Xingyu Lin

I am a research scientist at OpenAI working on general purpose robots.

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 have also spent two years as a postdoc the Berkeley Artificial Intelligence Research (BAIR) Lab working with Pieter Abbeel.

Google Scholar / Github / Twitter / CV (Mar. 2024) / xingyulin2016 [at] gmail (dot) edu


Research

My goal is to build general-purpose robots that can assist humans in unstructured environments. I work on the following themes:

  • Learning structured world models with spatial and temporal abstractions.
  • Learning from pre-trained multimodal foundation modelto enable knowledge transfer from Internet-scale data.
  • Building a diverse and reproducible robotics benchmark.

News

08/2024
I started a new job at OpenAI in a new robotics team.
08/2024
We are organizing the Workshop on Whole-body Control and Bimanual Manipulation at CoRL 2024.
05/2024
Four papers accepted at RSS 2024 and IROS 2024.
07/2023
Invited talk at RSS 2023 workshop on Interdisciplinary Exploration of Generalizable Manipulation Policy Learning
06/2023
I am co-organizing the RSS 2023 Pioneer Workshop.
03/2023
Two papers accepted at ICRA 2023 and RSS 2023

08/2022
I have successfully defended my PhD thesis! A big thanks to my thesis committee: David Held, Abhinav Gupta, Deepak Pathak and Ken Goldberg.
05/2022
I am selected as one of the RSS Pioneers of 2022.
02/2022
Invited talks at UC Berkeley, MIT and Stanford.
01/2022
One paper accepted at ICLR 2022! [OpenReview]
10/2021
Proposed my PhD thesis. [Link]
09/2021
One paper on cloth manipulation accepted at CoRL 2021! [OpenReview]
07/2021
Invited talk at RSS 2021 workshop on Deformable Object Simulation. (Co-present with David Held) [Link]
Show More


Publications

(show selected / show all by date)
 

Service

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