PeopleofSuperintelligence

Researcher

Hoseung Song

Hoseung Song is a statistics researcher at KAIST whose methods test for change points, differences between samples and dataset shift in high-dimensional and graph data. After earning bachelor's and master's degrees in statistics at Seoul National University in 2014 and 2016, he completed a doctorate in statistics at the University of California, Davis in August 2021 under Hao Chen and worked as a postdoctoral research fellow at Fred Hutchinson Cancer Research Center under Michael C. Wu from September 2021 to April 2024. With Chen, he published changepoint and kernel two-sample tests in Biometrika in 2022 and 2024, IEEE Transactions on Signal Processing in 2024, and Statistics and Computing in 2026, alongside a May 2021 graph dataset-shift study with Lawrence Livermore National Laboratory researchers. Since April 2024, he is an assistant professor at KAIST, where his research areas include change-point (anomaly) detection, A/B tests and explainable AI.

Now at
KAIST

Timeline

  1. 2014–2016

    Statistics at Seoul National University

    At Seoul National University, he earns a B.S. in Statistics with a minor in Mathematical Sciences in August 2014 and an M.S. in Statistics in August 2016.

  2. June 2019–September 2019

    Intern at Lawrence Livermore

    From June 2019 to September 2019, he works as a data science research intern at Lawrence Livermore National Laboratory.

  3. May 2021

    Dataset shift in graph data

    In May 2021, with Jayaraman J. Thiagarajan and Bhavya Kailkhura of Lawrence Livermore National Laboratory, he publishes a two-sample test approach for detecting dataset shift in safety-critical, large-scale graph data in Frontiers in Artificial Intelligence.

  4. August 2021

    A statistics Ph.D. at UC Davis

    Advised by Hao Chen, he completes a Ph.D. in Statistics at the University of California, Davis in August 2021.

  5. September 2021–April 2024

    Postdoctoral fellow at Fred Hutch

    In September 2021, he joins Fred Hutchinson Cancer Research Center as a postdoctoral research fellow mentored by Michael C. Wu, staying until April 2024. With Wu, he publishes "Multivariate differential association analysis" in Stat in 2024.

  6. 2022

    Distribution-free changepoint detection in Biometrika

    Working with Hao Chen, he publishes "Asymptotic distribution-free changepoint detection for data with repeated observations" in Biometrika in 2022.

  7. 2024

    Kernel tests with Hao Chen

    In 2024, Song and Hao Chen publish "Generalized kernel two-sample tests" in Biometrika, a test statistic for multivariate data that gains power in moderate and high dimensions, with the R package kerTests. Their paper "Practical and powerful kernel-based change-point detection" appears in IEEE Transactions on Signal Processing in 2024 with the R package kerSeg.

  8. Since April 2024

    Assistant professor at KAIST

    He becomes an assistant professor at KAIST in April 2024, in the Department of Industrial and Systems Engineering and the Graduate School of Data Science, with adjunct posts in the Department of AX and the Graduate School of AI for Math, where his research areas include change-point (anomaly) detection, A/B tests and explainable AI. In November 2024, he presents ongoing work on spatial clustering tests and online change-point detection at the KAIST ISE colloquium, and in December 2024 he and Julia Wrobel introduce the KAMP K-statistic for quantifying immune cell clustering in spatial proteomics data. His 2026 papers include the K-statistic study in The Annals of Applied Statistics and a fast kernel two-sample test for large-scale data with Hao Chen in Statistics and Computing.

Career

  1. Since 2024KAISTAssistant Professor
  2. 2021–2024Fred Hutchinson Cancer Research CenterPostdoctoral Research Fellow
  3. 2019Lawrence Livermore National SecurityData Science Research Intern

Education

  1. 2021University of California, DavisPh.D. in Statistics
  2. 2016Seoul National UniversityM.S. in Statistics
  3. 2014Seoul National UniversityB.S. in Statistics

From the biography.

  1. 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.
  2. 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.
  3. 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.
  4. 44% of AI career moves go from one university to anotherIncludes KAIST. We estimate how 26,439 AI career moves link universities, companies, labs, nonprofits and government research centers, with decade counts, net flows and the top paths.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Bio | Hoseung Song hoseungs.github.io. Checked 22 October 2026.
  2. Frontiers | Preventing Failures by Dataset Shift Detection in Safety-Critical Graph Applications frontiersin.org. Checked 22 October 2026.
  3. Group Members research.fredhutch.org. Checked 22 October 2026.
  4. Research | Hoseung Song hoseungs.github.io. Checked 22 October 2026.
  5. Generalized kernel two-sample tests - Korea Advanced Institute of Science and Technology pure.kaist.ac.kr. Checked 22 October 2026.
  6. Home | Hoseung Song hoseungs.github.io. Checked 22 October 2026.
  7. Faculty | AX aicollege.kaist.ac.kr. Checked 22 October 2026.
  8. 뉴스 및 공지사항 | KAIST 데이터사이언스대학원 gsds.kaist.ac.kr. Checked 22 October 2026.
  9. [2412.08498] A robust, scalable K-statistic for quantifying immune cell clustering in spatial proteomics data arxiv.org. Checked 22 October 2026.