David Romero

I’m a PhD student in Computer Vision at MBZUAI, working with Ivan Laptev. Previously I worked with Thamar Solorio at the Ritual Lab in Vision-Language models. Before that, I worked in NLP and Speech processing topics at the Ixa Research Group at the University of the Basque Country, working with Eneko Agirre and at the Universidad Politecnica de Madrid with Luis Fernando D’Haro. I am an Electronic Engineer and I’m originally from Ecuador 🇪🇨.

My current research is focused on large-scale difussion models for world modeling and its applications for Embodied AI. I’m also interested in Vision-Language Models for Video Understanding.