[2604.03333] Composer Vector: Style-steering Symbolic Music Generation in a Latent Space

Computer Science > Sound arXiv:2604.03333 (cs) [Submitted on 3 Apr 2026] Title:Composer Vector: Style-steering Symbolic Music Generation in a Latent Space Authors:Xunyi Jiang, Mingyang Yao, Jingyue Huang, Julian McAuley View a PDF of the paper titled Composer Vector: Style-steering Symbolic Music Generation in a Latent Space, by Xunyi Jiang and 3 other authors View PDF HTML (experimental) Abstract:Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled datasets. Besides, these methods typically support only single-composer generation at a time, limiting their applicability to more creative or blended scenarios. In this work, we propose Composer Vector, an inference-time steering method that operates directly in the model's latent space to control composer style without retraining. Through experiments on multiple symbolic music generation models, we show that Composer Vector effectively guides generations toward target composer styles, enabling smooth and interpretable control through a continuous steering coefficient. It also enables seamless fusion of multiple styles within a unified latent space framework. Overall, our work demonstrates that simple latent space steering provides a practical and general mechanism for controllable symbolic music generation, enabling more flexible and interactive cr...