Reproduce “Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization” 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
Filip Sondej, Yushi Yang, Mikołaj Kniejski, Marcel Windys
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.