{"id":"https://openalex.org/W7165160235","doi":"https://doi.org/10.48550/arxiv.2606.18906","title":"BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing","display_name":"BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165160235","doi":"https://doi.org/10.48550/arxiv.2606.18906"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.18906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18906","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2606.18906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060151070","display_name":"C W Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Chaewon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138840792","display_name":"Soyoon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Soyoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058910905","display_name":"N Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Naeun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138932693","display_name":"Minjung Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Minjung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051860463","display_name":"Seogkyu Jeon","orcid":"https://orcid.org/0000-0002-3770-0399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeon, Seogkyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138840437","display_name":"Kibeom Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Kibeom","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.914900004863739,"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":0.914900004863739,"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":0.009600000455975533,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.007000000216066837,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.707099974155426},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6883999705314636},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5264000296592712},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.520799994468689},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.3346000015735626},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.32839998602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102999925613403},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.707099974155426},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6883999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483999848365784},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.18906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18906","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.18906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18906","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"Real":[0],"image":[1],"editing":[2,162,199],"enables":[3],"precise":[4],"manipulation":[5],"of":[6,53,71],"visual":[7],"content,":[8],"yet":[9],"existing":[10,184],"methods":[11,185],"often":[12],"fail":[13],"in":[14],"complex":[15],"multi-object":[16,169,198],"scenarios,":[17],"causing":[18],"semantic":[19],"blending,":[20,64],"object":[21,63,173],"duplication,":[22],"or":[23],"incomplete":[24],"edits.":[25],"We":[26],"attribute":[27],"these":[28,84],"failures":[29],"to":[30,62,116],"attention":[31,77],"leakage,":[32],"where":[33,57,69],"signals":[34],"across":[35,159,194],"spatial":[36,119],"regions":[37],"and":[38,65,106,138,175,197],"text":[39],"tokens":[40,70],"become":[41],"entangled":[42],"during":[43],"the":[44,76,160],"denoising":[45],"process.":[46],"Specifically,":[47],"we":[48,86,165],"identify":[49],"two":[50],"distinct":[51],"forms":[52],"leakage:":[54],"Edit-Token":[55,100],"Leakage,":[56,68,101,129],"ambiguous":[58],"token-region":[59],"alignment":[60],"leads":[61],"Source":[66,127],"Dominance":[67,128],"unchanged":[72],"source":[73,141],"objects":[74],"overwhelm":[75],"intended":[78],"for":[79],"target":[80,111,135,154],"entities.":[81],"To":[82,98,125],"resolve":[83],"leakages,":[85],"propose":[87,166],"\\textbf{BindEdit},":[88],"which":[89],"enforces":[90],"attention-level":[91],"constraints":[92],"within":[93,143,186],"a":[94,130,147,167,187],"single":[95,188],"diffusion":[96,189],"trajectory.":[97],"suppress":[99,126],"BindEdit":[102,181],"jointly":[103],"regularizes":[104],"cross-":[105],"self-attention":[107],"so":[108],"that":[109,152,180],"each":[110,153],"token":[112,136],"group":[113],"is":[114,156],"bound":[115],"its":[117],"corresponding":[118],"region":[120,148],"while":[121],"maintaining":[122,191],"instance-level":[123],"separation.":[124],"cross-attention":[131],"re-balancing":[132],"mechanism":[133],"amplifies":[134],"influence":[137],"attenuates":[139],"residual":[140],"semantics":[142],"editable":[144],"regions.":[145],"Moreover,":[146],"fidelity":[149],"term":[150],"ensures":[151],"concept":[155],"expressed":[157],"coherently":[158],"entire":[161],"mask.":[163],"Additionally,":[164],"comprehensive":[168],"benchmark":[170],"encompassing":[171],"diverse":[172],"counts":[174],"categories.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"consistently":[182],"outperforms":[183],"trajectory,":[190],"robust":[192],"performance":[193],"both":[195],"single-":[196],"scenarios.":[200]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-19T00:00:00"}