01 / Background
Hi — people from the Internet. I am Shikun Liu (刘诗昆 in Chinese characters). I am currently a Senior Research Scientist at Google DeepMind – World Models team, based in London, England, working on generalist embodied AGI through advancing world modelling and agentic capabilities. Previously, I was a Research Scientist at Meta AI, where I focused on generative 3D and video model post-training strategies, particularly in control and editing capabilities. I earned my Ph.D. at Imperial College London, where I was part of the Dyson Robotics Lab, working with Andrew J. Davison and Edward Johns.
02 / Research
I am a pixel researcher. I believe that the path to more general and capable machine intelligence lies in a deep and fundamental understanding of vision. My research pursues this direction through two interconnected themes: 1. teaching machines to understand the world from pixels; and 2. enabling them to reason, create and reconstruct worlds with them.
Visual Representation Learning: I study self-supervised, multi-task, and multi-modal learning techniques that improve the generalisation and robustness of visual systems, which emphasis on neural architecture designs, training objectives, learning efficiency and interpretability. My notable work includes multi-task neural architectures: ; multi-task and auxiliary learning optimisation strategies: , ; and multi-modal reasoning frameworks: .
Visual Synthesis and Reconstruction: I design efficient and scalable visual systems that can model and create complex 3D/4D worlds. I contributed to one of the first real-time neural SLAM systems using neural fields: ; and I developed foundational components which enable scalable generative 3D neural rendering: and . In larger-scale frontier generative AI projects, I am part of the post-training team, where I designed and led the development of spatial and motion control capabilities.
03 / Hobbies
Apart from research, I especially enjoy arts and design, particularly in architecture, graphics, typography and generative arts, endorsing unobtrusive and minimal design principles. I also occasionally spend time building and collecting bespoke mechanical keyboards.