Papers › MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models

MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models

9 Dec 2024arXiv:2412.06660links table onlyarchive 2025-07-28

Shansong Liu, Atin Sakkeer Hussain, Qilong Wu, Chenshuo Sun, Ying Shan

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Research on large language models has advanced significantly across text, speech, images, and videos. However, multi-modal music understanding and generation remain underexplored due to the lack of well-annotated datasets. To address this, we introduce a dataset with 167.69 hours of multi-modal data, including text, images, videos, and music annotations. Based on this dataset, we propose MuMu-LLaMA, a model that leverages pre-trained encoders for music, images, and videos. For music generation, we integrate AudioLDM 2 and MusicGen. Our evaluation across four tasks--music understanding, text-to-music generation, prompt-based music editing, and multi-modal music generation--demonstrates that MuMu-LLaMA outperforms state-of-the-art models, showing its potential for multi-modal music applications.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 10 ran (4 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

shansongliu/MuMu-LLaMA officialmentioned on GitHubjaxMITSyntology: 7 samples, 7 ran (4 instrument-failed) · 0 unverified report
shansongliu/M2UGen mentioned on GitHubjaxMITSyntology: 12 samples, 10 ran (6 instrument-failed) · 2 unverified 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

19 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
9ran · our draft was wrong
1ran; the contract check could not run
5ran
2unverified

Licence: 5 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

shansongliu/MuMu-LLaMA official repository 7 samples, 7 ran (4 instrument-failed) · 0 unverified
add_special_tokens MuMu-LLaMA/llama/audioldm2/modeling_audioldm2.py ran MIT (permissive) · cec37d613e438bcc · report fixture: signature hidden_states:Tensor/3/float, attention_mask:Tensor/2/int, sos_token:Tensor/2/float, eos_token:Tensor/2/float · returned tuple · level recorded 2026-09-25
adjust_learning_rate in 125 papers MuMu-LLaMA/util/lr_sched.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · bd3578806ecf5ac2 · report fixture: signature optimizer:SGD/0/?, epoch:int/0/int, args:Args/0/? · returned float · level recorded, date not recorded
apply_rotary_emb in 121 papers MuMu-LLaMA/llama/llama.py ran · our draft was wrong MIT (permissive) · c2fac4e6b301302f · report fixture: signature xq:Tensor/3/float, xk:Tensor/3/float, freqs_cis:Tensor/2/complex · returned tuple · level recorded 2026-09-25
format_prompt in 45 papers MuMu-LLaMA/llama/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · fa5a132156cdaf6d · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-25
precompute_freqs_cis in 112 papers MuMu-LLaMA/llama/llama.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 14a84c2cbfebc413 · report fixture: signature dim:int/0/int, end:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-22
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input
MuMu-LLaMA/llama/llama.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 70bf6ebaafd266c4 · report fixture: signature freqs_cis:Tensor/2/float, x:Tensor/4/float · returned Tensor · level recorded, date not recorded
sample_top_p in 35 papers MuMu-LLaMA/llama/utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 8845976729f4c4ee · report fixture: signature probs:Tensor/2/float, p:float/0/float · returned Tensor · level recorded 2026-09-22
shansongliu/M2UGen community (archive-listed) 12 samples, 10 ran (6 instrument-failed) · 2 unverified
generate_text in 20 papers DataSet/MUEdit/mistral.py ran MIT (permissive) · f016081a436c0aff · report fixture: signature model:callable/0/?, tokenizer:MockTokenizer/0/?, device:device/0/?, prompt:str/0/str, max_length:int/0/int, temperature:float/0/float, top_p:float/0/float, top_k:int/0/int, num_return_sequences:int/0/int, max_new_tokens:int/0/int · returned list · level recorded 2026-09-25
get_audio_list DataSet/MUEdit/prepare.py ran · our draft was wrong fingerprinted MIT (permissive) · bd7422108ba38202 · report fixture: signature dir_path:str/0/str · returned dict · level recorded 2026-09-25
load_json in 344 papers DataSet/MUEdit/prepare.py ran · our draft was wrong MIT (permissive) · 67c2fccdb8646607 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
load_json in 344 papers DataSet/MUImage/llava_caption.py ran · our draft was wrong MIT (permissive) · 4d1ebce7f6f7cc0e · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-25
load_jsonl in 179 papers DataSet/MUImage/llava_caption.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9eb0b14fc790de41 · report fixture: signature file_path:str/0/str · returned list · level recorded 2026-09-22
pack_to_metadata DataSet/MUEdit/prepare.py ran MIT (permissive) · a691506445cd09a5 · report fixture: signature data:dict/0/?, music_dir:str/0/str · returned list · level recorded 2026-09-25
parse_text in 15 papers MuMu-LLaMA/gradio_app.py ran MIT (permissive) · a5a8373f8eeb0e5b · report fixture: signature text:str/0/str, image_path:NoneType/0/?, video_path:NoneType/0/?, audio_path:NoneType/0/? · returned tuple · level recorded 2026-09-25
prompt1 DataSet/MUEdit/mistral.py ran · our draft was wrong fingerprinted MIT (permissive) · 757329bc69615251 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-25
read_video_pyav Evaluation/Video2Music/generate_m2ugen.py ran · our draft was wrong MIT (permissive) · a9873e075389c691 · report fixture: signature container:MockContainer/0/?, indices:list/1/int · returned ndarray · level recorded 2026-09-25
sample_frame_indices Evaluation/Video2Music/generate_m2ugen.py ran MIT (permissive) · 6378137c116ad6da · report fixture: signature clip_len:int/0/int, frame_sample_rate:float/0/float, seg_len:int/0/int · returned ndarray · level recorded 2026-09-25
load_model in 479 papers DataSet/MUEdit/mistral.py unverified MIT (permissive) · 08e8f3d4af99bdb4 · report
load_model in 479 papers DataSet/MUImage/llava_caption.py unverified MIT (permissive) · 11e5e8810f15e38a · report

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