Aton Kamanda

Research engineer, LawZero · Montréal

I have been working as a research engineer in machine learning for the last three years. I currently work as a research engineer for the Scientist AI plan led by Yoshua Bengio. My focus is technical AI safety.

Publications
  1. Safety from Honesty in a Disinterested AI Predictor
    Y. Bengio, O. Richardson, T. Gavenčiak, M. Cohen, …, A. Kamanda, A. Oberman, …, J. Ghosn · arXiv 2026
  2. Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
    L. Le, D. Williams-King, M. A. Merzouk, A. Kamanda, A. Oberman · ICLR 2026 Workshop
  3. CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning LLMs to Coding Preferences
    M. Weyssow, A. Kamanda, X. Zhou, H. Sahraoui · ACM 2026

Contact