Multimodal Interactive Intelligence Laboratory (MIIL)

Welcome to our Multimodal Interactive Intelligence Laboratory (MIIL). In MIIL, we are dedicated to creating intelligent systems that can comprehend and engage in meaningful, context-aware conversations while seamlessly interacting with their surroundings. To this end, we recognize the significance of multimodal AI, which combines speech, vision, gesture, and touch, to enable natural understanding of our world. Moreover, we understand the critical role of conversational and embodied AI in realizing Artificial General Intelligence, the ultimate goal of creating machines that possess comprehensive intelligence and interact back with the world in a human-like manner.