{"id":"https://openalex.org/W7166808654","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1706","title":"What Do Vision\u2013Language Models Encode for Personalized Image Aesthetics Assessment?","display_name":"What Do Vision\u2013Language Models Encode for Personalized Image Aesthetics Assessment?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166808654","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1706"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1706","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1706","pdf_url":"https://aclanthology.org/2026.findings-acl.1706.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.1706.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133597809","display_name":"Koki Ryu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koki Ryu","raw_affiliation_strings":["Riken","The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Riken","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139792655","display_name":"Hitomi Yanaka","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hitomi Yanaka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47745952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34146","last_page":"34167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.5332000255584717,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.5332000255584717,"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":0.2921999990940094,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.032999999821186066,"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/vision-language-models","display_name":"vision-language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/internal-representations","display_name":"internal representations","score":0.7820000052452087},{"id":"https://openalex.org/keywords/aesthetic-characteristics","display_name":"aesthetic characteristics","score":0.8840000033378601},{"id":"https://openalex.org/keywords/linear-models","display_name":"linear models","score":0.5009999871253967},{"id":"https://openalex.org/keywords/layer-by-layer-analysis","display_name":"layer-wise analysis","score":0.5130000114440918},{"id":"https://openalex.org/keywords/cross-domain-transfer","display_name":"cross-domain transfer","score":0.5540000200271606}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6535000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5831000208854675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.508400022983551},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1706","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1706","pdf_url":"https://aclanthology.org/2026.findings-acl.1706.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1706","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1706","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1706","pdf_url":"https://aclanthology.org/2026.findings-acl.1706.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166808654.pdf","grobid_xml":"https://content.openalex.org/works/W7166808654.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155097843","https://openalex.org/W7169768694","https://openalex.org/W4416036908","https://openalex.org/W4386076227","https://openalex.org/W7155063472","https://openalex.org/W4387969606","https://openalex.org/W3034776788","https://openalex.org/W7140812685","https://openalex.org/W3208678646","https://openalex.org/W4308872605"],"abstract_inverted_index":{"Personalized":[0],"image":[1,114],"aesthetics":[2],"assessment":[3],"(PIAA)":[4],"is":[5,104],"an":[6],"important":[7],"research":[8],"problem":[9],"with":[10],"practical":[11],"real-world":[12],"applications.While":[13],"methods":[14],"based":[15],"on":[16,86],"vision-language":[17],"models":[18,94],"(VLMs)":[19],"are":[20],"promising":[21],"candidates":[22],"for":[23,37,64,125],"PIAA,":[24],"it":[25],"remains":[26],"unclear":[27],"whether":[28],"they":[29],"internally":[30],"encode":[31,75],"rich,":[32],"multi-level":[33],"aesthetic":[34,58,77,102,129],"attributes":[35,78],"required":[36],"effective":[38],"personalization.In":[39],"this":[40],"paper,":[41],"we":[42,89],"first":[43],"analyze":[44,100],"the":[45,52,82],"internal":[46],"representations":[47],"of":[48,56],"VLMs":[49,74,121],"to":[50],"examine":[51],"presence":[53],"and":[54,60,112],"distribution":[55],"such":[57],"attributes,":[59],"then":[61],"leverage":[62],"them":[63],"lightweight,":[65],"individual-level":[66],"personalization":[67],"without":[68],"model":[69],"fine-tuning.Our":[70],"analysis":[71],"reveals":[72],"that":[73,79,91],"diverse":[76],"propagate":[80],"into":[81,119],"language":[83],"decoder":[84],"layers.Building":[85],"these":[87],"representations,":[88],"demonstrate":[90],"simple":[92],"linear":[93],"can":[95,122],"perform":[96],"PIAA":[97],"effectively.We":[98],"further":[99],"how":[101,120],"information":[103],"transferred":[105],"across":[106,113],"layers":[107],"in":[108],"different":[109],"VLM":[110],"architectures":[111],"domains.Our":[115],"findings":[116],"provide":[117],"insights":[118],"be":[123],"utilized":[124],"modeling":[126],"subjective,":[127],"individual":[128],"preferences.":[130]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}