Photo of Marco Cusumano-Towner

Marco Cusumano-Towner

Email / GitHub / Google Scholar

Computer scientist working at the intersection of probabilistic inference, systems, 3D perception, and human-understanding


I recently completed my PhD in EECS at MIT, advised by Vikash Mansinghka and Josh Tenenbaum. During my PhD I created the Gen probabilistic programming system. Before MIT, I was an early member and lead at a molecular diagnostics startup, a Master’s student at Stanford University, and an undergraduate student in computer science at UC Berkeley, where I worked with Pieter Abbeel on probabilistic robotics. My graduate school research has been funded by the NSF graduate research fellowship and the NDSEG graduate fellowship program, among other sources.


PhD Thesis

Gen: A High-Level Programming Platform for Probabilistic Inference (PDF), PhD thesis, Massachusetts Institute of Technology, 2020.


Publications


Gothoskar, Cusumano-Towner, Zinberg, Ghavamizadeh, Pollok, Garrett, Gutfreund, Tenenbaum, Mansinghka
Accepted to NeurIPS 2021
Lew, Cusumano-Towner, Sherman, Carbin, Mansinghka.
47th ACM SIGPLAN Symposium on Principles of Programming Languages (POPL 2020)
Cusumano-Towner, Saad, Lew, Mansinghka.
40th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2019)
Saad, Cusumano-Towner, Schaechtle, Rinard, Mansinghka
46th ACM SIGPLAN Symposium on Principles of Programming Languages (POPL 2019)
Zinberg, Cusumano-Towner, Mansinghka
NeurIPS 2019 Workshop on Perception as Generative Reasoning.
Cusumano-Towner, Bichsel, Gehr, Vechev, Mansinghka
39th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2018)
Cusumano-Towner, Mansinghka
arXiv 2018
Cusumano-Towner, Mansinghka
Thirty-first Conference on Neural Information Processing Systems (NeurIPS 2017)
Cusumano-Towner, Radul, Wingate, Mansinghka
arXiv 2017
Cusumano-Towner, Li, Tuo, Krishnan, Maslove
Journal of the American Medical Informatics Association. 2013.
Cusumano-Towner, Singh, Miller, O'Brien, Abbeel
2011 IEEE International Conference on Robotics and Automation (ICRA 2011)
Maitin-Shepard, Cusumano-Towner, Lei, Abbeel
2010 IEEE International Conference on Robotics and Automation (ICRA 2010)

News

October 2021
We submitted two papers to AISTATS.

September 2021
Our paper, '3DPD: Scene Perception via Probabilistic Programming', which applies Gen to infer scene graphs from RGBD images, was accepted to NeurIPS.

May 2021
We submitted two papers to NeurIPS this year.

August 2020
I submitted the final version of my PhD thesis!

July 2020
I have new a paper on arXiv describing how Gen automates the low-level implementation of a flexible class of inference algorithms called involutive MCMC.

May 2020
I succesfully defended my thesis!

December 2019

October 2019

October 2019

September 2019
I gave a talk on probabilistic programming at the Strange Loop conference in St. Louis.

July 2019

June 2019
I presented our paper on Gen at PLDI (short video abstract here).

February 2019
I completed my EECS Research Qualifying Exam

January 2019
I co-taught an MIT IAP class on probabilistic programming in Gen.

January 2019
Feras Saad presented our paper on Bayesian program synthesis at POPL.

October 2018
Gave a talk on Gen at the first PROBPROG conference (video).

September 2018
First release of Gen.