# Composer Vector: Style-steering Symbolic Music Generation in a Latent Space

arXiv: https://arxiv.org/abs/2604.03333 · HTML: https://mlsanity.com/paper/2604.03333/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [ChatMusician: Understanding and Generating Music Intrinsically with LLM](https://mlsanity.com/paper/2402.16153/) (2024)
- [SEAL: Steerable Reasoning Calibration of Large Language Models for Free](https://mlsanity.com/paper/2504.07986/) (2025)
- [Controllable Text Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2408.12599/) (2024)
- [MuseCoco: Generating Symbolic Music from Text](https://mlsanity.com/paper/2306.00110/) (2023)
- [NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms](https://mlsanity.com/paper/2502.18008/) (2025)
- [CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages](https://mlsanity.com/paper/2502.10362/) (2025)
- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [Improved Representation Steering for Language Models](https://mlsanity.com/paper/2505.20809/) (2025)
- [Text2midi: Generating Symbolic Music from Captions](https://mlsanity.com/paper/2412.16526/) (2024)
- [XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework](https://mlsanity.com/paper/2501.08809/) (2025)
- [CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval](https://mlsanity.com/paper/2304.11029/) (2023)
- [CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models](https://mlsanity.com/paper/2410.13267/) (2024)
- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)
- [Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models](https://mlsanity.com/paper/2310.14044/) (2023)
- [EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models](https://mlsanity.com/paper/2504.15133/) (2025)
- [METEOR: Melody-aware Texture-controllable Symbolic Orchestral Music Generation via Transformer VAE](https://mlsanity.com/paper/2409.11753/) (2024)
- [From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training](https://mlsanity.com/paper/2506.17497/) (2025)

## Built on by (most cited first, 3 of 3)

- [Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation](https://mlsanity.com/paper/2605.31295/) (2026)
- [Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes](https://mlsanity.com/paper/2609.04516/) (2026)
- [Harmonic Representations in Symbolic Music Transformers are Localized and Controllable](https://mlsanity.com/paper/2610.15957/) (2026)

## Abstract (arXiv)

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 creative workflows. Code and Demo are available here: https://github.com/JiangXunyi/Composer-Vector and https://jiangxunyi.github.io/composervector.github.io/