Andrew D. Bagdanov

Accurate and Efficient Low-Rank Model Merging in Core Space

arXiv 2025

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

arXiv 2025

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

arXiv 2025

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning

arXiv 2024

A Benchmark Environment for Offline Reinforcement Learning in Racing Games

arXiv 2024

Masked Autoencoders are Efficient Class Incremental Learners

ICCV 2023 1

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

arXiv 2022

Joost Van de Weijer

Simone Magistri

Bartłomiej Twardowski

Daniel Marczak

Alberto Baldrati

Albin Soutif--Cormerais

Alessandro Sestini

Angelo Porrello

Aniello Panariello

Claudio Cusano