Daniel Marczak

21 papers A* 2A 2B 1Journal 13Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
Accurate and Efficient Low-Rank Model Merging in Core Space.
CoRR
Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartlomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer
2025 J jnl
Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses.
CoRR
Stanislaw Pawlak, Jan Dubinski, Daniel Marczak, Bartlomiej Twardowski
2025 A conf
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head.
WACV
Wojciech Lapacz, Daniel Marczak, Filip Szatkowski, Tomasz Trzcinski
2025 A* conf
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces.
ICML
Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2025 J jnl
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces.
CoRR
Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2025 A conf
Parameter-Efficient Interventions for Enhanced Model Merging.
SDM
Marcin Osial, Daniel Marczak, Bartosz Zielmski
2025 J jnl
Variance-Covariance Regularization Improves Continual Learning.
IEEE Access
Piotr Hondra, Daniel Marczak, Kamil Deja
2024 — conf
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery.
ECCV (11)
Grzegorz Rypesc, Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2024 J jnl
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head.
CoRR
Wojciech Lapacz, Daniel Marczak, Filip Szatkowski, Tomasz Trzcinski
2024 — conf
MAGMAX: Leveraging Model Merging for Seamless Continual Learning.
ECCV (85)
Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
2024 J jnl
MagMax: Leveraging Model Merging for Seamless Continual Learning.
CoRR
Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
2024 J jnl
Parameter-Efficient Interventions for Enhanced Model Merging.
CoRR
Marcin Osial, Daniel Marczak, Bartosz Zielinski
2024 — conf
Revisiting Supervision for Continual Representation Learning.
ECCV (6)
Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2023 J jnl
Generalized Continual Category Discovery.
CoRR
Daniel Marczak, Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2023 J jnl
Revisiting Supervision for Continual Representation Learning.
CoRR
Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2022 J jnl
Logarithmic Continual Learning.
IEEE Access
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
2022 J jnl
Logarithmic Continual Learning.
CoRR
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
2022 A* conf
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning.
IJCAI
Kamil Deja, Pawel Wawrzynski, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzcinski
2021 B conf
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning.
IJCNN
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
2021 J jnl
Multiband VAE: Latent Space Partitioning for Knowledge Consolidation in Continual Learning.
CoRR
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
2020 J jnl
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning.
CoRR
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski