Thico (Sike) Xiang is a computer vision researcher, focussing on Vision-Language Models (VLMs), multimodal representation learning, and medical imaging analysis. He has completed a BEng in Computer Science and technology at Beijing Institute of Technology, Zhuhai, followed by an MSc in Computing Science at the University of Glasgow. His undergraduate and master’s research focussed on multimodal learning and medical AI, with outcomes contributing to ongoing research projects and publications. He then worked for ~10 months (10/2023 – 07/2024) at the University of Electronic Science and Technology of China (UESTC) as a Research Assistant, researching multimodal learning and medical AI, and also gained practical experience as an Internet Center intern at Mianyang Third People’s Hospital. In his PhD at Durham University, he focusses on efficient and scalable vision-language understanding and cross-modal fusion mechanisms. Currently, Thico is a PhD student at the Adaptive Intelligence Lab, working on resource-efficient multimodal large language models, medical large language models (medical LLMs), and medical AI agents.