel Marczak, Bartlomiej Twardowski

CoRR, October, 2025

Accurate and Efficient Low-Rank Model Merging in Core Space.

Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartlomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer

CoRR, September, 2025

Variance-Covariance Regularization Improves Continual Learning.

Piotr Hondra, Daniel Marczak, Kamil Deja

IEEE Access, 2025

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

Wojciech Lapacz, Daniel Marczak, Filip Szatkowski, Tomasz Trzcinski

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Parameter-Efficient Interventions for Enhanced Model Merging.

Marcin Osial, Daniel Marczak, Bartosz Zielmski

Proceedings of the 2025 SIAM International Conference on Data Mining, 2025

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

Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Parameter-Efficient Interventions for Enhanced Model Merging.

Marcin Osial, Daniel Marczak, Bartosz Zielinski

CoRR, 2024

Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery.

Grzegorz Rypesc, Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski

Proceedings of the Computer Vision - ECCV 2024, 2024

MAGMAX: Leveraging Model Merging for Seamless Continual Learning.

Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert

Proceedings of the Computer Vision - ECCV 2024, 2024

Revisiting Supervision for Continual Representation Learning.

Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Generalized Continual Category Discovery.

Daniel Marczak, Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski

CoRR, 2023

2022

Logarithmic Continual Learning.

Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski

IEEE Access, 2022

Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning.

Kamil Deja, Pawel Wawrzynski, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzcinski

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

2021

Multiband VAE: Latent Space Partitioning for Knowledge Consolidation in Continual Learning.

Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski

CoRR, 2021

BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning.

Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski

Proceedings of the International Joint Conference on Neural Networks, 2021