PeopleofSuperintelligence

Researcher

Xueting Li

Xueting Li is a research scientist at Nvidia Research in Santa Clara. Her work focuses on computer vision, including 3D vision, affordance learning, and self-supervised methods. She earned a B.S. from Beijing University of Posts and Telecommunications in 2013 and an M.S. from Tsinghua University in 2016, then completed a Ph.D. at the University of California, Merced in 2021 with Ming-Hsuan Yang as advisor. In 2019 she published a universal style-transfer method at CVPR, and she received the NVIDIA Graduate Fellowship in 2020 and a Google PhD Fellowship in 2021. GAvatar, presented at CVPR in 2024, generates animatable avatars from text at 100 fps, and in 2026 she coauthored a head-avatar method that runs at 107.31 FPS.

Now at
NVIDIA
Works
150
Citations
2,699
h-index
28

Publication numbers from OpenAlex, as of 17 October 2026.

Timeline

  1. 2013–2016

    Degrees in Beijing and Tsinghua

    She earns a B.S. from Beijing University of Posts and Telecommunications in 2013 and an M.S. from Tsinghua University in 2016.

  2. 2019

    Fast style transfer at CVPR

    Learning Linear Transformations for Fast Image and Video Style Transfer appears at CVPR in 2019 with Sifei Liu, Jan Kautz, and Ming-Hsuan Yang. The approach learns a transformation matrix for universal style transfer and is demonstrated on artistic, photo-realistic, and video style transfer.

  3. 2020–2021

    Two graduate fellowships

    She receives the NVIDIA Graduate Fellowship in 2020 and a Google PhD Fellowship in 2021.

  4. 2021

    A doctorate at Merced

    She completes a Ph.D. at the University of California, Merced in 2021, supervised by Ming-Hsuan Yang. The dissertation is Learning Visual Correspondences across Instances and Video Frames.

  5. 2024

    GAvatar at CVPR

    GAvatar appears at CVPR in 2024 with Ye Yuan, Yangyi Huang, Shalini De Mello, Koki Nagano, Jan Kautz, and Umar Iqbal. The method generates diverse animatable avatars from text prompts and renders at 100 fps at 1K resolution.

  6. 2025

    SimAvatar at CVPR

    SimAvatar appears at CVPR in 2025 with Ye Yuan, Shalini De Mello, Gilles Daviet, Jonathan Leaf, Miles Macklin, Jan Kautz, and Umar Iqbal. The framework generates simulation-ready clothed 3D human avatars from a text prompt.

  7. 2026

    Head avatars over 100 FPS

    In 2026, Kaiwen Jiang, Xueting Li, Seonwook Park, Ravi Ramamoorthi, Shalini De Mello, and Koki Nagano author Instant Expressive Gaussian Head Avatars at Over 100 FPS. The method runs at 107.31 FPS for animation and pose control. She is affiliated with NVIDIA for the ECCV 2026 paper.

  8. As of October 2026

    Research scientist in Santa Clara

    She is a research scientist at Nvidia Research in Santa Clara. Her research focuses on computer vision, specifically 3D vision, affordance learning, and self-supervised methods.

Sources and credits

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

  1. Homepage - Xueting Li sunshineatnoon.github.io. Checked 16 October 2026.
  2. Xueting Li | DAIR @ NVIDIA Research research.nvidia.com. Checked 16 October 2026.
  3. CVPR 2019 Open Access Repository openaccess.thecvf.com. Checked 16 October 2026.
  4. Xueting Li | Research research.nvidia.com. Checked 16 October 2026.
  5. Google PhD Fellowship recipients research.google. Checked 16 October 2026.
  6. Xueting Li - The Mathematics Genealogy Project genealogy.math.ndsu.nodak.edu. Checked 16 October 2026.
  7. CVPR 2024 Open Access Repository openaccess.thecvf.com. Checked 16 October 2026.
  8. CVPR 2025 Open Access Repository openaccess.thecvf.com. Checked 16 October 2026.
  9. Instant Expressive Gaussian Head Avatars at Over 100 FPS research.nvidia.com. Checked 16 October 2026.
  10. [2512.16893] Instant Expressive Gaussian Head Avatars at Over 100 FPS arxiv.org. Checked 16 October 2026.