I am the director of the Social Cognitive AI (SCAI) Lab and an Assistant Professor in the Department of Computer Science at Johns Hopkins University. I also hold a joint appointment with the Deparment of Cognitive Science. My research goal is to advance human-centered AI by engineering machine social intelligence to build socially intelligent systems that can understand, reason about, and interact with humans in real-world settings. I approach this from an interdisciplinary perspective, connecting machine learning, computer vision, robotics, and social cognition to study machine social intelligence. Before joining JHU, I was a Research Scientist at MIT working with Josh Tenenbaum and Antonio Torralba.
Office: Malone Hall 213   Email: tianmin.shu [at] jhu.edu
08/2024: Our work on MMToM-QA received the Outstanding Paper Award at ACL 2024.
07/2024: Co-organized RSS Workshop on Social Intelligence in Humans and Robots.
07/2024: Invited talk at Utrecht University.
05/2024: Invited talk in the Measurement Errors and Latent Variables Workshop.
04/2024: Guest lecture for EECS 692: Advanced Artificial Intelligence at UMich.
12/2023: NeurIPS 2023 Tutorial on Language Models Meet World Models.
07/2023: Our work on test-time policy diagnosis & adaptation was covered by MIT News.
07/2023: Invited talk in the Cognitive-AI Benchmarking workshop at CogSci 2023.
07/2023: Co-organized RSS Workshop on Social Intelligence in Humans and Robots.
03/2023: Invited talk in the Social Cognitive Neuroscience Lab at the University of Iowa.