# BeatEdit: Symbolic Music Generation as Explicit Editing

arXiv: https://arxiv.org/abs/2607.11124 · HTML: https://mlsanity.com/paper/2607.11124/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training](https://mlsanity.com/paper/2106.05630/) (2021)
- [Learning Multimodal Graph-to-Graph Translation for Molecular Optimization](https://mlsanity.com/paper/1812.01070/) (2018)
- [Parallel Iterative Edit Models for Local Sequence Transduction](https://mlsanity.com/paper/1910.02893/) (2019)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [CoEdIT: Text Editing by Task-Specific Instruction Tuning](https://mlsanity.com/paper/2305.09857/) (2023)
- [Felix: Flexible Text Editing Through Tagging and Insertion](https://mlsanity.com/paper/2003.10687/) (2020)
- [Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion](https://mlsanity.com/paper/2402.14285/) (2024)
- [MuseCoco: Generating Symbolic Music from Text](https://mlsanity.com/paper/2306.00110/) (2023)
- [Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls](https://mlsanity.com/paper/2307.10304/) (2023)
- [miditok: A Python package for MIDI file tokenization](https://mlsanity.com/paper/2310.17202/) (2023)
- [The Piano Inpainting Application](https://mlsanity.com/paper/2107.05944/) (2021)
- [MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control](https://mlsanity.com/paper/2202.05528/) (2022)
- [Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation](https://mlsanity.com/paper/2412.07948/) (2024)
- [Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding](https://mlsanity.com/paper/2108.05064/) (2021)
- [Symbolic Music Representations for Classification Tasks: A Systematic Evaluation](https://mlsanity.com/paper/2309.02567/) (2023)
- [BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps](https://mlsanity.com/paper/2604.19532/) (2026)

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

- [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)

## Abstract (arXiv)

Music creation is fundamentally a process of revision. Yet symbolic music generation remains dominated by paradigms that produce complete sequences from scratch, with limited support for selective modification. Edit-based methods have proven effective for text transformation tasks, but remain largely unexplored for symbolic music. We trace this absence to the representational level: conventional event-based music encodings lack the structural properties required by explicit music editing. In contrast, the BEAT encoding, a beat-grid-anchored representation originally designed for autoregressive generation, possesses structural properties amenable to editing. We propose BeatEdit, the first framework for symbolic music generation based on explicit edit operations, recasting generation as producing new content by editing a draft rather than synthesizing from scratch. BeatEdit comprises three complementary mechanisms along an axis of increasing edit density: per-token sequence tagging for error correction, iterative refinement for accompaniment editing, and tag-then-fill for segment completion. All these mechanisms share a single encoding and pre-trained backbone, achieving higher precision and perceptual quality than autoregressive and diffusion methods across all three tasks, while remaining efficient, with single-pass inference completing in under 100 ms. Cross-encoding evaluation further reveals that encoding design substantially influences editing effectiveness, with notable encoding-method interaction effects. Code is available at https://github.com/Haoyu-Gu/BeatEdit-code