Mengxi Wu is a Ph.D. student at the USC Department of Computer Science, advised by Prof. Mohammad Rostami.

Mengxi's research focuses on machine learning in data-scarce regimes, including transfer learning, zero-shot/few-shot learning, lifelong learning, multi-task learning, and domain adaptation. Mengxi is especially interested in problems related to graph-structured data. Previously, Mengxi has worked on adversarial machine learning for 3D point cloud processing and streaming algorithms for time-varying volume data.