Welcome to the website for the Social Cognitive AI (SCAI) Lab at Johns Hopkins University. The lab is led by Dr. Tianmin Shu. Our 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. We work at the intersection of Embodied AI, Machine Learning, and Computational Social Cognition.
Research Highlights view all
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
ComposeCL: Continual Learning Mechanisms Compose for Long-Horizon Memorization
MindZero: Learning Online Mental Reasoning With Zero Annotations
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
MMToM-QA: Multimodal Theory of Mind Question Answering
MindZero: Learning Online Mental Reasoning With Zero Annotations
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
MMToM-QA: Multimodal Theory of Mind Question Answering