Hey, I’m Leonardo!

I'm a CS Ph.D. student at the University of Southern California, advised by Prof. Emilio Ferrara.
I study learned representations and internal mechanisms in AI systems to understand and control behavior, with a focus on human modeling and trustworthiness.
Specifically, I'm most interested in:

1. LLM-based human modeling, personalization, and psychometrics.
2. Safety, fairness, bias, alignment, and responsible AI.
3. Representation engineering and interpretability.
4. Computational social science.

I also study online social dynamics, particularly on Telegram.

Feel free to reach out!