3 papers
cs.LG2025
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli +6
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g.,…
cs.CV2025
CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
David Méndez, Gianpaolo Bontempo, Elisa Ficarra +2
Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts a…
cs.CV2024
Taming Mambas for Voxel Level 3D Medical Image Segmentation
Luca Lumetti, Vittorio Pipoli, Kevin Marchesini +3
Recently, the field of 3D medical segmentation has been dominated by deep learning models employing Convolutional Neural Networks (CNNs) and Transformer-based architectures, each w…