Diego Calanzone

me.jpg

I am a Research Intern in Deep RL + Biology at MILA Quebec AI Institute under the supervision of Prof. Pierre-Luc Bacon and Pierluca Dā€™Oro. I am a graduate student in Artificial Intelligence Systems from the University of Trento.
My research interests include deep learning reasoning, agency and intersections in applied sciences. I believe in (1) the gains from multi-modality, (2) logic can be structure in a conceptual space, (3) machines shall have a human nature as base. Iā€™m particularly keen on probability theory.

In this web space I share my research in a broad sense, that is the pursuit of understanding about life, society and intelligence (my main field of studies) artificially and naturally. I love blogs seeking for rationality and wisdom [1][2], as well as learning about different ethnicities and cultures (big fan of National Geographic).

news

Oct 16, 2024 Our paper Logically Consistent Language Models via Neuro-Symbolic Integration has been accepted at the System 2 Reasoning At Scale Workshop @ NeurIPS 2024! šŸ„³
Aug 1, 2024 I will serve as tutor and creator for the RL Lab @ M2L Summer School 2024 in Milan! Learning contents to be released soon.
Mar 5, 2024 Our paper Towards Logically Consistent Language Models via Probabilistic Reasoning has been accepted at the ICLR 2024 Workshop on Reliable and Responsible Foundation Models!
Feb 5, 2024 Iā€™m going to talk about ā€œAcquiring Complex Concepts with Comparative Learningā€ in a poster session at the 2024 CORE Project Workshop, Universitat Pompeu Fabra, Barcelona!
Jun 8, 2023 Our paper ā€œAn open source perspective on AI and alignment with the EU AI Actā€ has been accepted to the AI4Safety workshop @ IJCAI 2023!

Publications

  1. Reasoning
    Logically Consistent Language Models via Neuro-Symbolic Integration
    Diego Calanzone,Ā Stefano Teso,Ā andĀ Antonio Vergari
    NeurIPS 2024 Workshop on System 2 Reasoning at Scale
  2. Reasoning
    Towards Logically Consistent Language Models via Probabilistic Reasoning
    Diego Calanzone,Ā Stefano Teso,Ā andĀ Antonio Vergari
    ICLR 2024 Workshop on Reliable and Responsible Foundation Models
  3. AI Policy
    An open source perspective on AI and alignment with the EU AI Act
    Diego Calanzone,Ā Andrea Coppari,Ā Riccardo Tedoldi, and 2 more authors
    AISafety/SafeRL@ IJCAI 2023
Ā© Copyright 2024 Diego Calanzone. Powered by Jekyll. Last updated: October 16, 2024.