Davide Scassola

I’m a PhD student at the University of Trieste in collaboration with AINDO. My research focuses on generative models, in particular for tabular and relational data. I’m also interested in Bayesian methods, causality and probabilistic machine learning in general.

selected publications

AAAI

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints

Davide Scassola, Sebastiano Saccani, Ginevra Carbone, and 1 more author

In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

Bib

@inproceedings{scassola2025zero,
  title = {Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints},
  author = {Scassola, Davide and Saccani, Sebastiano and Carbone, Ginevra and Bortolussi, Luca},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {39},
  number = {19},
  pages = {20302--20309},
  year = {2025},
}

arXiv

Graph Conditional Flow Matching for Relational Data Generation

Davide Scassola, Sebastiano Saccani, and Luca Bortolussi

arXiv preprint arXiv:2505.15668, 2025

Bib

@article{scassola2025graph,
  title = {Graph Conditional Flow Matching for Relational Data Generation},
  author = {Scassola, Davide and Saccani, Sebastiano and Bortolussi, Luca},
  journal = {arXiv preprint arXiv:2505.15668},
  year = {2025},
}

Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading

Federico Cornalba, Constantin Disselkamp, Davide Scassola, and 1 more author

Neural Computing and Applications, 2024

Bib

@article{cornalba2024multi,
  title = {Multi-objective reward generalization: improving performance of Deep Reinforcement Learning for applications in single-asset trading},
  author = {Cornalba, Federico and Disselkamp, Constantin and Scassola, Davide and Helf, Christopher},
  journal = {Neural Computing and Applications},
  volume = {36},
  number = {2},
  pages = {619--637},
  year = {2024},
  publisher = {Springer},
}