PeopleofSuperintelligence

Researcher

Georgi Vitanov

Georgi Vitanov is a machine learning researcher whose interests include fairness, causality and practical applications. He earned a bachelor's degree in electrical engineering in Skopje from 2014 to 2018 and began a master's degree in mathematics and computer science at Saarland University in 2021. At the Max Planck Institute for Informatics, he presented SVMs, kernel methods, regression and dimensionality reduction in its Foundations of Machine Learning seminar in 2023. In June 2025, he coauthored Towards Reasonable Concept Bottleneck Models with Nektarios Kalampalikis, Kavya Gupta and Isabel Valera; the paper introduced CREAM, which encodes concept-concept and concept-task relationships in model reasoning, and appeared in Transactions on Machine Learning Research in 2026. As of October 2026, he is a research assistant in DFKI's Data Science and its Applications department.

Now at
DFKI

Timeline

  1. 2014–2018

    Electrical engineering in Skopje

    He earns a BSc in Electrical Engineering at the University of Ss. Cyril and Methodius in Skopje from 2014 to 2018.

  2. Since 2021

    An MSc at Saarland

    He starts an MSc in Mathematics and Computer Science at Saarland University in 2021 and continues his studies there. His research interests include fairness, causality and practical machine learning applications.

  3. May 2023

    SVMs with Yonggang Jiang

    In May 2023, he presents SVMs with Yonggang Jiang in the Foundations of Machine Learning seminar at the Max Planck Institute for Informatics.

  4. May 2023

    Kernel methods with Hans Simon

    In May 2023, he presents kernel methods with Hans Simon in the Foundations of Machine Learning seminar at the Max Planck Institute for Informatics.

  5. June 2023

    Regression at the MPI seminar

    In June 2023, he presents regression in the Foundations of Machine Learning seminar at the Max Planck Institute for Informatics.

  6. June 2023

    Dimensionality reduction at MPI

    In June 2023, he presents dimensionality reduction in the Foundations of Machine Learning seminar at the Max Planck Institute for Informatics.

  7. 2025–2026

    Towards Reasonable Concept Bottleneck Models

    In June 2025, he coauthors Towards Reasonable Concept Bottleneck Models with Nektarios Kalampalikis, Kavya Gupta and Isabel Valera. The paper proposes CREAM, a family of concept bottleneck models that lets practitioners encode concept-concept and concept-task relationships in model reasoning; it appears in Transactions on Machine Learning Research in 2026.

  8. As of October 2026

    Research assistant at DFKI

    He is a research assistant in DFKI's Data Science and its Applications department, which Sebastian Vollmer heads.

Career

  1. NowDFKIResearch assistant

Education

  1. From 2021Saarland UniversityMSc in Mathematics and Computer Science
  2. 2018Ss. Cyril and Methodius University in SkopjeBSc in Electrical Engineering

From the biography.

  1. Nonprofit roles are 2.3 times as common in AI safetyIncludes DFKI. We estimate where people focused on safety, alignment and evaluation work. Nonprofit roles appear for 25.1% of safety people with known affiliations, compared with 11.0% in other areas.
  2. The top 10 organizations employed 22% of people shaping AI in 2025: 51% of company researchers and 21% of university researchersIncludes DFKI. We estimate the share of people shaping AI who worked at the top 10 organizations each year from 1955 to 2025, comparing concentration across companies, universities, and institutes and labs.
  3. The United States employs an estimated 48% of people shaping AIIncludes DFKI. 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.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes DFKI. 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.

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 Georgi Vitanov yet. Send us a free-licensed photo.

  1. Georgi Vitanov — Data Science and its Applications dsa.dfki.de. Checked 22 October 2026.
  2. Seminar: Foundations of Machine Learning - Max Planck Institute for Informatics mpi-inf.mpg.de. Checked 22 October 2026.
  3. [2506.05014] Towards Reasonable Concept Bottleneck Models arxiv.org. Checked 22 October 2026.
  4. Georgi Vitanov csauthors.net. Checked 22 October 2026.
  5. Towards Reasonable Concept Bottleneck Models sota2.com. Checked 22 October 2026.