Tianmin Shu


I am Tianmin Shu. I received my Ph.D. in Statistics from University of California, Los Angeles under the supervision of Prof. Song-Chun Zhu. My research interests are social scene understanding, social perception, and multi-agent imitation and reinforcement learning. I have interned at Facebook AI Research working with Dr. Yuandong Tian, and at Salesforce Research (MetaMind) working with Dr. Caiming Xiong and Dr. Richard Socher. I have also closely worked with Prof. Hongjing Lu, Prof. Ying Nian Wu, Prof. Sinisa Todorovic, and Prof. Michael S. Ryoo.

Google Scholar Profile

Thesis

News

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.

08/2017: Invitated talk at ONR MURI meeting, UCLA.

07/2017: Invitated talk at 3rd Vision Meets Cognition Workshop in conjunction with CVPR 2017, Honolulu, HI.

06/2017: I started a deep learning research intenrship at Salesforce Research (MetaMind). I have written a blog based on my internship project.

06/2017: Our CogSci 2017 paper received Computational Modeling Prize in Perception and Action.

04/2017: Our ICRA 2017 work on human-robot interactions was covered by New Scientist .  

Reseach Highlights

Social Scene Understanding

Multi-agent Imitation and Reinforcement Learning

Social Perception