{"id":"https://openalex.org/W7133212376","doi":"https://doi.org/10.1145/3797956","title":"HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads","display_name":"HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133212376","doi":"https://doi.org/10.1145/3797956"},"language":"en","primary_location":{"id":"doi:10.1145/3797956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797956","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3797956","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127808895","display_name":"Yu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xu","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0003-3459-5455","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127820392","display_name":"Fan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Tang","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-3975-2483","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juan Cao","orcid":"https://orcid.org/0000-0002-7857-1546"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Cao","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-7857-1546","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127859003","display_name":"Xiaoyu Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Kong","raw_affiliation_strings":["Beihang University"],"raw_orcid":"https://orcid.org/0009-0004-1386-9394","affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398013","display_name":"Yuxin Zhang","orcid":"https://orcid.org/0000-0001-6433-2678"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Zhang","raw_affiliation_strings":["NLPR, Chinese Academy of Sciences Institute of Automation","School of Artificial Intelligence, University of the Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0001-6433-2678","affiliations":[{"raw_affiliation_string":"NLPR, Chinese Academy of Sciences Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127839851","display_name":"Jintao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Li","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-4597-8534","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036489223","display_name":"Oliver Deu\u00dfen","orcid":"https://orcid.org/0000-0001-5803-2185"},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Deussen","raw_affiliation_strings":["Universit\u00e4t Konstanz"],"raw_orcid":"https://orcid.org/0000-0001-5803-2185","affiliations":[{"raw_affiliation_string":"Universit\u00e4t Konstanz","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127798493","display_name":"Tong-Yee Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tong-Yee Lee","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":"https://orcid.org/0000-0001-6699-2944","affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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":0.254561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"3","first_page":"1","last_page":"14"},"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":0.8449000120162964,"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":0.8449000120162964,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05119999870657921,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.008100000210106373,"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":0.8504999876022339},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5972999930381775},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5800999999046326},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5594000220298767},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49000000953674316},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45890000462532043},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4237000048160553},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4162999987602234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574000000953674},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8504999876022339},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5800999999046326},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45890000462532043},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4237000048160553},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.305400013923645},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C65377053","wikidata":"https://www.wikidata.org/wiki/Q1572121","display_name":"Image file formats","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797956","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3797956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797956","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2028657573","display_name":null,"funder_award_id":"Z251100008125009","funder_id":"https://openalex.org/F4320335843","funder_display_name":"Beijing Science and Technology Planning Project"},{"id":"https://openalex.org/G2543158275","display_name":"Embodied agents in contemporary visual art (EACVA): How robotics and A.I. could influence creativity","funder_award_id":"508324734","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8887096489","display_name":null,"funder_award_id":"62572458","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335843","display_name":"Beijing Science and Technology Planning Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W4312933868","https://openalex.org/W4385527149","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390872297","https://openalex.org/W4390873195","https://openalex.org/W4396812217","https://openalex.org/W4400573550","https://openalex.org/W4400582020","https://openalex.org/W4402715857","https://openalex.org/W4402753860","https://openalex.org/W4402753991","https://openalex.org/W4402775818","https://openalex.org/W4403941572","https://openalex.org/W4405003063","https://openalex.org/W6912494966"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"Transformers":[1],"(DiTs)":[2],"have":[3],"exhibited":[4],"robust":[5],"capabilities":[6],"in":[7,48,98,127],"image":[8,14,70,80,87,133],"generation":[9],"tasks.":[10],"However,":[11],"accurate":[12,117],"text-guided":[13],"editing":[15,81,130],"for":[16,33,40,112],"multimodal":[17],"DiTs":[18],"(MM-DiTs)":[19],"still":[20],"poses":[21],"a":[22,78,103],"significant":[23],"challenge.":[24],"Unlike":[25],"UNet-based":[26],"structures":[27],"that":[28,83],"could":[29],"utilize":[30],"self/cross-attention":[31],"maps":[32],"semantic":[34,49,114],"editing,":[35],"MM-DiTs":[36,73],"inherently":[37],"lack":[38],"support":[39],"explicit":[41],"and":[42,55,74,116,132],"consistent":[43],"incorporated":[44],"text":[45,92],"guidance,":[46],"resulting":[47],"misalignment":[50],"between":[51],"the":[52,62,85,91],"edited":[53],"results":[54],"texts.":[56],"In":[57],"this":[58],"study,":[59],"we":[60,101],"disclose":[61],"sensitivity":[63],"of":[64,129],"different":[65,69,95],"attention":[66,96],"heads":[67,97],"to":[68,94,107],"semantics":[71],"within":[72],"introduce":[75],"HeadRouter":[76],",":[77],"training-free":[79],"framework":[82],"edits":[84],"source":[86],"by":[88],"adaptively":[89],"routing":[90],"guidance":[93,115],"MM-DiTs.":[99],"Furthermore,":[100],"propose":[102],"dual-token":[104],"refinement":[105],"module":[106],"refine":[108],"text/image":[109],"token":[110],"representations":[111],"precise":[113],"region":[118],"expression.":[119],"Experiments":[120],"on":[121],"multiple":[122],"benchmarks":[123],"demonstrate":[124],"HeadRouter\u2019s":[125],"performance":[126],"terms":[128],"fidelity":[131],"quality.":[134],"The":[135],"code":[136],"is":[137],"available":[138],"at":[139],"https://github.com/ICTMCG/HeadRouter":[140],".":[141]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-03T00:00:00"}
