My name is Liu, Shikun (刘诗昆 in Chinese characters), a first-year Ph.D. student in Machine Vision & Robotics at Imperial College London. I am currently working at the Dyson Robotics Lab, co-advised by Edward Johns and Andrew Davison. I am interested in and actively studying on AutoML, self-supervised learning and meta learning with applications in vision and robotics. I recently 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 The Penn State University - Schreyer Honors College.
I have also spent some great time doing internships both in industry and academia.
- @Adobe Research: I was working with Zhe Lin at Imagination Lab. We studied on architecture-level transfer learning and neural architecture morphing.
- @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.
- @CMU - The Robotics Institute: I was advised by Simon Lucey in CI2CV Lab, working on generative modelling on 3D shape learning and reconstruction.
My general research interest is to build learning frameworks which can induce learning algorithms automatically, with no or minimal human supervision. This includes learning a universal representation from various tasks; automating network architecture design with adaptation to different input signals; and showing a quick mastery of new tasks based on previous experiences.