Brian Lester
Source-listed: Senior Research Engineer · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Finetuned Language Models Are Zero-Shot LearnersSaved credit: Contributor · 2022Explore people connected to this work →
- The Power of Scale for Parameter-Efficient Prompt TuningSaved credit: First author · 2021Explore people connected to this work →
- SPoT: Better Frozen Model Adaptation through Soft Prompt TransferSaved credit: Contributor · 2022Explore people connected to this work →
- Training LLMs over Neurally Compressed TextSaved credit: First author · 2024Explore people connected to this work →
- The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed TextSaved credit: Contributor · 2025Explore people connected to this work →