Reproduce “UoMo: A Universal Model of Mobile Traffic Forecasting for Wireless Network Optimization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Haoye Chai, Shiyuan Zhang, Xiaoqian Qi, Baohua Qiu, Yong Li
UoMo combines traffic forecasting and generation in a shared model, using masked diffusion to reconstruct traffic tokens and fine-tuning with mobile-user counts and points of interest as context. In Beijing long-term prediction, it reports an MAE of 0.0696 versus 0.1014 for UniST. In a Nanchang platform planning test, its plan served 0.817 of users versus 0.652, not a physical deployment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.