← Search

Riccardo Salami

2 accepted papers

2026

Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature

ICLR 2026poster

Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors;…

Cited by 0SourceScholar
2025

Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

ICLR 2025poster

Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving performance and scalability. In this respect, the compositional properties of low-rank adaptation techniques (e.g., LoRA) have proven beneficial, as s…