Research Group

Inspired by Barsalou’s Grounded Cognition theory, our research group focuses on designing artificial agents that learn language by leveraging sensory information derived from interacting with the world and with other agents. We explore the intersection of natural language processing, computer vision, robotics, and cognitive science to develop AI systems that can understand and interact with their environment in meaningful ways.

Our work spans multiple domains including:

  • Embodied AI: Developing multimodal-native agents that can perceive and act in physical environments
  • Situated Language Understanding: Creating systems that understand language in context
  • Grounded Intelligence: Building AI that connects language to real-world experiences
  • Human-Robot Interaction: Designing conversational AI that builds common ground with humans and other agents in embodied, multi-agent settings
  • Multimodal Learning: Integrating vision, language, and action for comprehensive understanding

Explore our open-source projects and code on GitHub.

PhD Students

Our research group is fortunate to work with talented PhD students who are pushing the boundaries of embodied and situated AI:

Amit Parekh Generalisation for Embodied AI
Sabrina McCallum Learning from Multimodal Feedback in Embodied AI
Malvina Nikandrou Continual Learning for VLMs
George Pantazopoulos Designing and Implementing VLMs
Sophie Higham Safety and Reliability of Continually Learning VLAs
Joe Kelliher Continual Learning for VLAs

Together, we are working on cutting-edge research that bridges the gap between language understanding and embodied experience, creating AI systems that can truly understand and interact with the world around them.

Affiliates

Postdoctoral researchers affiliated with our research group:

Alumni, Visiting Students and Interns

Current list of students who have worked with us:

Alumni

Visiting Students and Interns