{"id":"https://openalex.org/W7162119037","doi":"https://doi.org/10.48550/arxiv.2605.22717","title":"Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators","display_name":"Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162119037","doi":"https://doi.org/10.48550/arxiv.2605.22717"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2605.22717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136734631","display_name":"Zachary Novack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Novack, Zachary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036136865","display_name":"Stephen Brade","orcid":"https://orcid.org/0009-0005-3182-1498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brade, Stephen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136751858","display_name":"Haven Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Haven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124243768","display_name":"Hugo Flores Garc\u00eda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garc\u00eda, Hugo Flores","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053554674","display_name":"Nithya Shikarpur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shikarpur, Nithya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046046825","display_name":"Chinmay Talegaonkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talegaonkar, Chinmay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136761450","display_name":"Suwan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Suwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136781849","display_name":"Valerie K. Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Valerie K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136758267","display_name":"Julian McAuley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McAuley, Julian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136767703","display_name":"Taylor Berg-Kirkpatrick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berg-Kirkpatrick, Taylor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007555810","display_name":"Cheng-Zhi Anna Huang","orcid":"https://orcid.org/0009-0009-4194-0393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Cheng-Zhi Anna","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/T11349","display_name":"Music Technology and Sound Studies","score":0.9505000114440918,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9505000114440918,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01269999984651804,"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/T11309","display_name":"Music and Audio Processing","score":0.008899999782443047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5745999813079834},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5367000102996826},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.527400016784668},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5160999894142151},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/improvisation","display_name":"Improvisation","score":0.45320001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060999870300293},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5160999894142151},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C125468537","wikidata":"https://www.wikidata.org/wiki/Q214961","display_name":"Improvisation","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C34259666","wikidata":"https://www.wikidata.org/wiki/Q1122550","display_name":"Computer music","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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":{"Interactive":[0],"streaming":[1],"music":[2,174],"generation":[3],"promises":[4],"the":[5,26,53,77,112,121,125,160],"use":[6],"of":[7,32,111,124,162,167],"generative":[8,113,188],"models":[9,23,66],"for":[10,34,80,206],"live":[11,205],"performance":[12],"and":[13,37,118,176],"co-creation":[14],"that":[15,90,116],"is":[16],"impossible":[17],"with":[18,48],"offline":[19],"models.":[20,157],"However,":[21],"SOTA":[22],"exist":[24],"in":[25,52,92,164,190],"discrete-AR":[27,99],"regime,":[28],"requiring":[29],"industrial":[30],"levels":[31],"compute":[33],"both":[35],"training":[36],"inference.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,84],"investigate":[43],"whether":[44],"audio":[45],"diffusion":[46,114],"models,":[47],"their":[49,98],"wide":[50],"support":[51],"open-source":[54],"community":[55],"but":[56],"non-streaming":[57],"bidirectional":[58],"nature,":[59],"can":[60,183],"be":[61,184],"repurposed":[62],"efficiently":[63],"into":[64],"interactive":[65],"accessible":[67],"on":[68,213],"consumer":[69,215],"hardware.":[70],"By":[71],"taking":[72],"a":[73,108,165,187,191,198,214],"critical":[74,86],"look":[75],"at":[76],"modern":[78],"pipeline":[79],"block-wise":[81,132],"outpainting":[82],"diffusion,":[83],"identify":[85],"inefficiencies":[87],"during":[88],"inference":[89,122],"result":[91],"strictly":[93],"worse":[94],"computational":[95],"efficiency":[96],"than":[97],"counterparts.":[100],"We":[101,158,178],"propose":[102],"Live":[103,127],"Music":[104,128],"Diffusion":[105],"Models":[106,129],"(LMDMs),":[107],"simple":[109],"modification":[110],"process":[115],"recovers,":[117],"then":[119],"outperforms,":[120],"complexity":[123],"discrete":[126],"(LMMs)":[130],"through":[131,143],"KV":[133],"Caching.":[134],"Unlike":[135],"LMMs,":[136],"LMDMs":[137,163,182,196],"further":[138],"enable":[139],"stable":[140],"post-training":[141],"alignment":[142],"our":[144],"novel":[145],"ARC-Forcing":[146],"paradigm,":[147],"reducing":[148],"error":[149],"accumulation":[150],"without":[151],"any":[152],"explicit":[153],"RL":[154],"or":[155],"reward":[156],"demonstrate":[159],"application":[161],"number":[166],"creative":[168],"domains,":[169],"including":[170],"text-conditioned":[171],"generation,":[172],"sketch-based":[173],"synthesis,":[175],"jamming.":[177],"finally":[179],"show":[180],"how":[181],"used":[185],"as":[186,197],"instrument":[189],"real":[192],"artist-AI":[193],"collaboration,":[194],"utilizing":[195],"\"generative":[199],"delay\"":[200],"to":[201],"transform":[202],"musicians'":[203],"improvisation":[204],"variable":[207],"timbral":[208],"effects":[209],"while":[210],"running":[211],"locally":[212],"gaming":[216],"laptop.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}