Yuyuan Liu

I am a Postdoctoral Researcher at the Department of Engineering Science, University of Oxford. Previously, I received my PhD from the Australian Institute for Machine Learning at the Adelaide University, where I was fortunate to be supervised by Prof. Gustavo Carneiro, Prof. Vasileios Belagiannis, and Prof. Ian Reid. My research focuses on visual understanding and multimodal intelligence across natural images, point clouds, and medical imaging, with an emphasis on real-world challenges such as limited data, noisy labels, and OoD inputs. Recently, I have been working on LVLMs, focusing on reasoning and multimodal perception for complex visual tasks through post-training. I build MLLMs better at truly seeing and reasoning about the visual world.