Author

D. Bacciu

h-index 27 View on Semantic Scholar

We have 5 of 218 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Oct 2026

Oscillatory Neural Dynamics over Sheaves

Effective long-range propagation remains a central challenge in graph neural networks, as increasing a model's propagation depth does not guarantee that distant nodes effectively influence each other. Sheaf neural networks enrich graph propagation through matrix-valued transport between stalks; still, this expressivity...

J. Van Looy, Alessandro Trenta, Alessio Gravina et al. · arXiv (Cornell University) · 0 citations

#artificial intelligence Preprint Sep 2026

Identifying ODEs from Unstructured Data with Causal Representation Learning

We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Cau...

Alessandro Trenta, Riccardo Massidda, D. Bacciu et al. · 0 citations

#natural language process... Preprint Sep 2026

Likelihood Ranking doesn't Scale Like Prompting in LLMs

LLM evaluation is commonly performed either by prompting models to produce answers or by scoring candidate outputs with likelihood-based metrics. In multiple-choice QA, however, standard likelihood-based scoring is still conditioned on the question and answer set, and can therefore leverage the same task-conditioned an...

Alessandro Bondielli, Lucia C. Passaro, D. Bacciu et al. · 0 citations

Open access Jul 2026

Deep Learning for Space Debris Tracking: One-Step Tracklet Filtering with a Hybrid GRU-CNN Architecture

A hybrid deep learning framework for learned one-step tracklet filtering of radar measurements that achieves lower filtering error and improved robustness under severe non-Gaussian disturbances, compared with EKF- and UKF-based analytical baselines.

A. Cabras, Niccolò Pilloni, Victor Mustieles-Pérez et al. · AI Sensors · 0 citations

Preprint Aug 2026

Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures

This work proposes Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification, and achieves the best performance while maintaining low and scalable computational cost among weight-space detectors.

Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni et al. · 0 citations