Y. Wang – NVIDIA Graduate Fellowship

Yuke Wang's major research focus is to exploit the inefficiency of the existing deep-learning (DL) applications (e.g., deep neural networks (DNNs) and graph neural networks (GNNs)) and improve their performance on GPUs through an array of technical innovations.

Wang's prior and ongoing projects cover diverse aspects, including optimizing DL algorithms to eliminate redundant computations, designing highly efficient GPU kernels to maximize hardware utilization, and parameterizing system designs to improve design adaptability and portability.

His final research goal is to facilitate the design and implementation of the next-generation high-performance and energy-efficient DL systems for a diverse range of real-world applications that demand powerful computation support (e.g., autonomous driving, AR/VR).

Wang is a member of the Scalable Energy-Efficient Architecture Lab (SEAL) and is supervised by Computer Science Professor Yufei Ding.

NVIDIA is the inventor of the Graphics Processing Units (GPUs) and the world's leading company in computer graphics, scientific computing, and artificial intelligence.