Giacomo Capitani
4 papers · 2024–2025 · 3 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
Venues
Top co-authors
Research topics
Keywords
continual learning
(1)
catastrophic forgetting
(1)
algorithmic fairness
(1)
cluster analysis
(1)
self-supervised learning
(1)
transformer
(1)
empirical risk minimization
(1)
spurious correlation
(1)
replay buffer
(1)
attention head
(1)
task vector
(1)
deep network
(1)
weight permutation
(1)
bias removal
(1)
spectral theory
(1)
model re-basin
(1)
Papers
Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations
WACV 2025
U-Net Transplant: The Role of Pre-training for Model Merging in 3D Medical Segmentation
MICCAI 2025
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
ICML 2025
ClusterFix: A Cluster-Based Debiasing Approach Without Protected-Group Supervision
WACV 2024