Marco Cusumano-Towner

I am currently a research scientist at Apple working with Vladlen Koltun on autonomous systems and physical intelligence.

I completed my PhD in EECS at MIT, where I was advised by Vikash Mansinghka and Josh Tenenbaum. My PhD research was focused on discovering novel primitives, means of abstraction, and means of composition for probabilistic models and model-based inference and learning algorithms. During my PhD I created the Gen probabilistic programming system. Prior to MIT, I was a technical lead at an early-stage molecular diagnostics startup backed by Sequoia Capital. I completed my MS in computer science at Stanford, where I researched machine learning for genomics. I completed my BS in EECS at UC Berkeley, where I worked with Pieter Abbeel on household robotics. My academic research has been funded by the NSF GRFP and the NDSEG fellowship.

Papers

In submission, 2025

Robust Autonomy Emerges from Self-Play

Marco Cusumano-Towner*, David Hafner*, Alex Hertzberg*, Brody Huval*, Aleksei Petrenko*, Eugene Vinitsky*, Erik Wijmans*, Taylor Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun

ICML 2025

In submission, 2025

Reinforcement Learning for Long-Horizon Interactive LLM Agents

Kevin Chen*, Marco Cusumano-Towner*, Brody Huval*, Aleksei Petrenko*, Jackson Hamburger, Vladlen Koltun, Philipp Krähenbühl

arXiv, 2025

Recursive Monte Carlo and Variational Inference with Auxiliary Variables

Alexander K. Lew, Marco Cusumano-Towner, Vikash K. Mansinghka

UAI 2022

Interval Estimators of Entropy and Information Measures via Inference in Probabilistic Models

Feras A. Saad, Marco Cusumano-Towner, Vikash K. Mansinghka

AISTATS 2022

3DP3: 3D Scene Perception via Probabilistic Programming

Nishad Gothoskar, Marco Cusumano-Towner, Ben Zinberg, Matin Ghavamizadeh, Falk Pollok, Austin Garrett, Joshua B. Tenenbaum, Dan Gutfreund, Vikash K. Mansinghka

NeurIPS 2021

Automating Involutive MCMC using Probabilistic and Differentiable Programming

Marco Cusumano-Towner, Alexander K. Lew, Vikash K. Mansinghka

arXiv 2020

Trace types and denotational semantics for sound programmable inference in probabilistic languages

Alexander K. Lew, Marco Cusumano-Towner, Benjamin Sherman, Michael Carbin, Vikash K. Mansinghka

POPL 2020

Gen: a general-purpose probabilistic programming system with programmable inference

Marco Cusumano-Towner, Feras A. Saad, Alexander K. Lew, Vikash K. Mansinghka

PLDI 2019

Bayesian synthesis of probabilistic programs for automatic data modeling

Feras A. Saad, Marco Cusumano-Towner, Ulrich Schaechtle, Martin C. Rinard, Vikash K. Mansinghka

POPL 2019

Structured differentiable models of 3D scenes via generative scene graphs

Ben Zinberg, Marco Cusumano-Towner, Vikash K. Mansinghka

NeurIPS Workshop 2019

Incremental inference for probabilistic programs

Marco Cusumano-Towner, Benjamin Bichsel, Timon Gehr, Martin T. Vechev, Vikash K. Mansinghka

PLDI 2018

Using probabilistic programs as proposals

Marco Cusumano-Towner, Vikash K. Mansinghka

arXiv 2018

Probabilistic programs for inferring the goals of autonomous agents

Marco Cusumano-Towner, Alexey Radul, David Wingate, Vikash K. Mansinghka

arXiv 2017

A social network of hospital acquired infection built from electronic medical record data

Marco Cusumano-Towner, Daniel Y. Li, Shanshan Tuo, Gomathi Krishnan, David M. Maslove

JAMIA 2013

Bringing clothing into desired configurations with limited perception

Marco Cusumano-Towner, Arjun Singh, Stephen Miller, James F. O’Brien, Pieter Abbeel

ICRA 2011

Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding

Jeremy Maitin-Shepard, Marco Cusumano-Towner, Jinna Lei, Pieter Abbeel

ICRA 2010

Talks

Monte Carlo Semantic Differencing of Probabilistic Programs.

LAFI 2020: Languages for Inference (Co-Located with POPL). New Orleans, LA. 2020.

New programming constructs for probabilistic AI.

Strange Loop. St. Louris, MO. 2019.

Towards Probabilistic Programming for Reliable Machine Perception.

Workshop on Dependable and Secure Software Systems. Zurich, Switzerland. 2019.

Gen: A Flexible System for Programming Probabilistic AI.

The International Conference on Probabilistic Programming (PROBPROG). Cambridge, MA. 2019.

Modular SMC-based inference for probabilistic programs in Gen.jl.

Sequential Monte Carlo Workshop. Uppsala, Sweden. 2017.

Likelihood-Free Bayesian Networks.

BIRS Workshop on Validating and Expanding Approximate Bayesian Computation Methods. Banff, Canada. 2017.

BayesDB: Query the Probable Implications of Data.

Future Programming Workshop at Strange Loop Conference. Pittsburgh. 2017.