Marczak, Daniel

8 publications

NeurIPS 2025 Accurate and Efficient Low-Rank Model Merging in Core Space Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartłomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer

WACV 2025 Exploring the Stability Gap in Continual Learning: The Role of the Classification Head Wojciech Łapacz, Daniel Marczak, Filip Szatkowski, Tomasz Trzciński

ICML 2025 No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost Van De Weijer

ECCV 2024 Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery Grzegorz Rypeść, Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski

ECCV 2024 MagMax: Leveraging Model Merging for Seamless Continual Learning Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert

ECCV 2024 Revisiting Supervision for Continual Representation Learning Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski

NeurIPSW 2023 Revisiting Supervision for Continual Representation Learning Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartłomiej Twardowski

IJCAI 2022 Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning Kamil Deja, Pawel Wawrzynski, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzcinski