Reproduce “AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling” 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

Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.