Sam Adam-Day (he/him)

AI and Mathematics Researcher at the University of Oxford

sam-adam-day-profile.jpg

I am interested in various topics related to ML/AI, specifically AI safety and graph machine learning. Currently I am carrying out a joint independent research project investigating multi-agent interaction for generalising trust in AI systems.

Previously I worked as a postdoctoral researcher at the Computer Science Department of the University of Oxford with Michael Benedikt.

You can download my CV here.

Check out my GitHub page.

The following are broadly my current research interests. See also my list of publications.

  • Multi-agent cooperation
  • Graph machine learning
  • Active learning with large language models
  • Logic/set theory

The best way to contact me is by email: [email protected].

News

Sep 1, 2024 I have begun working as an independent researcher on the Neural Interactive Proofs project with Lewis Hammond.
Jun 28, 2024 My joint workshop paper Neural Interactive Proofs will be presented at the ICML 2024 Next Generation of AI Safety Workshop.

Selected Publications

  1. aas-constant-schematic.png
    Sam Adam-Day, Michael Benedikt, İsmail İlkan Ceylan, and Ben Finkelshtein
    2024
    To appear NeurIPS ’24
  2. gcn-zero-one.png
    Sam Adam-Day, Theodor Mihai Iliant, and İsmail İlkan Ceylan
    In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS), 2023
  3. elementary-subdivisions.png
    Sam Adam-Day, Nick Bezhanishvili, David Gabelaia, and Vincenzo Marra
    The Journal of Symbolic Logic, 2022