Maria Sofia Bucarelli — accepted AI-conference papers

2026

MASS: MoErging through Adaptive Subspace Selection

Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo, Maria Sofia Bucarelli, Simone Scardapane, Fabrizio Silvestri +2

ICLR 2026poster

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching the full accuracy of separately fine-tuned endpoints. We pres…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Task Singular Vectors: Reducing Task Interference in Model Merging

Antonio Andrea Gargiulo, Donato Crisostomi, Maria Sofia Bucarelli, Simone Scardapane, Fabrizio Silvestri, Emanuele Rodolà

CVPR 2025poster

Task Arithmetic has emerged as a simple yet effective method to merge models without additional training. However, by treating entire networks as flat parameter vectors, it overlooks key structural information and is susceptible to task interference. In this paper, we study task vectors at the layer…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2023

Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels

Maria Sofia Bucarelli, Lucas Cassano, Federico Siciliano, Amin Mantrach, Fabrizio Silvestri

CVPR 2023poster

In practical settings, classification datasets are obtained through a labelling process that is usually done by humans. Labels can be noisy as they are obtained by aggregating the different individual labels assigned to the same sample by multiple, and possibly disagreeing, annotators. The inter-rat…

Cited by 19 Source ↗PDF ↗Scholar ↗

2023

On Generalization Bounds for Projective Clustering

Maria Sofia Bucarelli, Matilde Fjeldsø Larsen, Chris Schwiegelshohn, Mads Toftrup

NeurIPS 2023poster

Given a set of points, clustering consists of finding a partition of a point set into $k$ clusters such that the center to which a point is assigned is as close as possible. Most commonly, centers are points themselves, which leads to the famous $k$-median and $k$-means objectives. One may also choo…

Cited by 4 Source ↗PDF ↗Scholar ↗