{"id":"https://openalex.org/W7137884546","doi":"https://doi.org/10.1609/aaai.v40i10.37719","title":"X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning","display_name":"X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137884546","doi":"https://doi.org/10.1609/aaai.v40i10.37719"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37719","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37719","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37719/41681","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37719/41681","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129681795","display_name":"Jian Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Ma","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069331403","display_name":"Xujie Zhu","orcid":"https://orcid.org/0000-0003-4547-2039"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xujie Zhu","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672916","display_name":"Zihao Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Pan","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663177","display_name":"Qirong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirong Peng","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722475","display_name":"Xu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Guo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653544","display_name":"Chen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129693160","display_name":"Haonan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7764","last_page":"7772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22920000553131104,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22920000553131104,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.09889999777078629,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.039500001817941666,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.8988999724388123},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.704200029373169},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5414999723434448},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5393999814987183},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3801000118255615}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8988999724388123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468000292778015},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5414999723434448},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37719","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37719","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37719/41681","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37719","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37719","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37719/41681","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47877034544944763,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137884546.pdf","grobid_xml":"https://content.openalex.org/works/W7137884546.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"open-source":[1,166],"datasets":[2],"for":[3],"arbitrary-instruction":[4],"image":[5,47,94,136],"editing":[6,12,37,61,137,149],"remain":[7],"suboptimal,":[8],"while":[9],"a":[10,31,76],"plug-and-play":[11],"module":[13],"compatible":[14],"with":[15,63,84,92,105],"community-prevalent":[16],"generative":[17],"models":[18,49,52],"is":[19,151],"notably":[20],"absent.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,58,78,97,121],"first":[26],"introduce":[27,140],"the":[28,44,55,64,73,109,112,118,123,127,147,158],"X2Edit":[29],"Dataset,":[30],"comprehensive":[32],"dataset":[33,160],"covering":[34],"14":[35],"diverse":[36],"tasks,":[38],"including":[39],"subject-driven":[40],"generation.":[41],"We":[42],"utilize":[43,122],"industry-leading":[45],"unified":[46],"generation":[48,95],"and":[50,66,130],"expert":[51],"to":[53,71,88,139],"construct":[54,79],"data.":[56,74],"Meanwhile,":[57],"design":[59,98],"reasonable":[60],"instructions":[62],"VLM":[65],"implement":[67],"various":[68],"scoring":[69],"mechanisms":[70],"filter":[72],"As":[75],"result,":[77],"3.7":[80],"million":[81],"high-quality":[82],"data":[83],"balanced":[85],"categories.":[86],"Second,":[87],"better":[89],"integrate":[90],"seamlessly":[91],"community":[93],"models,":[96],"task-aware":[99],"MoE-LoRA":[100],"training":[101],"based":[102,134],"on":[103,135],"FLUX.1,":[104],"only":[106],"8%":[107],"of":[108,111,126],"parameters":[110],"full":[113],"model.":[114],"To":[115],"further":[116],"improve":[117],"final":[119],"performance,":[120],"internal":[124],"representations":[125],"diffusion":[128],"model":[129],"define":[131],"positive/negative":[132],"samples":[133],"types":[138],"contrastive":[141],"learning.":[142],"Extensive":[143],"experiments":[144],"demonstrate":[145],"that":[146],"model's":[148],"performance":[150],"competitive":[152],"among":[153],"many":[154],"excellent":[155],"models.":[156],"Additionally,":[157],"constructed":[159],"exhibits":[161],"substantial":[162],"advantages":[163],"over":[164],"existing":[165],"datasets.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}