PeopleofSuperintelligence

Researcher

Jong Chul Ye

Also known as 예종철, Jong C. Ye, Ye Jong Chul

Jong Chul Ye is a professor at KAIST whose work on deep learning for imaging inverse problems grew into research on diffusion models. He earned a Ph.D. at Purdue University in 1999, worked at Philips Research and GE Global Research, and joined KAIST in 2004. His 2017 paper on deep convolutional framelets explained deep networks for imaging inverse problems, and his 2022 work with Hyungjin Chung on diffusion posterior sampling appeared at ICLR 2023. The Ministry of Science and ICT gave him the Choi Sukjeong Award in 2023. He is a full professor at the Kim Jaechul Graduate School of AI and sits on KAIST's team in the Lunit Consortium's medical AI foundation model project.

Now at
KAIST
Badges

Timeline

  1. 1993–1999

    Seoul National and a Purdue PhD

    He earns a B.S. in 1993 and an M.S. in 1995 from Seoul National University, then a Ph.D. from Purdue University in 1999.

  2. 1999–2004

    Research jobs at Philips and GE

    From 1999 to 2001, he is a postdoctoral research associate at the University of Illinois at Urbana-Champaign. He then works as a senior member of research staff at Philips Research in New York from 2001 to 2003, and as a senior researcher in the X-ray CT Technology Group at GE Global Research from 2003 to 2004.

  3. 2004–2021

    Professor at KAIST

    He joins KAIST in 2004 and moves up from assistant to associate to full professor in the Department of Bio and Brain Engineering through 2021. He serves as interim head of that department from 2014 to 2015, and in 2016 he becomes a KAIST Endowed Chair Professor.

  4. 2017

    Deep convolutional framelets

    In 2017, he coauthors Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems with Yoseob Han and Eunju Cha. The paper builds a network from multilayer convolution framelets to explain why deep architectures work for imaging inverse problems.

  5. 2022–2023

    Diffusion posterior sampling

    In 2022, he coauthors two diffusion-model papers with Hyungjin Chung. One adds a manifold-constraint correction term to inverse-problem solvers; the other, Diffusion Posterior Sampling, handles noisy nonlinear problems such as Fourier phase retrieval and non-uniform deblurring, and appears at ICLR 2023 as a spotlight.

  6. 2022–2023

    Kumkok and Choi Sukjeong awards

    The Korean Society for Industrial and Applied Mathematics (KSIAM) gives him its Kumkok Academic Award in 2022, and the Ministry of Science and ICT gives him the Choi Sukjeong Award in 2023. In 2023, he also becomes president of the Korean Society of Artificial Intelligence in Medicine.

  7. June 2024

    CFG++ guidance for diffusion models

    In June 2024, he coauthors CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models with Hyungjin Chung, Jeongsol Kim, Geon Yeong Park and Hyelin Nam. The paper reformulates text guidance as an inverse problem to correct the off-manifold behavior of classifier-free guidance.

  8. Since 2025

    A medical AI foundation model

    In November 2025, KAIST joins the Lunit Consortium for the Ministry of Science and ICT's AI Specialized Foundation Model Development Project, and he serves on its joint research team. A full professor at the Kim Jaechul Graduate School of AI since 2022, he holds the Chung Moon Soul Mirae Chair.

Career

  1. Since 2004KAISTAssistant, Associate, and Full Professor, Interim Head
  2. From 2023Korean Society of Artificial Intelligence in MedicinePresident
  3. 2003–2004GE Global ResearchSenior researcher
  4. 2001–2003PhilipsSenior member of research staff
  5. 1999–2001University of Illinois Urbana-ChampaignPostdoctoral research associate

Education

  1. 1999Purdue UniversityPh.D.
  2. 1995Seoul National UniversityM.S.
  3. 1993Seoul National UniversityB.S.

From the biography.

  1. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Jong Chul Ye. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  2. The United States employs an estimated 48% of people shaping AIIncludes KAIST. We 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.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes KAIST. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes KAIST. 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.

Colleagues

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

Sources and credits

Photo: We have no published photo of Jong Chul Ye yet. Send us a free-licensed photo.

  1. Jong Chul Ye - Korean Academy of Science and Technology member profile kast.or.kr. Checked 21 October 2026.
  2. Professor Jong Chul Ye | M4DL maths4dl.ac.uk. Checked 21 October 2026.
  3. JongChul Ye - Korea Advanced Institute of Science and Technology pure.kaist.ac.kr. Checked 21 October 2026.
  4. Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems arxiv.org. Checked 21 October 2026.
  5. Improving Diffusion Models for Inverse Problems using Manifold Constraints arxiv.org. Checked 21 October 2026.
  6. Diffusion Posterior Sampling for General Noisy Inverse Problems arxiv.org. Checked 21 October 2026.
  7. CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models arxiv.org. Checked 21 October 2026.
  8. Imaging Seminar: Diffusion Models for Computational Imaging Problems - EPFL memento.epfl.ch. Checked 21 October 2026.
  9. AI Opens a New Era in Medical Science and Bio - KAIST News Center news.kaist.ac.kr. Checked 21 October 2026.