{"id":"https://openalex.org/W4414588497","doi":"https://doi.org/10.48550/arxiv.2505.20271","title":"In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation","display_name":"In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4414588497","doi":"https://doi.org/10.48550/arxiv.2505.20271"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.20271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20271","pdf_url":"https://arxiv.org/pdf/2505.20271","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.20271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020823775","display_name":"Yu Xu","orcid":"https://orcid.org/0000-0002-0146-9025"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014120192","display_name":"Fan Tang","orcid":"https://orcid.org/0000-0002-6867-8876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085587703","display_name":"You Wu","orcid":"https://orcid.org/0009-0003-9872-6917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, You","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108190421","display_name":"Gao Lin","orcid":"https://orcid.org/0009-0000-4346-3222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036489223","display_name":"Oliver Deu\u00dfen","orcid":"https://orcid.org/0000-0001-5803-2185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deussen, Oliver","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042504289","display_name":"Hongbin Yan","orcid":"https://orcid.org/0009-0009-8555-657X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hongbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334714","display_name":"Jintao Li","orcid":"https://orcid.org/0000-0002-9930-1449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jintao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045532110","display_name":"Juan Cao","orcid":"https://orcid.org/0000-0002-9029-2822"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Juan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050657606","display_name":"Tong\u2010Yee Lee","orcid":"https://orcid.org/0000-0001-6699-2944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Tong-Yee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5020823775"],"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9987000226974487,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9945999979972839,"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/feature","display_name":"Feature (linguistics)","score":0.5723000168800354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.5472999811172485},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5123000144958496},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5472999811172485},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.20271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20271","pdf_url":"https://arxiv.org/pdf/2505.20271","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.20271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.20271","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.20271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20271","pdf_url":"https://arxiv.org/pdf/2505.20271","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414588497.pdf","grobid_xml":"https://content.openalex.org/works/W4414588497.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"diffusion":[3],"models":[4],"have":[5],"enhanced":[6],"multimodal-guided":[7],"visual":[8],"generation,":[9],"enabling":[10],"customized":[11,34,60],"subject":[12,61,110,150],"insertion":[13,62],"that":[14,141,159,172],"seamlessly":[15],"\"brushes\"":[16],"user-specified":[17],"objects":[18],"into":[19],"a":[20,56,119],"given":[21],"image":[22,81,92,107,182],"guided":[23],"by":[24,63],"textual":[25,47,84,112],"prompts.":[26,48],"However,":[27],"existing":[28,186],"methods":[29],"often":[30],"struggle":[31],"to":[32,103,146,185],"insert":[33],"subjects":[35],"with":[36,42,93,108],"high":[37],"fidelity":[38],"and":[39,82,89,152,169,181],"align":[40],"results":[41],"the":[43,65,68,79,83,90,94,98,105,109,148],"user's":[44],"intent":[45],"through":[46,163],"In":[49],"this":[50],"work,":[51],"we":[52,77,124],"propose":[53],"\"In-Context":[54],"Brush\",":[55],"zero-shot":[57],"framework":[58],"for":[59],"reformulating":[64],"task":[66],"within":[67,137],"paradigm":[69],"of":[70,75],"in-context":[71],"learning.":[72],"Without":[73],"loss":[74],"generality,":[76],"formulate":[78],"object":[80],"prompts":[85,113],"as":[86,97],"cross-modal":[87],"demonstrations,":[88],"target":[91,106],"masked":[95],"region":[96],"query.":[99],"The":[100],"goal":[101],"is":[102],"inpaint":[104],"aligning":[111],"without":[114,189],"model":[115],"tuning.":[116],"Building":[117],"upon":[118],"pretrained":[120],"MMDiT-based":[121],"inpainting":[122],"network,":[123],"perform":[125],"test-time":[126],"enhancement":[127],"via":[128],"dual-level":[129],"latent":[130],"space":[131],"manipulation:":[132],"intra-head":[133],"\"latent":[134],"feature":[135],"shifting\"":[136],"each":[138],"attention":[139,144,165],"head":[140],"dynamically":[142],"shifts":[143],"outputs":[145],"reflect":[147],"desired":[149],"semantics":[151],"inter-head":[153],"\"attention":[154],"reweighting\"":[155],"across":[156],"different":[157],"heads":[158],"amplifies":[160],"prompt":[161],"controllability":[162],"differential":[164],"prioritization.":[166],"Extensive":[167],"experiments":[168],"applications":[170],"demonstrate":[171],"our":[173],"approach":[174],"achieves":[175],"superior":[176],"identity":[177],"preservation,":[178],"text":[179],"alignment,":[180],"quality":[183],"compared":[184],"state-of-the-art":[187],"methods,":[188],"requiring":[190],"dedicated":[191],"training":[192],"or":[193],"additional":[194],"data":[195],"collection.":[196]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}