# Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts

arXiv: https://arxiv.org/abs/2609.32788 · HTML: https://mlsanity.com/paper/2609.32788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [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)
- [MuPT: A Generative Symbolic Music Pretrained Transformer](https://mlsanity.com/paper/2404.06393/) (2024)
- [NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms](https://mlsanity.com/paper/2502.18008/) (2025)
- [MorpheuS: generating structured music with constrained patterns and tension](https://mlsanity.com/paper/1812.04832/) (2018)
- [TunesFormer: Forming Irish Tunes with Control Codes by Bar Patching](https://mlsanity.com/paper/2301.02884/) (2023)
- [ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis](https://mlsanity.com/paper/2510.10249/) (2025)

## Abstract (arXiv)

Deep learning has transformed symbolic music generation by borrowing the training paradigms of large language models, with systems such as NotaGen now producing complete, stylistically convincing classical scores from a short prompt. These systems could become powerful creative partners, helping musicians generate endless possibilities. However, current systems expose almost no control handles on the music itself. In principle, control handles could be built into a foundation model trained from scratch, but this is rarely practical without massive amounts of quality annotated data and compute resources. We therefore present MotiGen, a recipe for retrofitting pretrained symbolic music models to use new instruction prompts. MotiGen injects a musical motif as a structured prompt line, reinforces it with a scalar attention bias toward the motif tokens, and learns the association with a two-phase curriculum. First, it learns from focused excerpts cropped around motif occurrences in the training data, then full scores including the motifs. Our experiments show that our model composes with the prompted motif in over 92.3% of generated pieces. Generated pieces using a variety of motifs are included in our sample site: https://motigen-site.github.io/.