Rafael Rafailov
Source-listed: Member of Technical Staff · Thinking Machines Lab
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelSaved credit: First author · 2023Explore people connected to this work →
- Open X-Embodiment: Robotic Learning Datasets and RT-X ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- OpenVLA: An Open-Source Vision-Language-Action ModelSaved credit: Contributor · 2024Explore people connected to this work →
- Generative Reward ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Aligning protein-generative models to experimental fitness with ProteinDPOSaved credit: Contributor · 2026Explore people connected to this work →