Check here our recent #ICML2024 paper on mechanistic interpretability!
Check here our recent #ICML2024 paper on mechanistic interpretability!
Hi! Thanks for visiting my website. My name is Víctor Samuel Pérez Díaz.
I am a PhD Student at NYU Courant Institute of Mathematical Sciences, working with David Fouhey.
My research focuses on leveraging artificial intelligence (AI) for scientific discovery. I have primarily worked in the intersection of machine learning and (astro)physics. I am interested in foundation models for science, interpretability, and robustness.
Previously, I served positions at the Center for Astrophysics l Harvard & Smithsonian, NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI), Harvard John A. Paulson School of Engineering and Applied Sciences, and Universidad del Rosario (Colombia). Currently, I am a member of CILVR and AstroAI groups. I hold my B.Sc. in Applied Mathematics and Computer Science from Universidad del Rosario.