PeopleofSuperintelligence

Researcher

In So Kweon

Also known as In-So Kweon

In So Kweon is a computer-vision researcher whose work spans stereo correspondence, neural-network attention, and physical AI. He earned a robotics PhD at Carnegie Mellon in 1990 and joined KAIST’s Department of Electrical Engineering as a professor in 1992 after working at Toshiba's R&D Center. He coauthored a 2006 correspondence-search paper and the 2018 CBAM attention module; his KAIST team won WACV’s Best Student Paper award in 2023, and he received the 2024 Inchon Prize in science and technology. Since January 2026, he has led KIST’s Physical AI Research Group as a National Distinguished Researcher.

Timeline

  1. 1990–1992

    From robotics to KAIST

    He earns a robotics PhD at Carnegie Mellon University in 1990 and holds bachelor's and master's degrees in mechanical design and production engineering from Seoul National University. After working as a researcher at Toshiba's R&D Center, he joins KAIST's Department of Electrical Engineering as a professor in 1992.

  2. 2006

    Adaptive support-weight search

    He and Kuk-Jin Yoon publish “Adaptive Support-Weight Approach for Correspondence Search” in IEEE Transactions on Pattern Analysis and Machine Intelligence in 2006.

  3. 2018

    CBAM's channel and spatial attention

    With Sanghyun Woo, Jongchan Park, and Joon-Young Lee, he coauthors “CBAM: Convolutional Block Attention Module” at ECCV in 2018. The module infers channel and spatial attention from a feature map to refine a convolutional network's features.

  4. 2023

    A WACV paper award

    In 2023, his KAIST team wins WACV’s Best Student Paper Award for “Self-supervised Monocular Depth Estimation from Thermal Images via Adversarial Multi-spectral Adaptation.” The paper estimates distance from one thermal image by combining self-supervised learning with adversarial learning between thermal and color images.

  5. 2024

    The Inchon Prize

    He is selected for the 38th Inchon Prize in Science and Technology in 2024. His work includes extending attention models to computer vision and developing CBAM.

  6. Since January 2026

    Leading KIST's Physical AI group

    Since January 2026, he leads KIST’s Physical AI Research Group as a National Distinguished Researcher. He plans to develop a Korean-style Physical AI model and humanoid technology.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Sources and credits

Photo: We have no published photo of In So Kweon yet. Send us a free-licensed photo.

  1. Robotics Luminary Prof. In-So Kweon of KAIST to Join KIST as National Distinguished Researcher m2.dongascience.com. Checked 19 October 2026.
  2. Leading AI scholar In So Kweon to head KIST’s new Physical AI group m2.dongascience.com. Checked 19 October 2026.
  3. Kweon, In So - KAIST 전기 및 전자공학부 ee.kaist.ac.kr. Checked 19 October 2026.
  4. CBAM: Convolutional Block Attention Module openaccess.thecvf.com. Checked 19 October 2026.
  5. Professor In So Kweon’s research team wins the Best Student Paper award at IEEE/CVF Winter conference on Applications of Computer Vision (WACV) 2023 ee.kaist.ac.kr. Checked 19 October 2026.
  6. Professor In-So Kweon Selected as Recipient of the 38th Inchon Prize in the Science and Technology Category ee.kaist.ac.kr. Checked 19 October 2026.