{"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/levo-high-quality-song-generation-with-multi","title":"LeVo: High-Quality Song Generation with Multi-Preference Alignment","arxiv_id":"2506.07520","date":"2025-06-09","proceeding":null,"authors":["Shun Lei","Yaoxun Xu","Zhiwei Lin","Huaicheng Zhang","Wei Tan","Hangting Chen","Jianwei Yu","Yixuan Zhang","Chenyu Yang","Haina Zhu","Shuai Wang","Zhiyong Wu","Dong Yu"],"abstract":"Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in sound quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, an LM-based framework consisting of LeLM and a music codec. LeLM is capable of parallelly modeling two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and DPO post-training. Experimental results demonstrate that LeVo consistently outperforms existing methods on both objective and subjective metrics. Ablation studies further justify the effectiveness of our designs. Audio examples are available at https://levo-demo.github.io/. Code is released at https://github.com/tencent-ailab/songgeneration.","url_abs":"https://arxiv.org/abs/2506.07520v2","url_pdf":"https://arxiv.org/pdf/2506.07520v2.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":"abstracts"},"code_links":[{"paper_slug":"levo-high-quality-song-generation-with-multi","repo_url":"https://github.com/tencent-ailab/songgeneration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"music-generation","task_name":"Music Generation"}],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.07520","atlas_url":"https://app.syntology.ai/?focus=2506.07520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07520"}},"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":"deterministic:regex_extraction","url":"https://github.com/tencent-ailab/songgeneration","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"community":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"f1a2ea781d07a5ee","entry":"get_id_from_path","repo":"RifleZhang/LLaVA-Hound-DPO","repo_kind":"community","path":"llava_hound_dpo/inference/inference.py","file_url":"https://github.com/RifleZhang/LLaVA-Hound-DPO/blob/HEAD/llava_hound_dpo/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1a2ea781d07a5ee"}},{"code_sha256_prefix":"4354061aab23f5b9","entry":"remove_special_tokens","repo":"RifleZhang/LLaVA-Hound-DPO","repo_kind":"community","path":"llava_hound_dpo/inference/inference.py","file_url":"https://github.com/RifleZhang/LLaVA-Hound-DPO/blob/HEAD/llava_hound_dpo/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4354061aab23f5b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}