Reproduce “Hierarchical Wireless Foundation Model for Multi-Task 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
Yangjing Wang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
WFM uses a shared channel encoder and task-conditioned decoder to reuse radio-channel features across four simulated wireless tasks: beamforming, user scheduling, channel estimation, and beam selection. In beamforming, it reaches 98.5% of WMMSE’s normalized sum rate at 2.67 ms, versus 100% at 104 ms. The reported decoder latency excludes the shared encoder; tests use simulated DeepMIMO data, not real deployments.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.