# MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition

arXiv: https://arxiv.org/abs/2501.17011 · HTML: https://mlsanity.com/paper/2501.17011/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2025.

## Built on by (most cited first, 8 of 8)

- [Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment](https://mlsanity.com/paper/2505.12669/) (2025)
- [Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes](https://mlsanity.com/paper/2505.15559/) (2025)
- [Adaptable Symbolic Music Infilling with MIDI-RWKV](https://mlsanity.com/paper/2506.13001/) (2025)
- [PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation](https://mlsanity.com/paper/2512.11348/) (2025)
- [BMdataset: A Musicologically Curated LilyPond Dataset](https://mlsanity.com/paper/2604.10628/) (2026)
- [How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness](https://mlsanity.com/paper/2608.18025/) (2026)
- [From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editing](https://mlsanity.com/paper/2609.34994/) (2026)
- [Harmonic Representations in Symbolic Music Transformers are Localized and Controllable](https://mlsanity.com/paper/2610.15957/) (2026)

## Abstract (arXiv)

We present and release MIDI-GPT, a generative system based on the Transformer architecture that is designed for computer-assisted music composition workflows. MIDI-GPT supports the infilling of musical material at the track and bar level, and can condition generation on attributes including: instrument type, musical style, note density, polyphony level, and note duration. In order to integrate these features, we employ an alternative representation for musical material, creating a time-ordered sequence of musical events for each track and concatenating several tracks into a single sequence, rather than using a single time-ordered sequence where the musical events corresponding to different tracks are interleaved. We also propose a variation of our representation allowing for expressiveness. We present experimental results that demonstrate that MIDI-GPT is able to consistently avoid duplicating the musical material it was trained on, generate music that is stylistically similar to the training dataset, and that attribute controls allow enforcing various constraints on the generated material. We also outline several real-world applications of MIDI-GPT, including collaborations with industry partners that explore the integration and evaluation of MIDI-GPT into commercial products, as well as several artistic works produced using it.