Research

While recent advances in machine/deep learning, computer vision, natural language processing, and wearable sensing have enabled remarkable data-driven perception of human behaviors, machine social intelligence and its integration in human life remains an open challenge. True social intelligence involves more than just data processing and pattern recognition. It requires a deep understanding of social norms, cultural context, and the subtleties of human interaction. Machines must learn to navigate complex social situations, interpret ambiguous signals, and adapt to the dynamic nature of human relationships. To this end,  we develop approaches and solutions that are human-centric and reality-centric, where we ask the following questions: 

How can artificial intelligence systems

I. perceive situated human behaviors;

II. influence contextual human interactions and decision-making?