{"id":"https://openalex.org/W7165396365","doi":"https://doi.org/10.48550/arxiv.2606.20101","title":"RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers","display_name":"RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165396365","doi":"https://doi.org/10.48550/arxiv.2606.20101"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.20101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20101","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":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.2606.20101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050706055","display_name":"Liting Gao","orcid":"https://orcid.org/0009-0004-6659-382X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Liting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021436608","display_name":"Y C Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yonggang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138984120","display_name":"Yaru Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yaru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764278","display_name":"Dongyu Wang","orcid":"https://orcid.org/0000-0001-6751-3589"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101962292","display_name":"Shubin Zhang","orcid":"https://orcid.org/0000-0002-7985-4898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shubin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138972733","display_name":"Zhenbo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061857063","display_name":"Jean\u2010Yves Guillemaut","orcid":"https://orcid.org/0000-0001-8223-5505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillemaut, Jean-Yves","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138969832","display_name":"Wenwu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenwu","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":0.4284000098705292,"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":0.4284000098705292,"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/T11439","display_name":"Video Analysis and Summarization","score":0.11339999735355377,"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/T10860","display_name":"Speech and Audio Processing","score":0.09989999979734421,"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/transformer","display_name":"Transformer","score":0.6883999705314636},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.40849998593330383},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3662000000476837},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3188000023365021},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3156999945640564},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.30809998512268066},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3050000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320000171661377},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6883999705314636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.30809998512268066},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C107958047","wikidata":"https://www.wikidata.org/wiki/Q1413664","display_name":"Audio frequency","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.20101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20101","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":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.2606.20101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20101","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41417673230171204,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"editing":[1,34,76,110,120,168,196,208],"aims":[2],"to":[3,13,105,149,160,166],"modify":[4],"specific":[5],"content":[6],"in":[7,46,96,100],"an":[8],"existing":[9,32,75],"audio":[10,92,119,145,182,200],"clip":[11],"according":[12],"a":[14,80,116,133],"text":[15,94,147],"instruction":[16],"or":[17],"description":[18],"while":[19,205],"preserving":[20],"the":[21,26,39,155,171,187],"remaining":[22],"acoustic":[23],"content.":[24],"Despite":[25],"remarkable":[27],"progress":[28],"of":[29,61,83],"diffusion":[30,65,84,136],"models,":[31],"training-based":[33],"methods":[35],"mainly":[36],"rely":[37],"on":[38,123,132,194],"local":[40],"inductive":[41],"biases":[42],"and":[43,56,59,71,93,112,146,163,179,202],"cross-attention":[44,164],"interaction":[45],"convolutional":[47],"U-Net":[48],"backbones,":[49],"which":[50],"often":[51],"hinder":[52],"long-range":[53],"semantic":[54,152],"alignment":[55,153],"precise":[57],"understanding":[58],"localization":[60],"instructions.":[62],"In":[63],"contrast,":[64],"transformers":[66],"provide":[67],"stronger":[68],"global":[69],"modeling":[70],"multimodal":[72],"fusion,":[73],"but":[74],"architectures":[77],"usually":[78],"adopt":[79],"simple":[81],"stack":[82],"transformer":[85],"blocks.":[86],"Applying":[87],"joint":[88,142],"attention":[89,143],"over":[90,144],"concatenated":[91],"tokens":[95,148],"all":[97],"blocks":[98,165],"results":[99],"quadratic":[101],"complexity":[102],"with":[103],"respect":[104],"token":[106],"length.":[107],"To":[108],"balance":[109],"performance":[111,192],"efficiency,":[113],"we":[114],"propose":[115],"novel":[117],"instruction-guided":[118,181],"framework":[121,189],"based":[122],"rectified":[124],"flow":[125],"matching":[126],"(RFM),":[127],"named":[128],"RFM-Editing":[129],"2,":[130],"built":[131],"hybrid":[134],"two-stage":[135],"transformer.":[137],"The":[138],"proposed":[139,188],"model":[140],"performs":[141],"establish":[150],"coarse":[151],"at":[154,170],"low-resolution":[156],"stage,":[157],"then":[158],"switches":[159],"alternating":[161],"joint-attention":[162],"refine":[167],"details":[169],"high-resolution":[172],"stage.":[173],"This":[174],"coarse-to-fine":[175],"strategy":[176],"enables":[177],"efficient":[178],"accurate":[180],"editing.":[183],"Experiments":[184],"show":[185],"that":[186],"achieves":[190],"notable":[191],"gains":[193],"challenging":[195],"tasks":[197],"involving":[198],"overlapping":[199],"events":[201],"complex":[203],"instructions,":[204],"substantially":[206],"improving":[207],"efficiency.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-20T00:00:00"}