Research Fellow
Theoretical Physics, University of Oxford
UKRI Horizon Europe Guarantee Marie Skłodowska-Curie Fellowship Award
Project: Phenomenology of Deep Learning
News
-
9-15 December: I'm attending NeurIPS'24 in Vancouver. Feel free to reach out if you'd like to meet up and chat!
-
19 November: I will participate in the Physics for AI and AI for Physics: Landscaping Workshop at the Institute of Physics, London.
-
1 November: I'm giving a talk at the AI Security Reading Group, Mathematical Institute, University of Oxford.
-
28-29 October: I'm attending the 'Beyond the symbols vs signals debate' meeting at The Royal Society (London).
-
September: Our paper, An exactly solvable model for emergence and scaling laws, was accepted at NeurIPS 2024!
-
March-June: I'm participating in the AI Alignment Course run by BlueDot Impact. Please feel free to reach out if you'd like to exchange ideas or explore potential collaborations!
RESEARCH
ABOUT ME
I'm a Research Fellow at Oxford Theoretical Physics, where I'm exploring the interplay between Machine Learning and Physics. I'm hosted at Ard Louis group. Before Oxford, I worked as a Research Scientist at IBM Research UK. Previously, I was at ICTP in Trieste, DESY Theory Group in Hamburg, CTP at MIT, University of São Paulo, and University of Campinas.
For more details, please see my [CV].
I am a physicist seeking ways to understand generalization in deep learning. Toward this goal, I study AI as a scientific discipline, where both empirical validity and explainable methodologies are essential. For instance, see [here] for our work on emergence and scaling laws and [here] for our work on double descent and online/offline correspondence in similarity learning.
Previously, I explored the construction of models to explain small- and large-scale phenomena in the universe. I worked on the interplay between particle physics and cosmology, learning from the early universe how to build and interpret our models of particle physics. See [here] for all publications.