Welcome to the Social Cognitive AI (SCAI, pronounced “sky”) Lab at Johns Hopkins University. The lab is led by Dr. Tianmin Shu. We study machine social intelligence: building AI agents that can understand, reason about, and interact with humans and other agents in complex, open-ended environments. We are particularly interested in agents that learn from embodied and social experiences, build models of the world and other minds, and cooperate with humans and machines over long horizons.
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