Biography

I am a PhD candidate at the Center for Automated Reasoning at Stanford University, under the guidance of Prof. Clark Barrett. My research focuses on improving the prosocial tendencies of language models (LMs) through a series of unique developmental approaches. This includes the introduction of communication channels during autoregressive training (akin to a kindergarten setting), allowing a parent LM to guide a child LM by curating its training data, and enhancing human feedback on LMs via a combined embedding of EEG data and speech.

During my PhD journey, my focus has evolved from formal verification and programming languages to AI alignment, prompted by my belief that robust AI represents a substantial existential threat to humanity. Prior to this, I majored in computer science and electrical engineering at MIT, contributing to AI and robotics research. After MIT, I explored interactive theorem proving at CMU with Simon Dedeo. During this period, I published research on the application of abduction in mathematics in the Cognition journal. I am currently in the 4th year of my PhD, where I have engaged in various projects related to SMT solving and interactive theorem proving. I have also probed into ontology mapping as a technique for targeted neural network interpretability.

My primary character trait is curiosity, and I really love math.