1 citations · 1 across the 6 of their papers we have counts for
6 papers
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…
A Practical Guide to Streaming Continual Learning
Andrea Cossu, Federico Giannini, Giacomo Ziffer +5
Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they addr…
Neural Autoencoder-Based Structure-Preserving Model Order Reduction and Control Design for High-Dimensional Physical Systems
Marco Lepri, Davide Bacciu, Cosimo Della Santina
This work concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems. We…
Classifier-free graph diffusion for molecular property targeting
Matteo Ninniri, Marco Podda, Davide Bacciu
This work focuses on the task of property targeting: that is, generating molecules conditioned on target chemical properties to expedite candidate screening for novel drug and mate…
Constraint-Free Structure Learning with Smooth Acyclic Orientations
Riccardo Massidda, Francesco Landolfi, Martina Cinquini +1
The structure learning problem consists of fitting data generated by a Directed Acyclic Graph (DAG) to correctly reconstruct its arcs. In this context, differentiable approaches co…
Learning heuristics for A*
Danilo Numeroso, Davide Bacciu, Petar Veličković
Path finding in graphs is one of the most studied classes of problems in computer science. In this context, search algorithms are often extended with heuristics for a more efficien…