Yang Li


Welcome to my homepage! I'm an assistant professor at the Internet of Things and Societal Cyber Physical System Lab of Tsinghua Berkeley Shenzhen Institute (TBSI).

My overall research interest is learning about shared structures in uncertain data and among different learning tasks. I design algorithms to exploit such structures in both homogeneous problems, such as the collective analysis of GPS trajectories, as well as heterogeneous problems, such as in multi-modal and transfer learning. Applications of my research cover a wide range of problems, including

  • image-based computer vision & semantics, medical image processing

  • mobility computing and smart transportation

  • interactions of mobile agents

My current work incorporates information theory into transfer learning problems, where we aim to answer fundamental questions such as how transferable are features from one task to another, and how to extract discriminative features that are invariant to different input domains.

I obtained my PhD. degree in Computer Science from Stanford University in 2017, advised by Leonidas Guibas. My dissertation explores how to find shared structures in large GPS trajectories under uncertainty, and how the shared structures can be used to solve challenging problems. See the Research page for details about my past projects. I was also a contributor to the KINARI project.

Curriculum Vitae






Nanshan Intelligence Park, Tower C2, 15th Floor
1001 Xueyuan Blvd, Nanshan District
Shenzhen, Guangdong, China (518055)