My name is Liu Shikun (刘诗昆 in Chinese characters), an upcoming Ph.D. student in Machine Learning Research at Imperial College London, working on self-supervised & meta learning and its intersection with vision perception and robotics. I am currently collaborating with Edward Johns and Andrew Davison and my Ph.D. research will be generously funded by Dyson. I recently completed my Master of Research degree (with Distinction) in Advanced Computing at the same lab working on multi-task learning. Before graduate school, I obtained my Bachelor degrees in mathematics and electrical engineering at The Penn State University - Schreyer Honors College.
I have also spent some fun time doing internship both in industry and academics: @CMU - The Robotics Institute, I was advised by Simon Lucey in CI2CV Lab and have worked on generative modelling on 3D shape learning and reconstruction. @Tencent - YouTu Lab [优图实验室], I contributed to Tecent MiYing [腾讯觅影], an AI-powered diagnostic medical imaging service in which I worked on early-stage lung cancer detection. @Adobe Research (upcoming summer 2019), I will work with Zhe Lin at Creative Intelligence Lab on efficient neural architecture search to solve complex computer vision tasks.
My general research interest is to build learning frameworks which can induce learning algorithms automatically and incrementally learn with no or minimal human supervision. It involves learning a universal representation from a diverse range of tasks; understand compositional and relational structure from complex visual signals; and quickly show mastery of new learning tasks from previous experiences.