{"id":"https://openalex.org/W4417492222","doi":"https://doi.org/10.1109/iccv51701.2025.00144","title":"One Last Attention for Your Vision-Language Model","display_name":"One Last Attention for Your Vision-Language Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417492222","doi":"https://doi.org/10.1109/iccv51701.2025.00144"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035921366","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0003-0968-2936"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Liang Chen","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120855393","display_name":"Ghazi Shazan Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ghazi Shazan Ahmad","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120855394","display_name":"Tianjun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Tianjun Yao","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070976480","display_name":"Lingqiao Liu","orcid":"https://orcid.org/0000-0003-3584-795X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066530136","display_name":"Zhiqiang Shen","orcid":"https://orcid.org/0000-0002-4560-5092"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Zhiqiang Shen","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.47257521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8179000020027161,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8179000020027161,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10530000180006027,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.022299999371170998,"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/exploit","display_name":"Exploit","score":0.6425999999046326},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6309000253677368},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39419999718666077},{"id":"https://openalex.org/keywords/matrix-representation","display_name":"Matrix representation","score":0.38940000534057617},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3815000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279000282287598},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6309000253677368},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5303999781608582},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C44000306","wikidata":"https://www.wikidata.org/wiki/Q244330","display_name":"Hinge","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15480","pdf_url":"https://arxiv.org/pdf/2507.15480","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.15480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.15480","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":"pmh:oai:arXiv.org:2507.15480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15480","pdf_url":"https://arxiv.org/pdf/2507.15480","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pretrained":[0],"vision-language":[1],"models":[2],"(VLMs),":[3],"such":[4],"as":[5,148],"CLIP,":[6],"achieve":[7],"remarkable":[8],"zero-shot":[9],"performance,":[10],"yet":[11,62],"their":[12,39],"downstream":[13],"potential":[14],"hinges":[15],"on":[16,24],"effective":[17,63],"fine-tuning.":[18,75],"Most":[19],"adaptation":[20],"methods":[21],"typically":[22],"focus":[23],"refining":[25],"representation":[26,73],"from":[27,82],"separate":[28],"modalities":[29],"(text":[30],"or":[31,127],"vision)":[32],"but":[33],"neglect":[34],"the":[35,43,51,56,70,89,97,103,110,140,154],"critical":[36],"role":[37],"of":[38,91,99],"fused":[40,72],"representations":[41],"in":[42,102,122,131,165],"decision-making":[44],"process,":[45],"\\emph{\\ie}":[46],"rational":[47,104],"matrix":[48],"that":[49,136,145],"drives":[50],"final":[52,71,111],"prediction.":[53],"To":[54],"bridge":[55],"gap,":[57],"we":[58],"propose":[59],"a":[60,78,83,92,149],"simple":[61],"\\textbf{R}ational":[64],"\\textbf{Ada}ptaion":[65],"({RAda})":[66],"to":[67,94,109,118],"explicitly":[68],"exploit":[69],"during":[74],"RAda":[76,146],"employs":[77],"learned":[79],"mask,":[80],"obtained":[81],"lightweight":[84],"attention":[85],"layer":[86],"attached":[87],"at":[88,171],"end":[90],"VLM,":[93],"dynamically":[95],"calibrate":[96],"contribution":[98],"each":[100],"element":[101],"matrix,":[105],"enabling":[106],"targeted":[107],"adjustments":[108],"cross-modal":[112],"interactions":[113],"without":[114],"incurring":[115],"costly":[116],"modifications":[117],"intermediate":[119],"features.":[120],"Experiments":[121],"different":[123],"settings":[124],"(i.e.,":[125],"updating,":[126],"freezing":[128],"pretrained":[129],"encoders":[130],"adaptation,":[132],"and":[133,159],"test-time":[134],"training":[135],"can":[137],"only":[138],"access":[139],"unlabeled":[141],"test":[142],"data)":[143],"show":[144],"serves":[147],"versatile":[150],"fine-tuning":[151],"technique,":[152],"improving":[153],"baseline":[155],"with":[156],"minimal":[157],"code":[158],"performing":[160],"comparably":[161],"against":[162],"current":[163],"arts":[164],"most":[166],"settings.":[167],"Code":[168],"is":[169],"available":[170],"\\href{https://github.com/khufia/RAda/tree/main}{github.com/khufia/RAda}.":[172]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}