Tianhe (Kevin) Yu
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 →
- RRM: Robust Reward Model Training Mitigates Reward HackingSaved credit: Contributor · 2025Explore people connected to this work →
- RT-1: Robotics Transformer for Real-World Control at ScaleSaved credit: Contributor · 2022Explore people connected to this work →
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement LearningSaved credit: Contributor · 2019Explore people connected to this work →
- MOPO: Model-based Offline Policy OptimizationSaved credit: Contributor · 2020Explore people connected to this work →