Get started
Author

Damiano Fornasiere

Observed name: Fornasiere, Damiano
Institution: McGill University
OpenAlex ID: A5134098489
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
2025 · Yoshua Bengio, Michael Cohen, et al. · SuperIntelligence - Robotics - Safety & Alignment · 14
PDF
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
2025 · Bengio, Yoshua, Cohen, Michael, et al. · arXiv (Cornell University) · 3
PDF
Can a Bayesian Oracle Prevent Harm from an Agent?
2025 · Yoshua Bengio, Matt McDermott, et al. · SuperIntelligence - Robotics - Safety & Alignment · 1
PDF
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
2026 · Baldelli, Davide, Kozierok, Robyn, et al. · arXiv (Cornell University)
PDF
PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution
2026 · St-Charles, Pierre-Luc, Palmas, Alessandro, et al. · arXiv (Cornell University)
PDF
Bayesian Symbolic Regression with Entropic Reinforcement Learning
2026 · Boussif, Oussama, Mahfoud, Mohammed, et al. · arXiv (Cornell University)
PDF
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026 · Merzouk, Mohamed Amine, Smyth, Nolan, et al. · arXiv (Cornell University)
PDF
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
2026 · Merzouk, Mohamed Amine, Carpov, Dmitri, et al. · arXiv (Cornell University)
PDF
Safety from Honesty in a Disinterested AI Predictor
2026 · Bengio, Yoshua, Richardson, Oliver, et al. · arXiv (Cornell University)
PDF
Language models recognize dropout and Gaussian noise applied to their activations
2026 · Fornasiere, Damiano, Bronzi, Mirko, et al. · arXiv (Cornell University)
PDF
Projective Unification in Bi-Intuitionistic Logic
2025 · Fornasiere, Damiano, Gougeon, Quentin, et al. · HAL
PDF
Embedding concrete spaces into positive topologies
2019 · Damiano Fornasiere
Works count: 12
Citation count: 18
H-index: 2
I10-index: 1
Year
Topic
Type