Maria Sofia Bucarelli

Orcid: 0009-0007-5101-8242

According to our database1, Maria Sofia Bucarelli authored at least 25 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Select, Label, Evaluate: Active Testing in NLP.
CoRR, March, 2026

Same Answer, Different Representations: Hidden instability in VLMs.
CoRR, February, 2026

2025
PISA: Prioritized Invariant Subgraph Aggregation.
CoRR, November, 2025

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic.
CoRR, November, 2025

On Task Vectors and Gradients.
CoRR, August, 2025

Report on the 2nd Search Futures Workshop at ECIR 2025.
SIGIR Forum, June, 2025

Early-Exit Graph Neural Networks.
CoRR, May, 2025

MASS: MoErging through Adaptive Subspace Selection.
CoRR, April, 2025

The Majority Vote Paradigm Shift: When Popular Meets Optimal.
CoRR, February, 2025

Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design.
Trans. Mach. Learn. Res., 2025

IJCNN 2025 Competition: Learning with Noisy Graph Labels.
Proceedings of the International Joint Conference on Neural Networks, 2025

Link Prediction with Physics-Inspired Graph Neural Networks.
Proceedings of the International Joint Conference on Neural Networks, 2025

ATM: Improving Model Merging by Alternating Tuning and Merging.
Proceedings of the Image Analysis and Processing - ICIAP 2025 Workshops, 2025

Task Singular Vectors: Reducing Task Interference in Model Merging.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
A topological description of loss surfaces based on Betti Numbers.
Neural Networks, 2024

Robustness of Graph Classification: failure modes, causes, and noise-resistant loss in Graph Neural Networks.
CoRR, 2024

∇ τ: Gradient-based and Task-Agnostic machine Unlearning.
CoRR, 2024

Link Prediction under Heterophily: A Physics-Inspired Graph Neural Network Approach.
CoRR, 2024

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity.
Proceedings of the International Joint Conference on Neural Networks, 2024


2023
False Data Injection Impact on High RES Power Systems with Centralized Voltage Regulation Architecture.
Sensors, March, 2023

Combining Distance to Class Centroids and Outlier Discounting for Improved Learning with Noisy Labels.
CoRR, 2023

On Generalization Bounds for Projective Clustering.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks.
Proceedings of the International Joint Conference on Neural Networks, 2022


  Loading...