Damiano Fornasiere

Artificial Intelligence

Language models recognize dropout and Gaussian noise applied to their activations Damiano Fornasiere^●, Mirko Bronzi^●, Spencer Kitts^●, Alessandro Palmas, Yoshua Bengio, Oliver Richardson. χ2604.17465. Honorable mention at SPAR Demo Day
Efficient safety alignment of language models via latent personality traits Amine Merzouk, Nolan Smyth, Damiano Fornasiere, Linh Le, David Williams-King, Adam Oberman. COLM 2026
Bayesian symbolic regression with entropic reinforcement learning Oussama Boussif, Mohammed Mahfoud, Younesse Kaddar, Moksh Jain, Sida Li, Damiano Fornasiere, Xiaoyin Chen, Yoshua Bengio, Nikolay Malkin. UAI 2026
Can a Bayesian oracle prevent harm from an agent? Yoshua Bengio, Michael K. Cohen, Nikolay Malkin, Matt MacDermott, Damiano Fornasiere, Pietro Greiner, Younesse Kaddar. UAI 2025

Mathematics

Degrees of incompleteness of implicative logics: the trichotomy theorem Damiano Fornasiere, Tommaso Moraschini. To appear at Journal of Symbolic Logic. 2026
Projective unification in bi-intuitionistic logic Damiano Fornasiere, Quentin Gougeon, Miguel Martins. To appear at Review of Symbolic Logic. 2026
Trees and spectra of Heyting algebras Damiano Fornasiere, Tommaso Moraschini. Indagationes Mathematicae. 2025
Frame definability in conditional logic Damiano Fornasiere, Johannes Marti, Giovanni Varricchione. Advances in Modal Logic 2024
Sahlqvist theory for deductive systems Damiano Fornasiere, Tommaso Moraschini. Journal of Symbolic Logic. 2023

Position

The Scientist AI: safe by design, by not desiring Damiano Fornasiere^●, Oliver Richardson^●, Gaël Gendron, Iulian Serban, Yoshua Bengio. LawZero Research. 2026
Chain-of-thought is not explainability Fazl Barez, Tung-Yu Wu, Iván Arcuschin, Michael Lan, Vincent Wang, Noah Siegel, Nicolas Collignon, Clement Neo, Isabelle Lee, Alasdair Paren, Adel Bibi, Robert Trager, Damiano Fornasiere, John Yan, Yanai Elazar, Yoshua Bengio. Preprint. 2025
Can Scientist AI offer a safer path? Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King. χ2502.15657

Preprints

How much is left? LLMs linearly encode their remaining output length Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi, Damiano Fornasiere^○, Adam Oberman^○. χ2607.05316
Safety from honesty in a disinterested AI predictor Yoshua Bengio, Oliver Richardson, Tomáš Gavenčiak, Michael Cohen, Rory Svarc, Damiano Fornasiere, Gaël Gendron, David Hyland, Aton Kamanda, Adam Oberman, Francis Rhys Ward, Anna Gavenčiak, Jacob Livingston Slosser, Vincent Mai, Iulian Serban, Joumana Ghosn. χ2606.29657
Reasoning and learning about injected concepts in language models Samarth Bhargav, Damiano Fornasiere^○, Mirko Bronzi^○.
PyINE: a framework for scalable elicitation and oversight via code execution Pierre-Luc St-Charles, Alessandro Palmas, Damiano Fornasiere, Storm Lei, Mirko Bronzi, Jean-Pierre R. Falet, Iulian Serban, Yoshua Bengio.

Full^● and empty^○ circles denote equivalent contribution and supervision, respectively.