{"id":"https://openalex.org/W6912094964","doi":"https://doi.org/10.5281/zenodo.14877469","title":"DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation","display_name":"DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6912094964","doi":"https://doi.org/10.5281/zenodo.14877469"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877469","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877469","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zachary Novack","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zachary Novack","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julian McAuley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taylor Berg-Kirkpatrick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Nicholas J. Bryan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37193595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.8187999725341797,"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":0.8187999725341797,"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":0.051100000739097595,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.020800000056624413,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6482999920845032},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.579800009727478},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5633999705314636},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.529699981212616},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.48539999127388},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48399999737739563},{"id":"https://openalex.org/keywords/diffusion-process","display_name":"Diffusion process","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.579800009727478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5658000111579895},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.4009000062942505},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C2779429693","wikidata":"https://www.wikidata.org/wiki/Q274959","display_name":"Distilled water","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2533999979496002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877469","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877469","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877469","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877469","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Controllable":[0],"music":[1,9,70],"generation":[2,62,126,149,158],"methods":[3],"are":[4,12],"critical":[5],"for":[6,63,89,133],"human-centered":[7],"AI-based":[8],"creation,":[10],"but":[11,31,152],"currently":[13],"limited":[14],"by":[15,82],"speed,":[16],"quality,":[17],"and":[18,59,75,119,157,178],"control":[19,58,155],"design":[20],"trade-offs.":[21],"Diffusion":[22,44],"inference-time":[23,56,104],"T-optimization":[24],"(DITTO),":[25],"in":[26],"particular,":[27],"offers":[28],"state-of-the-art":[29,195],"results,":[30],"is":[32],"over":[33,150],"10x":[34],"slower":[35],"than":[36],"real-time,":[37],"limiting":[38],"practical":[39],"use.":[40],"We":[41],"propose":[42],"Distilled":[43],"Inference-Time":[45],"T":[46],"-Optimization":[47],"(or":[48],"DITTO-2),":[49],"a":[50,64,85,122,169,191],"new":[51,170],"method":[52,80,144],"to":[53,168],"speed":[54],"up":[55,148],"optimization-based":[57],"unlock":[60],"faster-than-real-time":[61],"wide-variety":[65],"of":[66,172],"applications":[67],"such":[68],"as":[69,113],"inpainting,":[71],"outpainting,":[72],"intensity,":[73],"melody,":[74],"musical":[76],"structure":[77],"control.":[78,197],"Our":[79],"works":[81],"(1)":[83],"distilling":[84],"pre-trained":[86],"diffusion":[87,185],"model":[88,109,186,192],"fast":[90],"sampling":[91,112,125],"via":[92],"an":[93,114,183],"efficient,":[94],"modified":[95],"consistency":[96,98],"or":[97],"trajectory":[99],"distillation":[100],"process":[101],"(2)":[102],"performing":[103],"optimization":[105,117],"using":[106,128],"our":[107,129,143,166],"distilled":[108],"with":[110],"one-step":[111],"efficient":[115],"surrogate":[116],"task":[118],"(3)":[120],"running":[121],"final":[123],"multi-step":[124],"(decoding)":[127],"estimated":[130],"noise":[131],"latents":[132],"best-quality,":[134],"fast,":[135],"controllable":[136],"generation.":[137],"Through":[138],"thorough":[139],"evaluation,":[140],"we":[141,164,180],"find":[142],"not":[145],"only":[146],"speeds":[147],"10-20x,":[151],"simultaneously":[153],"improves":[154],"adherence":[156,175],"quality":[159],"all":[160],"at":[161,203],"once.":[162],"Furthermore,":[163],"apply":[165],"approach":[167],"application":[171],"maximizing":[173],"text":[174,188,196],"(CLAP":[176],"score)":[177],"show":[179],"can":[181,200],"convert":[182],"unconditional":[184],"without":[187],"inputs":[189],"into":[190],"that":[193],"yields":[194],"Sound":[198],"examples":[199],"be":[201],"found":[202],"https://ditto-music.github.io/ditto2/.":[204]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}