Xingyu Lin

I am a postdoc at the Berkeley Artificial Intelligence Research (BAIR) Lab working with Pieter Abbeel. I received my Ph.D. in Robotics from Carnegie Mellon University, advised by David Held and my B.S. in computer science from Peking University.

I am looking for a research position in both academia and industry. Please reach out if you think I could be a good fit!

Google Scholar / Github / Twitter / CV (Mar. 2024) / xingyu [at] berkeley (dot) edu


My research lies in robotics, machine learning, and computer vision, with the primary goal of learning generalizable robot skills from two angles:

  • Learning structured world models with spatial and temporal abstractions.
  • Pre-training visual representation and skills to enable knowledge transfer from Internet-scale vision datasets and simulators.

Ultimately, my goal is to enable robots to assist humans in unstructured environments, particularly at home. To achieve this, many of my works consider tasks in deformable object manipulation, which are common in our daily lives but pose significant challenges for current robot systems.


I am co-organizing the RSS 2023 Pioneer Workshop.
Two papers accepted at ICRA 2023 and RSS 2023

I have successfully defended my PhD thesis! A big thanks to my thesis committee: David Held, Abhinav Gupta, Deepak Pathak and Ken Goldberg.
I am selected as one of the RSS Pioneers of 2022.
Invited talks at UC Berkeley, MIT and Stanford.
One paper accepted at ICLR 2022! [OpenReview]
Proposed my PhD thesis. [Link]
One paper on cloth manipulation accepted at CoRL 2021! [OpenReview]
Invited talk at RSS 2021 workshop on Deformable Object Simulation. (Co-present with David Held) [Link]
Show More


(show selected / show all by date)



  • Conference Reviewer: NeurIPS, ICML, ICLR, RSS, CoRL, ICRA, IROS
  • Journal Reviewer: IEEE RA-L, AURO, T-RO