New York City Metropolitan Area
I’m a machine learning researcher with a PhD in cognitive science and AI from NYU Center for Data Science, advised by Brenden Lake and Todd Gureckis. My dissertation offered theoretical, empirical, and computational advances in the study of goals: how do we represent, reason about, and come up with them? My recent work follows it to study task representations in large language models using mechanistic interpretability tools (as a visiting researcher at Meta FAIR with Adina Williams). In my non-academic life, I live with my wife Sarah, and our dog Lila, and spend time making homemade hot sauces, playing board games, and lifting weights.
Machine Learning Researcher.
Visiting researcher at Meta's Fundamental AI Research group on the Alignment team.
Developed methods inspired by the cognitive psychology concept of task-sets (abstract task representations) to analyze and predict behavior in a large-scale gameplay dataset in a multiplayer game. Initial results highlighted consistent differences between players by their propensity to flee or attack in fight-or-flight scenarios. Mentored by Ida Momennejad and Harm van Seijen.
Joined the Niv Lab , headed by Dr. Yael Niv , to investigate attention functions in human reinforcement learning in multidimensional environments. Modeled data from previous experiments, making discoveries regarding the roles of attention and decay, and the efficacy of eye-tracking and fMRI-based attention measures. Currently drafting a manuscript for publication. Implemented a reinforcement learning experiment in a flexible web platform, enabling data collection using Amazon Mechanical Turk. Developed a simulation environment for momentum-endowed agents on bandit problems to motivate work framing mood as a momentum variable.