# Genre Controlled Music Generation via Activation Steering

arXiv: https://arxiv.org/abs/2506.10225 · HTML: https://mlsanity.com/paper/2506.10225/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Mustango: Toward Controllable Text-to-Music Generation](https://mlsanity.com/paper/2311.08355/) (2023)
- [MuseCoco: Generating Symbolic Music from Text](https://mlsanity.com/paper/2306.00110/) (2023)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation](https://mlsanity.com/paper/2406.10970/) (2024)
- [SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers](https://mlsanity.com/paper/2404.02252/) (2024)
- [Activation Patching for Interpretable Steering in Music Generation](https://mlsanity.com/paper/2504.04479/) (2025)

## Built on by (most cited first, 1 of 1)

- [Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation](https://mlsanity.com/paper/2606.18790/) (2026)

## Abstract (arXiv)

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.