Yinhuai Wang

Hi! I am a first-year Ph.D student at HKUST, under the supervision of Prof. Ping Tan. I hold a Master's degree from Peking University and a Bachelor's degree from Xidian University. Additionally, I have interned at IDEA Research and Unitree Robotics.

Before my postgraduate studies, I worked at DH-Robotics as one of the initial team members (the first engineer), where I led a team in the development of electronics and algorithms for robot grippers and arms.

Email  /  CV  /  Google Scholar  /  Github  /  Zhihu

My current research interest focuses on enabling humanoid robots to interact dynamically with objects, environments, and humans with agility and robustness. We are committed to addressing the data bottleneck in robotics through simulation and reinforcement learning techniques, developing foundational controllers for general-purpose robot skills. Below are some selected papers.

By introducing novel data augmentation techniques for skill transitions and recovery patterns, we acquire robust and generalizable interaction skills from noisy and sparse HOI demonstrations.

We for the first time enable simulated humanoids to learn basketball interaction skills purely from HOI demonstrations. The learned interaction skills can be reused for complex and long-horizon tasks such as continuous scoring.

We enable physically simulated humanoids to imitate interactions from video demonstrations, without designing task-specific rewards.

We bring Range-Null space Decomposition (RND) into diffusion models, enabling diverse image restoration tasks in a zero-shot manner, without extra training or optimization.

We bring Range-Null space Decomposition (RND) into GAN-Prior based SR models to accelerate the convergence and ensure the downsampling consistency.

FreeDoM is a simple but effective training-free method generating results under control from various conditions using unconditional diffusion models.

We find that simply adding an independent LN to each layer can robustly improve the performance of vision transformers.

We fuse the generative prior and the image prior dynamically according to the degradation levels.

This cool template is stolen from Jon Barron!