{"id":"https://openalex.org/W7129456359","doi":"https://doi.org/10.48550/arxiv.2602.14514","title":"Efficient Text-Guided Convolutional Adapter for the Diffusion Model","display_name":"Efficient Text-Guided Convolutional Adapter for the Diffusion Model","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129456359","doi":"https://doi.org/10.48550/arxiv.2602.14514"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.14514","doi":"https://doi.org/10.48550/arxiv.2602.14514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14514","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.14514","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126178467","display_name":"Aryan Das","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Aryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010852509","display_name":"Koushik Biswas","orcid":"https://orcid.org/0000-0002-9818-8966","observed_orcids":["https://orcid.org/0000-0002-9818-8966"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biswas, Koushik","raw_affiliation_strings":["IIIT Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Delhi","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087427076","display_name":"Swalpa Kumar Roy","orcid":"https://orcid.org/0000-0002-6580-3977","observed_orcids":["https://orcid.org/0000-0002-6580-3977"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy, Swalpa Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035714586","display_name":"Badri N. Patro","orcid":"https://orcid.org/0000-0002-2585-7014","observed_orcids":["https://orcid.org/0000-0002-2585-7014"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patro, Badri Narayana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101744115","display_name":"Vinay Kumar Verma","orcid":"https://orcid.org/0000-0002-6532-2997","observed_orcids":["https://orcid.org/0000-0002-6532-2997"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Verma, Vinay Kumar","raw_affiliation_strings":["IIT Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"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":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":1.0,"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":1.0,"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":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/diffusion-models","display_name":"diffusion models","score":0.8180000185966492},{"id":"https://openalex.org/keywords/sketch-to-image-generation","display_name":"sketch-to-image generation","score":0.578000009059906},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.8840000033378601},{"id":"https://openalex.org/keywords/prompt-conditioning","display_name":"prompt conditioning","score":0.5019999742507935},{"id":"https://openalex.org/keywords/multimodal-conditioning","display_name":"multimodal conditioning","score":0.6710000038146973}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.9377999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673799991607666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C148609458","wikidata":"https://www.wikidata.org/wiki/Q7021281","display_name":"Nexus (standard)","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C184992742","wikidata":"https://www.wikidata.org/wiki/Q7243229","display_name":"Prime (order theory)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.14514","doi":"https://doi.org/10.48550/arxiv.2602.14514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14514","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,"listed_in":[],"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.2602.14514","doi":"https://doi.org/10.48550/arxiv.2602.14514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14514","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,168],"introduce":[1],"the":[2,10,14,62,66,76,79,87,95,101,110,116,121,153,161,166,173,179,193,210],"Nexus":[3,129,142,180,202],"Adapters,":[4],"novel":[5],"text-guided":[6],"efficient":[7,127],"adapters":[8],"to":[9,65,74,147,192],"diffusion-based":[11],"framework":[12],"for":[13,36,42,109,115],"Structure":[15],"Preserving":[16],"Conditional":[17],"Generation":[18],"(SPCG).":[19],"Recently,":[20],"structure-preserving":[21],"methods":[22],"have":[23],"achieved":[24,214],"promising":[25],"results":[26],"in":[27,61],"conditional":[28],"image":[29],"generation":[30],"by":[31,136],"using":[32],"a":[33,157,200],"base":[34,67],"model":[35,77,81],"prompt":[37,163],"conditioning":[38],"and":[39,56,85,131,138,176],"an":[40],"adapter":[41,63,96,155,182,204],"structure":[43],"input,":[44],"such":[45],"as":[46],"sketches":[47],"or":[48],"depth":[49],"maps.":[50],"These":[51],"approaches":[52],"are":[53,134],"highly":[54,90],"inefficient":[55],"sometimes":[57],"require":[58],"equal":[59],"parameters":[60,190,208],"compared":[64,191],"architecture.":[68],"It":[69],"is":[70,82,89,97,106],"not":[71,98,114],"always":[72],"possible":[73],"train":[75],"since":[78],"diffusion":[80],"itself":[83],"costly,":[84],"doubling":[86],"parameter":[88],"inefficient.":[91],"In":[92],"these":[93],"approaches,":[94],"aware":[99],"of":[100,160],"input":[102,112,117,162],"prompt;":[103],"therefore,":[104],"it":[105],"optimal":[107],"only":[108,187],"structural":[111,139],"but":[113],"prompt.":[118],"To":[119],"overcome":[120],"above":[122],"challenges,":[123],"we":[124,197],"proposed":[125,154,174],"two":[126],"adapters,":[128],"Prime":[130,181],"Slim,":[132],"which":[133,212],"guided":[135],"prompts":[137],"inputs.":[140],"Each":[141],"Block":[143],"incorporates":[144],"cross-attention":[145],"mechanisms":[146],"enable":[148],"rich":[149],"multimodal":[150],"conditioning.":[151],"Therefore,":[152],"has":[156],"better":[158],"understanding":[159],"while":[164],"preserving":[165],"structure.":[167],"conducted":[169],"extensive":[170],"experiments":[171],"on":[172],"models":[175],"demonstrated":[177],"that":[178],"significantly":[183],"enhances":[184],"performance,":[185],"requiring":[186],"8M":[188],"additional":[189],"baseline,":[194],"T2I-Adapter.":[195],"Furthermore,":[196],"also":[198],"introduced":[199],"lightweight":[201],"Slim":[203],"with":[205],"18M":[206],"fewer":[207],"than":[209],"T2I-Adapter,":[211],"still":[213],"state-of-the-art":[215],"results.":[216],"Code:":[217],"https://github.com/arya-domain/Nexus-Adapters":[218]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-02-18T00:00:00"}