Yiming Xu

I am currently a PhD Fellow at the Computer Vision Center (CVC), Universitat Autònoma de Barcelona (UAB). I am part of the Vision & Language Group, supervised by Dimosthenis Karatzas and Ernest Valveny, my research focuse on Multimodal Document Understanding.

Before starting my PhD, I received my master degree from the University of Amsterdam, where I completed my thesis on Multimodal RAG under the supervision of Benno Kruit and Jan-Christoph Kalo.

After graduating from my MSc program, I spent two years in industry building AI agents for e-commerce scenarios. I served as the principal developer on our flagship agent project, which went on to raise close to USD 7 million in funding.