Reproduce “Arc Gradient Descent: A Geometrically Motivated Gradient Descent-based Optimiser with Phase-Aware, User-Controlled Step Dynamics (proof-of-concept)” 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
Nikhil Verma, Joonas Linnosmaa, Leonardo Espinosa-Leal, Napat Vajragupta
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.