2 papers
cs.LG2025
GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging
Eric Nuertey Coleman, Irene Testa, Luigi Quarantiello +3
The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich representations lear…
cs.LG2025
Parameter-Efficient Continual Fine-Tuning: A Survey
Eric Nuertey Coleman, Luigi Quarantiello, Ziyue Liu +4
The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance. However, these models inherit a fu…