Belarusian State University
Jacobs University Bremen
Ekin Dogus CubukCo-founder · Periodic LabsResearcher↗
Researcher
Dzmitry Bahdanau
Periodic LabsAI Research Scientist
Bahdanau introduced neural attention in machine translation, letting a model focus on the most relevant input words as it generated each output.[1] That idea became a foundation for transformers; he now applies learning and reasoning methods to AI scientists and autonomous laboratories at Periodic Labs.
Career & education
Current rolePeriodic Labs2026-presentAI Research Scientist
Periodic Labs2026-presentPreviously
ServiceNow2021-2025Research Scientist -> Research Lead
Element AI2020-2021Researcher
ServiceNow2021-2025Element AI2020-2021Work 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.
citations120,150As of Nov 1, '26
citations+1,920Since last snapshot, Oct 1, '26
Selected contributions
Neural Machine Translation by Jointly Learning to Align and Translate
With Kyunghyun Cho and Yoshua BengioAttention helps neural translation models focus on relevant words as each word is generated.
References
- Neural Machine Translation by Jointly Learning to Align and Translatearxiv.org
Bahdanau and his co-authors show how a translation model can learn which parts of a source sentence to focus on as it generates each word.
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.
Reviewed August 10, 2026 · Checked for accuracy and new information.
