Papers
8
Total Citations
34
H-Index
3
About
Yiming Yang is a robotics researcher whose work spans reinforcement learning, robot dynamics, dexterous manipulation, and medical robotics. His research addresses some of the most challenging problems in embodied intelligence, including enabling anthropomorphic robotic hands to perform complex, high-degree-of-freedom tasks. His 2024 work on bionic-constrained diffusion policy for piano playing exemplifies his focus on bridging biological inspiration and robotic control, while his spatiotemporal transformer framework for reinforcement learning—developed in 2022—demonstrates his commitment to making robots more perceptually aware in partially observable environments. Yang has also made notable contributions to generalizable robot dynamics learning, proposing frameworks that eliminate the need to retrain models from scratch for each new robot platform, significantly reducing data collection burdens. His work on handling time-varying observation delays in reinforcement learning addresses critical real-world deployment challenges often overlooked in academic settings. Perhaps most distinctively, Yang has applied his robotics expertise to healthcare, leading the development of autonomous nasopharyngeal swabbing robots during the COVID-19 pandemic, including novel pneumatic soft swab designs. Collectively, his papers have accumulated over 30 citations, reflecting growing recognition across both fundamental robot learning and translational medical robotics communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2Efficient Spatiotemporal Transformer for Robotic Reinforcement Learning10 citations · 2022
- 3General Robot Dynamics Learning and Gen2Real4 citations · 2021
- 4
- 5
- 6Generalized Robot Dynamics Learning and Gen2Real Transfer2 citations · 2023
- 7
- 8