Sam Adam-Day (he/him)

AI and Mathematics Researcher at the University of Oxford


I am interested in various topics related to ML/AI, specifically graph machine learning and AI safety. Currently I working 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:


Sep 25, 2023 My paper Zero-One Laws of Graph Neural Networks has been accepted for publication at the NeurIPS Conference.
Sep 18, 2023 I’ve started a new job as a Research Associate in the Department of Computer Science at University of Oxford, advised by Michael Benedikt
Aug 1, 2023 My collaborators and I have written a new paper, The Intermediate Logic of Convex Polyhedra.
Mar 16, 2023 My joint paper Polyhedral completeness of intermediate logics: the Nerve Criterion has been published by the Journal of Symbolic Logic.

Selected Publications

  1. gnn-convergence.png
    Sam Adam-Day, Michael Benedikt, İsmail İlkan Ceylan, and Ben Finkelshtein
  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