Archit Sharma
Source-listed: Research Scientist · Google DeepMind
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: Contributor · 2023Explore people connected to this work →
- Dynamics-Aware Unsupervised Discovery of SkillsSaved credit: First author · 2020Explore people connected to this work →
- Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement LearningSaved credit: First author · 2023Explore people connected to this work →
- A Critical Evaluation of AI Feedback for Aligning Large Language ModelsSaved credit: First author · 2024Explore people connected to this work →
- FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real UsersSaved credit: Contributor · 2025Explore people connected to this work →