collaborators

5 papers

cs.LG2026

Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures

Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni +3

Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a significant attack surface, as ma…

cs.LG2026

Position: Modular Memory is the Key to Continual Learning Agents

Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21

Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…

cs.LG2025

CLA: Latent Alignment for Online Continual Self-Supervised Learning

Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa +2

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, wher…

cs.LG2025

Continual Learning Should Move Beyond Incremental Classification

Rupert Mitchell, Antonio Alliegro, Raffaello Camoriano +17

Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental cl…

cs.LG2025

Replay-free Online Continual Learning with Self-Supervised MultiPatches

Giacomo Cignoni, Andrea Cossu, Alex Gomez-Villa +2

Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However…