mlsanityData to 14 Oct 2026

Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling

arXiv 2301.12525 ↗First posted 29 Jan 2023cs.SD cs.LG eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

We introduce Composer's Assistant, a system for interactive human-computer composition in the REAPER digital audio workstation. We consider the task of multi-track MIDI infilling when arbitrary track-measures have been deleted from a contiguous slice of measures from a MIDI file, and we train a T5-like model to accomplish this task. Composer's Assistant consists of this model together with scripts that enable interaction with the model in REAPER. We conduct objective and subjective tests of our model. We release our complete system, consisting of source code, pretrained models, and REAPER scripts. Our models were trained only on permissively-licensed MIDI files.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 29 Jan 2023.

Builds on

26 of 42 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  6. 2020GLU Variants Improve Transformercited by 1,804
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  8. 2021Symbolic Music Generation with Diffusion Modelscited by 154
  9. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  10. 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 110
  11. 2022Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?cited by 103
  12. 2016DeepBach: a Steerable Model for Bach Chorales Generationcited by 91
14 more
  1. 2021MT3: Multi-Task Multitrack Music Transcriptioncited by 71
  2. 2019LakhNES: Improving multi-instrumental music generation with cross-domain pre-trainingcited by 54
  3. 2020The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measurescited by 53
  4. 2020MMM : Exploring Conditional Multi-Track Music Generation with the Transformercited by 49
  5. 2019Counterpoint by Convolutioncited by 43
  6. 2022Investigating Efficiently Extending Transformers for Long Input Summarizationcited by 43
  7. 2022Symphony Generation with Permutation Invariant Language Modelcited by 35
  8. 2020Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythmcited by 28
  9. 2019Learning to Traverse Latent Spaces for Musical Score Inpaintingcited by 24
  10. 2021The Piano Inpainting Applicationcited by 23
  11. 2022MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Controlcited by 17
  12. 2021Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encodingcited by 14
  13. 2019NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpaintingcited by 10
  14. 2022The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modelingcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Controlcited by 5
  2. 2025Hookpad Aria: A Copilot for Songwriterscited by 4
  3. 2024Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenizationcited by 3
  4. 2025Adaptable Symbolic Music Infilling with MIDI-RWKVcited by 2
  5. 2025MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Modelscited by 1
  6. 2026Stemphonic: All-at-once Flexible Multi-stem Music Generationcited by 1
  7. 2025TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structurecited by 0
  8. 2025Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networkscited by 0
  9. 2026From One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editingcited by 0