# Segment-Factorized Full-Song Generation on Symbolic Piano Music

arXiv: https://arxiv.org/abs/2510.05881 · HTML: https://mlsanity.com/paper/2510.05881/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [DeepBach: a Steerable Model for Bach Chorales Generation](https://mlsanity.com/paper/1612.01010/) (2016)
- [The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures](https://mlsanity.com/paper/2008.01307/) (2020)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls](https://mlsanity.com/paper/2307.10304/) (2023)
- [Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models](https://mlsanity.com/paper/2405.09901/) (2024)
- [AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfer](https://mlsanity.com/paper/2108.11213/) (2021)
- [Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach](https://mlsanity.com/paper/2209.08212/) (2022)
- [PiCoGen: Generate Piano Covers with a Two-stage Approach](https://mlsanity.com/paper/2407.20883/) (2024)
- [PiCoGen2: Piano cover generation with transfer learning approach and weakly aligned data](https://mlsanity.com/paper/2408.01551/) (2024)
- [Melody Infilling with User-Provided Structural Context](https://mlsanity.com/paper/2210.02829/) (2022)
- [Diffusion-based Symbolic Music Generation with Structured State Space Models](https://mlsanity.com/paper/2507.20128/) (2025)

## Built on by (most cited first, 2 of 2)

- [PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation](https://mlsanity.com/paper/2512.11348/) (2025)
- [Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation](https://mlsanity.com/paper/2608.03999/) (2026)

## Abstract (arXiv)

We propose the Segmented Full-Song Model (SFS) for symbolic full-song generation. The model accepts a user-provided song structure and an optional short seed segment that anchors the main idea around which the song is developed. By factorizing a song into segments and generating each one through selective attention to related segments, the model achieves higher quality and efficiency compared to prior work. To demonstrate its suitability for human-AI interaction, we further wrap SFS into a web application that enables users to iteratively co-create music on a piano roll with customizable structures and flexible ordering.