PeopleofSuperintelligence

Researcher

Xinyang Li

Also known as 李欣阳

Xinyang Li is a Tsinghua researcher whose AI methods support scientific imaging. At Xi'an Jiaotong, he earned a bachelor's degree in 2018; he completed a control science and engineering Ph.D. in Tsinghua's Department of Automation in 2023 and worked as a postdoctoral fellow there through June 2025. His work spans self-supervised denoising for fluorescence microscopy and unsupervised tracking of multiple animals. He received the PhotoniX Prize in 2025. He is an assistant professor at Tsinghua's College of AI, a role he has held since July 2025.

Timeline

  1. 2018

    Xi'an Jiaotong bachelor's degree

    In 2018, he earns a bachelor's degree at Xi'an Jiaotong University's School of Electronic and Information Engineering.

  2. 2019

    Adaptive multi-foci optimization

    In 2019, he coauthors an Optics Express paper on adaptive optimization for axial multi-foci generation in multiphoton microscopy.

  3. 2021

    DeepCAD for calcium imaging

    In 2021, he coauthors DeepCAD, a self-supervised deep-learning method for spatiotemporal enhancement of calcium-imaging data.

  4. September 2022

    DeepCAD-RT for fluorescence imaging

    In September 2022, he coauthors the Nature Biotechnology paper “Real-time denoising enables high-sensitivity fluorescence time-lapse imaging beyond the shot-noise limit.”

  5. 2023

    Doctorate at Tsinghua

    He completes a Ph.D. in control science and engineering in Tsinghua University's Department of Automation in 2023.

  6. July 2023–June 2025

    Postdoctoral fellow at Tsinghua

    From July 2023 through June 2025, he works as a postdoctoral research fellow in Tsinghua University's Department of Automation.

  7. 2025

    The PhotoniX Prize

    In 2025, he receives the PhotoniX Prize for his work using AI to empower scientific observation and accelerate scientific discovery.

  8. 2025

    Light-field denoising

    In 2025, he coauthors LF-denoising, a self-supervised transformer that uses spatial-angular redundancy to denoise 3D fluorescence images.

  9. May 2026

    UDMT for animal tracking

    In May 2026, he coauthors “Unsupervised transfer learning enables multi-animal tracking without training annotation,” a Nature Methods paper on tracking multiple animals.

  10. Since July 2025

    Assistant professor at Tsinghua

    Since July 2025, he serves as an assistant professor at Tsinghua University's College of AI.

Career

  1. Since 2025Tsinghua UniversityAssistant professor

Education

  1. 2023Tsinghua UniversityPhD
  2. 2018Xi'an Jiaotong UniversityBachelor's degree

From the biography.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

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

  1. 李欣阳-清华大学人工智能学院 collegeai.tsinghua.edu.cn. Checked 26 October 2026.
  2. Xinyang Li xinyang-li.github.io. Checked 26 October 2026.
  3. Reinforcing neuron extraction and spike inference in calcium imaging using deep self-supervised denoising | Nature Methods nature.com. Checked 26 October 2026.
  4. Real-time denoising enables high-sensitivity fluorescence time-lapse imaging beyond the shot-noise limit | Nature Biotechnology nature.com. Checked 26 October 2026.
  5. Xinyang LI-College of Al, Tsinghua University collegeai.tsinghua.edu.cn. Checked 26 October 2026.
  6. Leveraging spatial-angular redundancy for self-supervised denoising of 3D fluorescence imaging without temporal dependency | Nature Communications nature.com. Checked 26 October 2026.
  7. Nat Methods 2026 | Unsupervised transfer learning enables multi-animal tracking without training annotation-LImIT Tsinghua University media.au.tsinghua.edu.cn. Checked 26 October 2026.