About
Hey there! I’m Vitoria, a Ph.D. student at the University of Pennsylvania. I work in the Brachio Lab 🦕 under the supervision of Professor Eric Wong. My research focuses on theory-grounded mechanistic interpretability of large language models, along with broader topics in trustworthy ML.
I earned my Master of Science in Mathematical Modelling in 2023 and my Bachelor of Science in Applied Mathematics in 2020 from the School of Applied Mathematics at Fundação Getulio Vargas. During my studies, I was part of the Visual Data Science Lab and worked with Professors Jorge Poco and Marcos M. Raimundo. My research focused on machine learning, multi-objective optimization, and fairness in ML.
After my master’s, I worked as a research scientist at the Visualization and Data Analytics Research Center at New York University with Professor Claudio Silva. At NYU, I focused on visualization systems for Explainable AI and topological data analysis, developing tools to help interpret complex ML models.
Thanks for stopping by!
Interests
- Mechanistic Interpretability
- Explainable AI
- Trustworthy ML
- Optimization
Fun facts
- 🇧🇷 I’m Brazilian
- 🏎️ I never miss a Formula 1 race (forza Ferrari!)
- 🧵 I spend way too much time cross stitching (basically pixel art made with fabric and thread)
- 📚 On a lifelong quest to read a book from every country, currently making my way through South America. Send me your suggestions!
Last update: Jul 23, 2026