collaborators

11 papers

cs.LG2026

What changes after deployment? A survey on On-device Learning in TinyML

Massimo Pavan, Luca Pezzarossa, Fabrizio Pittorino +2

Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static models. On-device learning (OD…

cs.LG2026

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transit…

cs.LG2026

Active In-Context Learning for Tabular Foundation Models

Wilailuck Treerath, Fabrizio Pittorino

Active learning (AL) reduces labeling cost by querying informative samples, but in tabular settings its cold-start gains are often limited because uncertainty estimates are unrelia…

cs.LG2026

Architecture-Aware Minimization (AM): How to Find Flat Minima in Neural Architecture Search

Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Neural Architecture Search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neura…

cs.CL2026

EmbBERT: Attention Under 2 MB Memory

Riccardo Bravin, Massimo Pavan, Hazem Hesham Yousef Shalby +2

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. Howev…

cs.LG2026

BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training

Luca Colombo, Fabrizio Pittorino, Daniele Zambon +3

Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy…