Research

I work across the six research themes of the DeCLaRe Lab — Safety, Trustworthiness, Multimodality, AI for Science, Efficiency, and Embodied AI. My own current focus is memory for AI agents, efficient and reliable multi-agent systems, and reasoning.

Earlier work centred on multimodal representation learning, affective computing, and sentiment analysis.

Foundational workCOSMICDialogueGCNDialogueRNNMELDMISAMultimodal-InfomaxTensor Fusion Network