Rushuai Yang

I'm a Ph.D. student at the Hong Kong University of Science and Technology (2023–present). Previously, I received my bachelor's degree in Computer Science from Harbin Institute of Technology (2019–2023). When supervision alone is insufficient, I study how to reliably enable physical agents to learn through their own experience.

Research Highlights

Selected work by research theme, from skill discovery to real-robot post-training.

2023–2024

How can agents discover new skills without human supervision?

Exploration-driven objectives for diverse, reusable behaviors.

2024–2025

How can RL improve VLA training beyond human demonstrations?

RL-generated skills and trajectories for scalable VLA pretraining.

Research Interests

  • Reinforcement learning for embodied intelligence and robot learning
  • Vision-language-action models and scalable embodied pretraining
  • Post-training, evaluation, and decision-making for foundation models
  • Real-world robotic systems, deployment constraints, and data generation