Reproduce “Tiny-Twin: A CPU-Native Full-stack Digital Twin for NextG Cellular Networks” 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
Ali Mamaghani, Ushasi Ghosh, Srinivas Shakkottai, Dinesh Bharadia, Ish Kumar Jain
Tiny-Twin replays time-varying multipath channel traces through a 5G software stack, applying them to baseband signals so they shape protocol behavior. The authors reorganize channel convolution across per-UE processes and use sparse convolution and CPU pinning. In a five-UE, 10-tap benchmark, 90th-percentile compute time fell from 8 ms to about 2 ms; results concern single-cell CPU emulation, not field equivalence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.