Hi — people from the Internet. I am Shikun Liu (刘诗昆 in Chinese characters), a fourth-year Ph.D. student in robotics, studying at Imperial College London. I am affiliated to the Dyson Robotics Lab, co-advised by Edward Johns and Andrew Davison. I am interested in and actively working on multi-task learning, self-supervised learning, and AutoML. I completed my Master of Research degree with Distinction at the same lab working on multi-task and auxiliary learning. Prior to joining Imperial College, I obtained my Bachelor degrees in Mathematics and Electrical Engineering at Penn State - Schreyer Honors College. My research is generously funded by Dyson.
My general research interest is to develop generally capable learning systems through large-scale multi-task and self-supervised learning, with applications to robotics and all types of data. This includes learning a universal representation from a wide range of tasks; automating network architecture design with adaptation to different input signals; and showing a quick mastery of new tasks based on few demonstrations.
I like drawing beautiful diagrams and all sorts of formats for data visualisation. And I am a strong advocate of reproducible and open machine learning research, for which I open-sourced all of my projects in my GitHub page. Apart from research, I enjoy arts and design, particularly in architecture, graphic design, typography and generative arts. I also spend time building and collecting bespoke mechanical keyboards.