Justin Cosentino

📍 Toronto || Beijing || San Francisco
✉️ name.first at name.last dot io


I’m a second-year Master’s candidate studying Computer Science at Tsinghua University. I’m supervised by Professor Jun Zhu in the Tsinghua Statistical Artificial Intelligence and Learning Group. I’m currently a research intern in Uber’s Advanced Technologies Group under the supervision of Professor Raquel Urtasun. This past summer I interned with the Google Brain Genomics team.

Previously, I was a Senior Software Engineer working on Search at Salesforce. I studied Computer Science at Swarthmore College.

I enjoy drinking too much coffee and playing (subpar) blitz and bullet chess. Before some knee injuries, I was an avid downhill skier, distance runner, and lacrosse player.

Research Interests


Generative Well-intentioned Networks
A novel framework for leveraging uncertainty and rejection-based classifiers.
Justin Cosentino and Jun Zhu.
Neural Information Processing Systems (NeurIPS), 2019.
[ paper ] [ poster ] [ slides ] [ bibtex ] 

The Search for Sparse, Robust Neural Networks
Showing that winning Lottery Tickets account for the robustness of a network.
{Justin Cosentino, Federico Zaiter}, and {Dan Pei, Jun Zhu}
Safety and Robustness in Decision Making Workshop @ Neural Information Processing Systems (NeurIPS), 2019.
[ paper ] [ poster ] [ code ] [ bibtex ] 

Last updated in January, 2020.