{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mumu-llama-multi-modal-music-understanding","title":"MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models","arxiv_id":"2412.06660","date":"2024-12-09","proceeding":null,"authors":["Shansong Liu","Atin Sakkeer Hussain","Qilong Wu","Chenshuo Sun","Ying Shan"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2412.06660v1","url_pdf":"https://arxiv.org/pdf/2412.06660v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"mumu-llama-multi-modal-music-understanding","repo_url":"https://github.com/shansongliu/MuMu-LLaMA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mumu-llama-multi-modal-music-understanding","repo_url":"https://github.com/shansongliu/M2UGen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.06660","atlas_url":"https://app.syntology.ai/?focus=2412.06660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06660"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shansongliu/M2UGen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shansongliu/MuMu-LLaMA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"ran_violates":1,"ran_fixture":1,"unverified":14},"by_repo_kind":{"official":{"samples":7,"ran":4,"repositories":1},"listed":{"samples":12,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bd3578806ecf5ac2","entry":"adjust_learning_rate","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/util/lr_sched.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/util/lr_sched.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3578806ecf5ac2"}},{"code_sha256_prefix":"9eb0b14fc790de41","entry":"load_jsonl","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUImage/llava_caption.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUImage/llava_caption.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9eb0b14fc790de41"}},{"code_sha256_prefix":"14a84c2cbfebc413","entry":"precompute_freqs_cis","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/llama.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/llama.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"code_sha256_prefix":"70bf6ebaafd266c4","entry":"reshape_for_broadcast","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/llama.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/llama.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70bf6ebaafd266c4"}},{"code_sha256_prefix":"8845976729f4c4ee","entry":"sample_top_p","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/utils.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8845976729f4c4ee"}},{"code_sha256_prefix":"cec37d613e438bcc","entry":"add_special_tokens","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/audioldm2/modeling_audioldm2.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/audioldm2/modeling_audioldm2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cec37d613e438bcc"}},{"code_sha256_prefix":"c2fac4e6b301302f","entry":"apply_rotary_emb","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/llama.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2fac4e6b301302f"}},{"code_sha256_prefix":"fa5a132156cdaf6d","entry":"format_prompt","repo":"shansongliu/MuMu-LLaMA","repo_kind":"official","path":"MuMu-LLaMA/llama/utils.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa5a132156cdaf6d"}},{"code_sha256_prefix":"f016081a436c0aff","entry":"generate_text","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/mistral.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/mistral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f016081a436c0aff"}},{"code_sha256_prefix":"bd7422108ba38202","entry":"get_audio_list","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/prepare.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/prepare.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd7422108ba38202"}},{"code_sha256_prefix":"67c2fccdb8646607","entry":"load_json","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/prepare.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/prepare.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67c2fccdb8646607"}},{"code_sha256_prefix":"4d1ebce7f6f7cc0e","entry":"load_json","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUImage/llava_caption.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUImage/llava_caption.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d1ebce7f6f7cc0e"}},{"code_sha256_prefix":"08e8f3d4af99bdb4","entry":"load_model","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/mistral.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/mistral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08e8f3d4af99bdb4"}},{"code_sha256_prefix":"11e5e8810f15e38a","entry":"load_model","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUImage/llava_caption.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUImage/llava_caption.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11e5e8810f15e38a"}},{"code_sha256_prefix":"a691506445cd09a5","entry":"pack_to_metadata","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/prepare.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/prepare.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a691506445cd09a5"}},{"code_sha256_prefix":"a5a8373f8eeb0e5b","entry":"parse_text","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"MuMu-LLaMA/gradio_app.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/MuMu-LLaMA/gradio_app.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5a8373f8eeb0e5b"}},{"code_sha256_prefix":"757329bc69615251","entry":"prompt1","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"DataSet/MUEdit/mistral.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/mistral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"757329bc69615251"}},{"code_sha256_prefix":"a9873e075389c691","entry":"read_video_pyav","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"Evaluation/Video2Music/generate_m2ugen.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/Evaluation/Video2Music/generate_m2ugen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9873e075389c691"}},{"code_sha256_prefix":"6378137c116ad6da","entry":"sample_frame_indices","repo":"shansongliu/M2UGen","repo_kind":"listed","path":"Evaluation/Video2Music/generate_m2ugen.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/Evaluation/Video2Music/generate_m2ugen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6378137c116ad6da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}