Reproduce “Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks” 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
Xiaojun Jia, Jianshu Li, Jindong Gu, Yang Bai, Xiaochun Cao
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.