Quantao Yang
Papers
6
Total Citations
47
H-Index
3
About
Quantao Yang is a robotics researcher advancing the frontier of robot manipulation through skill learning, imitation learning, and reinforcement learning. His work addresses the fundamental challenge of enabling robots to perform contact-rich and long-horizon tasks with data efficiency and safety. Yang’s most cited paper, "Variable Impedance Skill Learning for Contact-Rich Manipulation" (2022, 27 citations), introduces reinforcement learning approaches for complex physical interactions. He further developed PRIME (2024, 10 citations), a framework that scaffolds manipulation tasks with behavior primitives for data-efficient imitation learning, significantly reducing sample complexity in long-horizon scenarios. Yang has also contributed to safe reinforcement learning through null-space-based hierarchical constraints (2021), and to skill transfer across different robots using cycle generative networks (2023). His recent work on S²-Diffusion (2025) generalizes skills from instance-level to category-level manipulation, while his diffusion trajectory-guided policy (2025) tackles long-horizon robot manipulation. Collectively, Yang’s research pushes toward more adaptable, safe, and efficient robotic systems capable of operating in unstructured real-world environments.
Research Focus
Key Achievements
Top Papers
- 1Variable Impedance Skill Learning for Contact-Rich Manipulation27 citations · 2022
- 2
- 3
- 4
- 5
- 6Diffusion Trajectory-Guided Policy for Long-Horizon Robot Manipulation2 citations · 2025