Papers › Content-based Controls For Music Large Language Modeling

Content-based Controls For Music Large Language Modeling

26 Oct 2023arXiv:2310.17162archive 2025-07-28

Liwei Lin, Gus Xia, Junyan Jiang, Yixiao Zhang

Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions. However, the control power of text controls on music is intrinsically limited, as they can only describe music indirectly through meta-data (such as singers and instruments) or high-level representations (such as genre and emotion). We aim to further equip the models with direct and content-based controls on innate music languages such as pitch, chords and drum track. To this end, we contribute Coco-Mulla, a content-based control method for music large language modeling. It uses a parameter-efficient fine-tuning (PEFT) method tailored for Transformer-based audio models. Experiments show that our approach achieved high-quality music generation with low-resource semi-supervised learning, tuning with less than 4% parameters compared to the original model and training on a small dataset with fewer than 300 songs. Moreover, our approach enables effective content-based controls, and we illustrate the control power via chords and rhythms, two of the most salient features of music audio. Furthermore, we show that by combining content-based controls and text descriptions, our system achieves flexible music variation generation and arrangement. Our source codes and demos are available online.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.17162")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · violated contract; 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kikyo-16/coco-mulla-repo officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
1ran · our draft was wrong
3ran
6unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from kikyo-16/coco-mulla-repo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_norm_fn kikyo-16/coco-mulla-repo/coco_mulla/models/transformer_cc.py official repository ran no licence file found · pointer only · 799fbd89d9ecbf5b · report
exists kikyo-16/coco-mulla-repo/coco_mulla/utilities/model_utils.py official repository ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report
first kikyo-16/coco-mulla-repo/coco_mulla/utilities/model_utils.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 0ff658860f6a6e4f · report
get_encodec_autoencoder kikyo-16/coco-mulla-repo/coco_mulla/models/builders_cc.py official repository ran no licence file found · pointer only · 383d03399d7ba9ee · report
get_init_fn kikyo-16/coco-mulla-repo/coco_mulla/models/lm_cc.py official repository ran no licence file found · pointer only · f09362f0b657d8b6 · report
once kikyo-16/coco-mulla-repo/coco_mulla/utilities/model_utils.py official repository ran · our draft was wrong no licence file found · pointer only · 52e10a7d6b0fa036 · report
create_sin_embedding kikyo-16/coco-mulla-repo/coco_mulla/models/transformer_cc.py official repository unverified no licence file found · pointer only · 8563f5c5fae8ad76 · report
expand_repeated_kv kikyo-16/coco-mulla-repo/coco_mulla/models/transformer_cc.py official repository unverified no licence file found · pointer only · 0627f3dc8c933828 · report
get_encodec_autoencoder kikyo-16/coco-mulla-repo/coco_mulla/audiocraft/models/builders.py official repository unverified no licence file found · pointer only · 8eeb1681acf258b7 · report
get_musicgen kikyo-16/coco-mulla-repo/coco_mulla/models/model.py official repository unverified no licence file found · pointer only · cd47db48a31b937a · report
load_compression_model kikyo-16/coco-mulla-repo/coco_mulla/models/loaders_cc.py official repository unverified no licence file found · pointer only · 4deb496341887485 · report
load_lm_model kikyo-16/coco-mulla-repo/coco_mulla/models/loaders_cc.py official repository unverified no licence file found · pointer only · 8b569f0c75f3f66d · report

Tasks

Language ModelingLanguage ModellingMusic GenerationStyle Transferparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections