Reproduce “Transfer Learning for Rhythm Game Chart Generation from Music Transcription and Across Games” 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
Sojeong An, Nathan Pruyne, Chris Donahue, Dasaem Jeong
MuScriptor uses a frozen encoder trained for music transcription to generate rhythm-game charts, feeding its representations to a chart decoder. In osu! standard, it reaches event F1 0.433, versus 0.323 for the same Transformer trained from scratch; events require matching note type and onset within 25 ms. Joint training improves mania with other osu! modes, but not Clone Hero.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.