Daniel Marczak

6 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ECCV (3) ICML (1) IJCAI (1) WACV (1)

Top co-authors

Tomasz Trzcinski (5) Sebastian Cygert (4) Bartlomiej Twardowski (3) Kamil Deja (1) Simone Magistri (1) Wojciech Łapacz (1) Filip Szatkowski (1) Paweł Wawrzyński (1) Grzegorz Rypeść (1) Andrew D. Bagdanov (1)

Research topics

Artificial Intelligence (3) Deep Learning (3) Machine Learning (3) Core AI (3) Architectures (2) Learning Types · Machine Learning (2) Application Areas (1) Core Methods (1) Learning Types · Deep Learning (1) Models (1) Techniques (1)

Keywords

continual learning (3) pre-trained model (2) model merging (2) catastrophic forgetting (2) knowledge integration (1) knowledge consolidation (1) latent space alignment (1) generative continual learning (1) large language model (1) task-specific model (1) stability gap (1) weight selection (1) common subspace (1) singular value spectrum (1) representation learning (1) task-specific subspaces (1) knowledge transfer (1) classification head (1) variational autoencoder (1)

Papers

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head WACV 2025 No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces ICML 2025 Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery ECCV 2024 MagMax: Leveraging Model Merging for Seamless Continual Learning ECCV 2024 Revisiting Supervision for Continual Representation Learning ECCV 2024 Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning IJCAI 2022