用简单模型在钢琴乐谱续写上超越大模型。
A Traditional Approach to Symbolic Piano Continuation
- 直接预测下一个音符，不加复杂结构。
- 基于高质量数据训练，效果优于大型模型。
- 适合研究基础生成机制的学者与开发者。
我们针对 MIREX 2025 符号音乐生成挑战，提出一种传统的符号钢琴音乐续写方法。尽管当前计算音乐生成多聚焦于具有复杂架构调整的大规模基础模型，我们认为对于约束性、单乐器任务，更简单的方案仍更具有效性。因此，我们回归到对分词后的原始 MIDI 数据进行未增强的下一个标记预测目标，通过更优的数据和更扎实的基础方法，旨在超越大型基础模型的表现。相关模型权重与代码已开源：https://github.com/christianazinn/mirex2025。
原文摘要 · Abstract (English)
We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently focused on developing large foundation models with sophisticated architectural modifications, we argue that simpler approaches remain more effective for constrained, single-instrument tasks. We thus return to a simple, unaugmented next-token-prediction objective on tokenized raw MIDI, aiming to outperform large foundation models by using better data and better fundamentals. We release model weights and code at https://github.com/christianazinn/mirex2025.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。