通过干预生成模型的激活值，实现音乐风格的精准控制。
Genre Controlled Music Generation via Activation Steering
- 在推理阶段用线性探针调节残差流，实现风格可控生成
- 可精确控制音乐风格，支持多种类型混合生成
- 适合音乐创作与人机协同创作场景
计算音乐生成正向非传统风格演进，需要能够精确、可控融合多样音乐元素的方法。本文提出一种在自回归生成变换器MusicGen上进行推理时干预的方法，通过使用线性探针对残差流施加权重调控，实现音乐风格的精细控制。将激活值调控设计为人类可交互的操作，凸显了可解释模型行为在协同音乐创作中的价值。音频样例可在演示页面查看。
原文摘要 · Abstract (English)
Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work, we present a method for fine grained control using inference-time interventions on an autoregressive generative transformer, MusicGen. Through our approach, we achieve genre control by steering the residual stream using weights of a linear probe on it. By framing activation steering as a human-controllable interaction, our work highlights how interpretable model behaviors can empower in co-creative music generation.Audio samples demonstrating our method are available on our demo page.
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。