{"id":"https://openalex.org/W4416247105","doi":"https://doi.org/10.18653/v1/2026.acl-long.102","title":"CARES: Context-Aware Resolution Selector for VLMs","display_name":"CARES: Context-Aware Resolution Selector for VLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416247105","doi":"https://doi.org/10.18653/v1/2026.acl-long.102"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.102","pdf_url":"https://aclanthology.org/2026.acl-long.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.102.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046832314","display_name":"Moshe Kimhi","orcid":"https://orcid.org/0009-0000-7645-7339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moshe Kimhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011071587","display_name":"Nimrod Shabtay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nimrod Shabtay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072571599","display_name":"Raja Giryes","orcid":"https://orcid.org/0000-0002-2830-0297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raja Giryes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019913171","display_name":"Chaim Baskin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaim Baskin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054401063","display_name":"Eli Schwartz","orcid":"https://orcid.org/0000-0002-3393-8666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eli Schwartz","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01751799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2243","last_page":"2256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7350999712944031,"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":0.7350999712944031,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04490000009536743,"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":0.032099999487400055,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7102000117301941},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.520799994468689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7102000117301941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122999787330627},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.102","pdf_url":"https://aclanthology.org/2026.acl-long.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.19496","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.19496","pdf_url":"https://arxiv.org/pdf/2510.19496","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.19496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19496","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.102","pdf_url":"https://aclanthology.org/2026.acl-long.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416247105.pdf","grobid_xml":"https://content.openalex.org/works/W4416247105.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"commonly":[4],"process":[5],"images":[6,40],"at":[7,102],"native":[8],"or":[9],"high":[10,33],"resolution":[11],"to":[12,21,22,68,80,84,130],"remain":[13],"effective":[14],"across":[15,134],"tasks.This":[16],"inflates":[17],"visual":[18],"tokens":[19,26],"up":[20,129],"99%":[23],"of":[24,27,95],"total":[25],"the":[28,58],"prefill":[29],"stage,":[30],"resulting":[31],"in":[32],"compute":[34,127],"and":[35,71,112],"latency,":[36],"even":[37],"when":[38,73],"lowresolution":[39],"would":[41],"suffice.We":[42],"introduce":[43],"CARES-a":[44],"Context-Aware":[45],"Resolution":[46],"Selector,":[47],"a":[48,64,74,89,93],"lightweight":[49],"preprocessing":[50],"module":[51],"that,":[52],"given":[53],"an":[54],"image-query":[55],"pair,":[56],"predicts":[57],"minimal":[59],"sufficient":[60],"input":[61],"resolution.CARES":[62],"uses":[63],"compact":[65],"VLM":[66],"(350M)":[67],"extract":[69],"features":[70],"predict":[72],"target":[75,119],"pretrained":[76],"VLM's":[77],"response":[78],"converges":[79],"its":[81],"peak":[82],"ability":[83],"answer":[85],"correctly.Though":[86],"trained":[87],"as":[88,115,117],"discrete":[90],"classifier":[91],"over":[92],"set":[94],"optional":[96],"resolutions,":[97],"CARES":[98,121],"interpolates":[99],"continuous":[100],"resolutions":[101],"inference":[103],"for":[104],"fine-grained":[105],"control.Across":[106],"nine":[107],"multimodal":[108],"benchmarks":[109],"spanning":[110],"documents":[111],"natural":[113],"images,":[114],"well":[116],"diverse":[118],"VLMs,":[120],"preserves":[122],"task":[123],"performance":[124],"while":[125],"reducing":[126],"by":[128],"78%":[131],"on":[132],"average":[133],"9":[135],"benchmarks.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-24T00:00:00"}