Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Matteo Saponati

Matteo Saponati

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Vision×1AI×1

Frequent co-authors

Nicolas Stalder1×
Benjamin F. Grewe1×
Pau Vilimelis Aceituno1×
Tommy He1×
Jerome Sieber1×

Research Timeline

2026
A Predictive Law for On-Policy Self-Distillation From World Feedback

The paper identifies a linear predictive law linking the initial performance gap in on-policy self-distillation (OPSD) to the final performance improvement, allowing researchers to anticipate and tune OPSD outcomes before full training.

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computational overhead compared to state-of-the-art methods.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CVRecentJun 1, 2026

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs

Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati, Pau Vilimelis Aceituno

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…

View →
cs.LGcs.AIRecentMay 28, 2026

A Predictive Law for On-Policy Self-Distillation From World Feedback

Tommy He, Jerome Sieber, Matteo Saponati

The paper identifies a linear predictive law linking the initial performance gap in on-policy self-distillation (OPSD) to the final performance improvement, allowing researchers to anticipate and tune…

View →