Aleksandar Botev
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- RecurrentGemma: Moving Past Transformers for Efficient Open Language ModelsSaved credit: First author · 2024Explore people connected to this work →
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Gemma: Open Models Based on Gemini Research and TechnologySaved credit: Contributor · 2024Explore people connected to this work →
- Practical Gauss-Newton Optimisation for Deep LearningSaved credit: First author · 2017Explore people connected to this work →
- Hamiltonian Generative NetworksSaved credit: Contributor · 2020Explore people connected to this work →