Anthony Baez

Welcome to my website! I am an MEng student at MIT studying Artificial Intelligence and Decision Making, where I work in the Cyborg Psychology group under Prof. Pat Pataranutaporn in the Media Lab. I am also a recipient of the NSF Graduate Research Fellowship.

My research interests lie in mechanistic interpretability for improving our understanding and safety of LLMs. I also am interested in applying mechanistic interpretability to create interfaces for better monitoring and controlling AI for both technical and non-technical users.

Outside of work, I enjoy traveling, and learning other languages, hiking, videogames, and everything science fiction.

Email - CV - LinkedIn - Google Scholar - Github

Anthony Baez – MIT MEng student and AI researcher

Selected Works

Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
Sheer Karny*, Anthony Baez*, and Pat Pataranutaporn
*Equal Contribution
Under Review

Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
Sheer Karny*, Anthony Baez*, and Pat Pataranutaporn
*Equal Contribution
ACM Conference on Intelligent User Interfaces 2026
Code

Guaranteeing Conservation of Integrals in Physics-Informed Neural Networks
Anthony Baez, Wang Zhang, Ziwen Ma, Subhro Das, Lam M Nguyen, and Luca Daniel
Arxiv Preprint
Code