PeopleofSuperintelligence

Researcher

Wan-Yen Lo

Also known as W.-Y. Lo, Wan‐Yen Lo

Wan-Yen Lo is a computer vision researcher whose work spans interactive motion planning, visual-recognition software, video understanding and image segmentation. She completed a computer science PhD at UC San Diego in 2012 with Henrik Jensen and Matthias Zwicker as advisers, and worked as a software engineer at Google Switzerland in Zurich by 2012. She co-invented Waymo’s Rare instance classifiers patent, filed in 2017 and published in 2019, and coauthored a 2019 study of neural-network design spaces. In 2021, she shared the PAMI Mark Everingham Prize with the Detectron team and coauthored PyTorchVideo for video understanding. In 2023, she coauthored Segment Anything, a promptable image-segmentation project whose dataset contains over one billion masks across 11 million licensed images; since 2022, she is a Research Engineering Manager at Meta.

Now at
Meta
Works
15
Citations
12,720
h-index
10
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2012

    A PhD in computer science

    She earns a computer science PhD at UC San Diego in 2012 under Henrik Jensen and Matthias Zwicker. Her dissertation is titled Interactive Motion Planning with Motion Capture Data.

  2. By 2012

    Software engineer in Zurich

    By 2012, she works as a software engineer at Google Switzerland in Zurich.

  3. 2017–2019

    Rare instance classifiers

    With Abhijit Ogale and Yang Gao, she files Rare instance classifiers for Waymo LLC in 2017; the patent is published in 2019. It describes neural-network scoring designed to reduce repeated misclassification of rare objects in vehicle images.

  4. 2019

    Network design spaces

    In 2019, she coauthors On Network Design Spaces for Visual Recognition. The paper compares neural-network design spaces using distribution estimates across sampled models.

  5. 2021

    The Detectron prize

    As a member of Meta AI’s Detectron team, she shares the PAMI Mark Everingham Prize in 2021. The award recognizes the team’s contributions to the computer-vision community through its object-detection and segmentation software.

  6. 2021

    PyTorchVideo for video understanding

    At the ACM Multimedia conference in 2021, she coauthors PyTorchVideo, a deep-learning library for video-understanding research.

  7. 2023

    Segment Anything at Meta

    In 2023, she coauthors Segment Anything with Meta AI Research, a project for promptable image segmentation. Its dataset contains over one billion masks across 11 million licensed images.

  8. Since 2022

    Research engineering at Meta

    She is a Research Engineering Manager at Meta and works on faster training for vision transformers. In May 2022, she and her coauthors report reducing a ViT training epoch from 0.65 hours to 0.43 hours.

Career

  1. Since 2022MetaDetectron Team Member
  2. Google SwitzerlandSoftware engineer

Education

  1. 2012University of California, San DiegoPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Wan-Yen Lo. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  2. 5 of the 25 people with the most-cited recent papers also lead on career citationsIncludes Wan-Yen Lo. We compare citations to 2023–2025 papers with career citations and h-index, after correcting reviewed publication-date errors: who leads, when they started and where they work.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Meta. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.

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 Wan-Yen Lo yet. Send us a free-licensed photo.

  1. Graduating PhDs in 2011-2012 | Computer Science cse.ucsd.edu. Checked 21 October 2026.
  2. US10346724B2 - Rare instance classifiers - Google Patents patents.google.com. Checked 21 October 2026.
  3. On Network Design Spaces for Visual Recognition arxiv.org. Checked 21 October 2026.
  4. Detectron Q&A: The origins, evolution, and future of our pioneering computer vision library web.archive.org. Checked 21 October 2026.
  5. ICCV 2021 PAPER AWARDS | ICCV 2021 iccv2021.thecvf.com. Checked 21 October 2026.
  6. GitHub - facebookresearch/pytorchvideo: A deep learning library for video understanding research. github.com. Checked 21 October 2026.
  7. ICCV 2023 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  8. GitHub - facebookresearch/segment-anything github.com. Checked 21 October 2026.
  9. Significantly faster Vision Transformer training web.archive.org. Checked 21 October 2026.