University of Maryland
Jadavpur University
Nitish Shirish KeskarMember of Technical Staff · OpenAIResearcher↗
Researcher
Soham De
OpenAIMember of Technical Staff
Career & education
Current roleOpenAIOct 2026-presentMember of Technical Staff
OpenAIOct 2026-presentPreviously
Google DeepMind2018-2026Research Scientist
Google DeepMind2018-2026Work 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.
citations10,660As of Nov 10, '26
References
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Modelsarxiv.org
Original author list names De first; recurrent state/local attention provide memory efficiency on long sequences.
- RecurrentGemma: Moving Past Transformers for Efficient Open Language Modelsarxiv.org
De co-authorship verified. Official Google report lists De as joint-first author in Griffin Team; open models use Griffin.
- High-Performance Large-Scale Image Recognition Without Normalizationarxiv.org
Brock, De, Smith and Simonyan develop Normalizer-Free Networks without batch normalization.
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.
