I recently completed my PhD in Computational Cognitive Science at MIT, supervised by Josh Tenenbaum. I spent the first three years mostly developing Bayesian machine learning methods for explainable AI, then the next three years studying attitude formation, political persuasion, and basically how to elect Democrats.

lhewitt@protonmail.com  |  LinkedIn  |  Google Scholar   

Papers

Hybrid memoised wake-sleep: paper (ICLR 2022)
Le et al.

Persistence of party cues: paper (JEPS 2021)
Tappin and Hewitt

DreamCoder: paper (PLDI 2021)
Ellis et al.

Memoised wake-sleep: paper (UAI 2020)
Hewitt, Le, Tenenbaum

SketchAdapt: paper (ICML 2019)
Nye, Hewitt, Tenenbaum, Solar-Lezama

Inferring Structured Visual Concepts from Minimal Data: paper (CogSci 2019)
Qian, Hewitt, Tenenbaum, Levy

Variational Homoencoder: GitHub,  paper,  oral presentation (UAI 2018)
Hewitt, Nye, Gane, Jaakkola, Tenenbaum

Bayesian Auditory Scene Analysis: website,  paper,  oral presentation (CogSci 2018)
Cusimano, Hewitt, Tenenbaum, McDermott

( Figure from Memoised wake-sleep, UAI 2020 )