Peizhong Ju

Peizhong Ju works on machine learning theory and applications, with recent focus on generative models (flow matching, diffusion-like methods), reinforcement learning (including offline and federated settings), and optimization techniques for training neural networks. Earlier work included wireless communications topics like massive MIMO and full-duplex systems, suggesting a research trajectory that has shifted from communications engineering toward core machine learning methods and theory.

Publication output has grown substantially over the last decade, rising from just a couple of papers per year in 2017-2021 to 6-13 papers annually in 2023-2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026