PeopleofSuperintelligence

Researcher

Chien-Yao Wang

Chien-Yao Wang is a computer-vision researcher at Academia Sinica whose work spans neural-network design and real-time object detection. He earned a Ph.D. in computer science and information engineering from National Central University in 2017 and worked as a postdoctoral research fellow at Academia Sinica from 2017 to 2022. His papers include CSPNet, the YOLOv4, Scaled-YOLOv4, YOLOv7 and YOLOv9 object detectors, and Generalist YOLO for real-time vision and language tasks. Since July 2025, he is an associate research fellow at Academia Sinica's Institute of Information Science.

Timeline

  1. 2017–2022

    A doctorate and a postdoc

    He earns a Ph.D. in computer science and information engineering from National Central University in 2017. In November 2017, he joins Academia Sinica's Institute of Information Science as a postdoctoral research fellow and serves there through July 2022.

  2. 2019

    CSPNet and efficient CNNs

    In 2019, he coauthors CSPNet, which integrates feature maps from the start and end of a network stage to reduce computation.

  3. 2020

    YOLOv4 for real-time detection

    In 2020, he coauthors YOLOv4, which reaches 43.5% AP on MS COCO at about 65 frames per second on Tesla V100.

  4. 2020–2021

    Scaling YOLOv4

    In 2020, he posts Scaled-YOLOv4, which scales YOLOv4 up and down for small and large networks. CVPR publishes the work in 2021.

  5. 2023–2024

    YOLOv7 and YOLOv9

    In 2023, he coauthors YOLOv7, which proposes a trainable bag-of-freebies solution for real-time object detectors. In 2024, he coauthors YOLOv9, which proposes Programmable Gradient Information to address information loss through deep networks.

  6. 2025

    Generalist YOLO and a research award

    In February 2025, he coauthors Generalist YOLO, a system for real-time vision and language tasks that uses a unified encoder and primary-secondary co-attention. Academia Sinica names him a recipient of its 2025 Early-Career Investigator Research Achievement Award.

  7. 2026

    Frontiers of Science Award

    In 2026, he receives the Frontiers of Science Award with Mark Liao.

  8. Since July 2025

    Associate Research Fellow at Academia Sinica

    Since July 2025, he serves as an Associate Research Fellow at the Institute of Information Science, Academia Sinica.

Career

  1. Since 2017Academia SinicaPostdoctoral Research Fellow, Associate Research Fellow

Education

  1. 2017National Central UniversityPh.D.

From the biography.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Academia Sinica. 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.
  2. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  3. The United States employs an estimated 48% of people shaping AIWe estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  4. 43% of living people shaping AI work outside their country of birthWe estimate that 43% of living people shaping AI work outside their country of birth (520 of 1,198 people with known birth and employment countries).

Colleagues

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

Sources and credits

Photo: We have no published photo of Chien-Yao Wang yet. Send us a free-licensed photo.

  1. Wang, Chien Yao Homepage homepage.iis.sinica.edu.tw. Checked 21 October 2026.
  2. Wang, Chien Yao Homepage homepage.iis.sinica.edu.tw. Checked 21 October 2026.
  3. CSPNet: A New Backbone that can Enhance Learning Capability of CNN arxiv.org. Checked 21 October 2026.
  4. YOLOv4: Optimal Speed and Accuracy of Object Detection arxiv.org. Checked 21 October 2026.
  5. Scaled-YOLOv4: Scaling Cross Stage Partial Network arxiv.org. Checked 21 October 2026.
  6. Scaled-YOLOv4: Scaling Cross Stage Partial Network openaccess.thecvf.com. Checked 21 October 2026.
  7. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors openaccess.thecvf.com. Checked 21 October 2026.
  8. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information arxiv.org. Checked 21 October 2026.
  9. Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models openaccess.thecvf.com. Checked 21 October 2026.
  10. 2025 Announcements iis.sinica.edu.tw. Checked 21 October 2026.
  11. 2026 Announcements iis.sinica.edu.tw. Checked 21 October 2026.
  12. Personnel sinica.edu.tw. Checked 21 October 2026.