{"id":"https://openalex.org/W7166666555","doi":"https://doi.org/10.48550/arxiv.2606.30642","title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","display_name":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166666555","doi":"https://doi.org/10.48550/arxiv.2606.30642"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.30642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.30642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139682068","display_name":"Shun Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Shun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102222270","display_name":"Huaicheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Huaicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106974408","display_name":"Di Wu","orcid":"https://orcid.org/0000-0003-2169-8236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Dapeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015396622","display_name":"Yaoxun Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yaoxun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056321739","display_name":"Lishi Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Lishi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139645225","display_name":"Wei Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hangting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139665697","display_name":"Guangzheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guangzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107877612","display_name":"J. Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139676073","display_name":"Zhiyong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhiyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139702073","display_name":"Dong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.42969998717308044,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.42969998717308044,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.22210000455379486,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.12070000171661377,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4251999855041504},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.4196999967098236},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.41530001163482666},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4108999967575073},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4104999899864197},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4025000035762787},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3959999978542328},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.34940001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275000214576721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5490999817848206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.4196999967098236},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4104999899864197},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.30642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.30642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Full-length":[0],"song":[1,60],"generation":[2,145],"must":[3],"preserve":[4],"coherence":[5],"and":[6,11,14,17,45,81,138,148,173,179,190,204,224],"musicality,":[7],"render":[8],"detailed":[9],"vocal":[10,80],"accompaniment":[12,82],"acoustics,":[13],"follow":[15],"lyrics":[16],"prompts.":[18],"Existing":[19],"language":[20],"model-based":[21],"systems":[22,208],"face":[23],"a":[24,53,90],"structural":[25],"trade-off:":[26],"mixed-token":[27],"modeling":[28],"preserves":[29],"vocal-instrument":[30],"coordination":[31],"but":[32,41],"obscures":[33],"track-specific":[34,87],"details,":[35],"whereas":[36],"dual-track":[37],"prediction":[38],"improves":[39],"acoustics":[40],"requires":[42],"longer":[43],"sequences":[44],"weakens":[46],"global":[47],"planning.":[48],"We":[49],"present":[50],"LeVo":[51,62,195],"2,":[52],"hybrid":[54],"LLM-Diffusion":[55],"framework":[56,118],"for":[57,75,86,109,157],"controllable":[58],"full-length":[59,95],"generation.":[61],"2":[63,196],"formulates":[64],"this":[65,101],"trade-off":[66],"as":[67],"hierarchical":[68,225],"modeling:":[69],"LeLM":[70],"first":[71],"predicts":[72,79],"mixed":[73],"tokens":[74,83],"semantic":[76,164],"planning,":[77],"then":[78,152],"in":[84],"parallel":[85],"refinement,":[88,175],"while":[89,160],"diffusion-based":[91],"Music":[92],"Codec":[93],"reconstructs":[94],"waveforms.":[96],"A":[97],"central":[98],"contribution":[99],"of":[100,182,217],"extended":[102],"version":[103],"is":[104],"an":[105,113],"aesthetics-guided":[106],"training":[107,219],"schedule":[108,167],"alignment.":[110,130],"During":[111],"pre-training,":[112],"automated":[114],"music":[115],"aesthetic":[116],"evaluation":[117],"assigns":[119],"musicality-tier":[120],"conditions":[121],"to":[122,142],"large-scale":[123,135],"data,":[124],"providing":[125],"musicality":[126,169],"priors":[127],"before":[128],"preference":[129,185],"Progressive":[131],"post-training":[132],"applies":[133],"SFT,":[134],"offline":[136,184],"DPO,":[137],"closed-loop":[139],"semi-online":[140],"DPO":[141],"separately":[143],"improve":[144],"quality,":[146],"controllability,":[147],"musicality.":[149],"Modular":[150],"extension":[151],"trains":[153],"the":[154,162,180,215,218],"Track-Specific":[155],"LM":[156],"acoustic":[158,174],"refinement":[159],"preserving":[161],"aligned":[163],"planner.":[165],"This":[166],"separates":[168],"learning,":[170],"controllability":[171],"alignment,":[172],"mitigating":[176],"optimization":[177],"conflict":[178],"limitations":[181],"static":[183],"pairs.":[186],"Expert":[187],"listening":[188,211],"tests":[189],"objective":[191],"evaluations":[192],"show":[193],"that":[194],"outperforms":[197],"open-source":[198],"baselines":[199],"across":[200],"six":[201],"subjective":[202],"dimensions,":[203],"approaches":[205],"leading":[206],"commercial":[207],"on":[209],"several":[210],"metrics.":[212],"Ablations":[213],"validate":[214],"effects":[216],"strategy,":[220],"aesthetics":[221],"guidance,":[222],"scaling,":[223],"architecture.":[226]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-01T00:00:00"}