Orgad Keller
Source-listed: Research Scientist · Google Research
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Gemini: A Family of Highly Capable Multimodal ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- Multi-turn Reinforcement Learning with Preference Human FeedbackSaved credit: Contributor · 2024Explore people connected to this work →
- Dynamic Planning in Open-Ended Dialogue using Reinforcement LearningSaved credit: Contributor · 2022Explore people connected to this work →
- Factually Consistent Summarization via Reinforcement Learning with Textual Entailment FeedbackSaved credit: Contributor · 2023Explore people connected to this work →
- Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model PerformanceSaved credit: Contributor · 2024Explore people connected to this work →