Home

I’m Ziqi Zhou, a first-year PhD student in the CDT for Machine Learning Systems at the University of Edinburgh, supervised by Professor Laura Sevilla-Lara. I completed my bachelor’s degree in Computer Science and Technology at the University of Chinese Academy of Sciences, followed by a master’s degree at the Institute of Automation, Chinese Academy of Sciences, where I was co-supervised by Professor Dong-Ming Yan and Professor Weize Quan. During my studies, I worked on projects ranging from GCN-based mesh denoising to multimodal-driven and controllable talking face generation. I also gained industry experience through an internship at JD.com, where I worked on visual feature learning for advertisement recommendation systems.

These experiences have shaped my broader research interests in computer vision and multimodal learning, particularly in the intersection of understanding and generation with large-scale models. Going forward, I am eager to explore how these models can capture higher-level concepts such as aesthetics, controllability, and interpretability, and to apply them in creative and impactful ways.