Published several papers including 'Bayes3D: fast learning and inference in structured generative models of 3D objects and scenes', '3DP3: 3D Scene Perception via Probabilistic Programs', 'Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps', 'DURableVS: Data-efficient Unsupervised Recalibrating Visual Servoing via online learning in a structured generative model'.
Research Experience
SWE Intern at Google (2016), Software Engineer at Uber ATG (2017-2018), Research Engineer at Vicarious AI (2018-2020), Graduate Student at MIT (2020-2025), Co-founder at Stealth Startup (2025-present).
Education
PhD in Computer Science from MIT, advised by Vikash Mansinghka and Josh Tenenbaum, 2020-2025.
Background
Currently at a stealth startup, working on using probabilistic programming to scale up 3D perception. The goal is to build AI vision systems that can learn as rapidly and generalize as broadly as humans.