Seoul National University
MIT
Agnieszka Grabska BarwińskaSenior Research Scientist · Google DeepMindResearcher↗
Researcher
Been Kim
Google DeepMindDirector
Kim works to make AI understandable and turn its discoveries into knowledge people can use. She co-developed TCAV, which tests whether concepts such as stripes influence a model’s predictions.[1] She also co-authored research extracting chess concepts from AlphaZero and teaching them to grandmasters, who improved on related puzzles.[2]
Career & education
Current roleGoogle DeepMindMay 2026-presentDirector
Google DeepMindMay 2026-presentPreviouslyGoogle DeepMind2023-2026Senior Staff Research Scientist
Google Brain2017-2023Research Scientist -> Senior Staff Research Scientist
Ai22015-2017Research Scientist
Google DeepMind2023-2026Google Brain2017-2023Ai22015-2017Education
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations41,516As of Oct 18, '26
citations+4,514Since last snapshot, Jun 15, '26
References
- TCAV — ICML 2018proceedings.mlr.press
Co-authorship and concept-based testing of model predictions, including stripes. Read directly on 2026-10-18.
- Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZeropnas.org
Kim coauthored research extracting novel teachable chess concepts from AlphaZero; four grandmasters improved on concept puzzles after teaching in a small proof-of-concept study, not evidence of broad playing-strength or championship effects.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
