Hey There! I'm Frank.

I'm currently a contract researcher with Google DeepMind working on AGI Safety & Alignment. Previously, I was a MATS scholar, worked with the Perona Lab on diffusion models, and Goodfire on mechanistic interpretability. I also went to Caltech, where I am on leave from right now.

I'm very excited about machine learning! I think that artificial intelligence has incredible potential to help humanity and we ought to build it with this in mind. To this end, I'm broadly interested in alignment, post-training, and diffusion models.

Please feel free to reach out via email. I'm always interested in meeting new people and any paper recommendations you might have!