01 / Background
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 currently affiliated to the Dyson Robotics Lab, where I am co-advised by Edward Johns and Andrew J. Davison. 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.
02 / Research
My research focus is on developing generally capable learning systems for multi-task and multi-modal perception, reasoning, generation, and control. Specifically, I am interested in and currently working on these following topics: 1. multi-task/multi-modal relationships, representation learning, and optimisation strategies; 2. scalable and modality-agnostic neural architecture design; 3. multi-task skill discovery with open-ended exploration. Additionally, I am a strong advocate for reproducible and open science, for which I have open-sourced and actively maintained all my research projects in my personal GitHub.
03 / Hobbies
Apart from research, I especially enjoy arts and design, particularly in architecture, graphics, typography and generative arts. I have been mostly influenced by Kenya Hara, Dieter Rams, Hermann Zapf, Alberto Campo Baeza and Louis Khan, endorsing unobtrusive and minimal design principles. I also occasionally spend time building and collecting bespoke mechanical keyboards.