Tianmin Shu

Tianmin Shu

I am a postdoc at MIT advised by Josh Tenenbaum and Antonio Torralba. I work on social perception and multi-agent systems. In particular, I am interested in building computational models that have human-like abilities to reason about the mental states of others and applying those abilities to multi-agent systems to solve problems such as human-AI collaboration. I received my Ph.D. in Statistics from University of California, Los Angeles under the supervision of Song-Chun Zhu, and have interned at Facebook AI Research and Salesforce Research.

Email: tshu [at] mit.edu

Google Scholar / Thesis


09/2019: Invitated talk at ONR MURI meeting, Edinburgh.

05/2019: Our work on interpretable and hierarchical reinforcement learning was covered by Science News.   

03/2019: Our work on building a 3D virtual environment VRKitchen was covered by Tech Xplore.   

11/2018: Invitated talk in Cognitive Learning for Vision and Robotics Lab, USC.

09/2018: Invitated talk at ONR MURI meeting, White Mountain, NH.

06/2018: I started a research internship at Facebook AI Research.

Reseach Highlights

Social Scene Understanding

Human-AI Collaboration

Social Perception

Multi-agent Imitation and Reinforcement Learning