PeopleofSuperintelligence

Researcher

Yufei Ye

Also known as Judy Ye, 叶雨菲

Yufei Ye, also known as Judy Ye, is a computer vision and robotics researcher whose work connects human-object understanding with robot action. She studied computer science at Tsinghua and robotics at Carnegie Mellon, where she earned a Robotics Institute PhD in 2024. She received the NVIDIA Graduate Fellowship for 2022–2023 and was selected for the EECS Rising Stars workshop in 2023. Her research moved from object-centric robot planning and 3D reconstruction to hand-object interaction synthesis and humanoid control learned from human data. As of October 2026, she is a Research Scientist on NVIDIA Research's Data-Driven AI for Robotics team.

Now at
NVIDIA
Badges

Timeline

  1. 2019

    Tsinghua and CMU robotics

    Before CMU, she earns a B.S. in computer science at Tsinghua University, where she works with Shi-Min Hu and Yankui Sun. At CMU's Robotics Institute, she completes the MSR program in August 2019 under Abhinav Gupta.

  2. 2019–2020

    An object-centric robot model

    In 2019, she introduces an object-centric forward model that helps robots plan action sequences from random interaction data. The paper appears in the CoRL proceedings published in 2020.

  3. 2021

    Predicting 3D object shape

    She coauthors a 2021 CVPR method that infers 3D shape and pose from one image and trains from unstructured image collections using segmentation outputs from off-the-shelf recognition systems.

  4. 2022–2023

    Hand-held object reconstruction

    In 2022, she coauthors a CVPR method that reconstructs generic hand-held objects from a single RGB image, using hand articulation and visual input. She receives the NVIDIA Graduate Fellowship for 2022–2023.

  5. 2023

    Diffusion for hand-object interaction

    She coauthors Affordance Diffusion, a 2023 CVPR method that synthesizes plausible hand-object interaction images from an object image. In November 2023, she is selected for the EECS Rising Stars workshop.

  6. 2024

    A Robotics Institute PhD

    She completes a Robotics Institute PhD in August 2024 with a thesis on learning to perceive and predict everyday interactions. Her advisors are Abhinav Gupta and Shubham Tulsiani.

  7. 2025

    Stanford postdoc and humanoids

    Before joining NVIDIA, she works as a postdoctoral scholar at Stanford with Karen Liu. In 2025, she coauthors HEAD, a framework for humanoid navigation, locomotion, and reaching learned from human motion and vision data. In June 2025, she co-organizes CVPR's 4DVision and Agents in Interaction, from Human to Robots workshops.

  8. As of October 2026

    Research Scientist at NVIDIA

    She is a Research Scientist in NVIDIA Research's Data-Driven AI for Robotics (DAIR) team, with interests in 3D vision, robotics, and human motion. Her work includes GRAIL, which generates humanoid loco-manipulation from 3D assets and video priors.

Career

  1. NowNVIDIAResearch Scientist
  2. Stanford UniversityPostdoctoral Scholar

Education

  1. 2024Carnegie Mellon UniversityPhD
  2. 2019Carnegie Mellon UniversityMSR
  3. Tsinghua UniversityB.S.

From the biography.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Yufei Ye. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Yufei Ye yet. Send us a free-licensed photo.

  1. Yufei (Judy) Ye Home Page judyye.github.io. Checked 20 October 2026.
  2. Yufei Ye - Robotics Institute Carnegie Mellon University ri.cmu.edu. Checked 20 October 2026.
  3. [1910.03568] Object-centric Forward Modeling for Model Predictive Control arxiv.org. Checked 20 October 2026.
  4. Object-centric Forward Modeling for Model Predictive Control proceedings.mlr.press. Checked 20 October 2026.
  5. CVPR 2021 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  6. CVPR 2022 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  7. CVPR 2023 Open Access Repository openaccess.thecvf.com. Checked 20 October 2026.
  8. Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching tml.stanford.edu. Checked 20 October 2026.
  9. Yufei (Judy) Ye | DAIR @ NVIDIA Research research.nvidia.com. Checked 20 October 2026.