{"id":"https://openalex.org/W7140105005","doi":"https://doi.org/10.18653/v1/2026.eacl-long.6","title":"SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language Models","display_name":"SCoPE VLM: Selective Context Processing for Efficient Document Navigation in Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140105005","doi":"https://doi.org/10.18653/v1/2026.eacl-long.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.6","doi":"https://doi.org/10.18653/v1/2026.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.6","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2026.eacl-long.6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134394736","display_name":"Gyubeum Lim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyubeum Lim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134387524","display_name":"Yemo Koo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yemo Koo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111982286","display_name":"Vijay Krishna Madisetti","orcid":"https://orcid.org/0000-0002-6539-6769","observed_orcids":["https://orcid.org/0000-0002-6539-6769"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay Krishna Madisetti","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":0.12203145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"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":0.9970999956130981,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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/vision-language-models","display_name":"vision-language models","score":0.9700000286102295},{"id":"https://openalex.org/keywords/document-navigation","display_name":"document navigation","score":0.9089999794960022},{"id":"https://openalex.org/keywords/website-navigation","display_name":"web navigation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6610000133514404},{"id":"https://openalex.org/keywords/memory-efficiency","display_name":"memory efficiency","score":0.5230000019073486},{"id":"https://openalex.org/keywords/multimodal-agents","display_name":"multimodal agents","score":0.8299999833106995},{"id":"https://openalex.org/keywords/data-generation-pipeline","display_name":"data generation pipeline","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754000186920166},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.24869999289512634}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.6","doi":"https://doi.org/10.18653/v1/2026.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.6","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.21850","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21850","pdf_url":"https://arxiv.org/pdf/2510.21850","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.21850","doi":"https://doi.org/10.48550/arxiv.2510.21850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21850","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.6","doi":"https://doi.org/10.18653/v1/2026.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.6","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140105005.pdf","grobid_xml":"https://content.openalex.org/works/W7140105005.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4386185600","https://openalex.org/W4415798734"],"related_works":["https://openalex.org/W7214577769","https://openalex.org/W7220847659","https://openalex.org/W7196957589","https://openalex.org/W7196953550","https://openalex.org/W4415318177","https://openalex.org/W7196969543","https://openalex.org/W7166869837","https://openalex.org/W2472672021","https://openalex.org/W7196927440","https://openalex.org/W4415800380"],"abstract_inverted_index":{"Understanding":[0],"long-context":[1],"visual":[2,47],"information":[3],"remains":[4],"a":[5,73,79,98,116],"fundamental":[6],"challenge":[7],"for":[8,61],"vision-language":[9],"models,":[10],"particularly":[11],"in":[12,39,159],"agentic":[13,156],"tasks":[14],"such":[15],"as":[16],"GUI":[17,26],"control":[18],"and":[19,25,59,87,110,127,135],"web":[20,23],"navigation.":[21],"While":[22],"pages":[24],"environments":[27],"are":[28,57],"inherently":[29],"structured":[30],"documents,":[31,90],"current":[32],"VLMs":[33],"typically":[34],"neglect":[35],"decision-oriented":[36],"document":[37,74,161],"understanding":[38],"their":[40],"training":[41,126],"objectives.":[42],"Existing":[43],"approaches":[44],"primarily":[45],"extend":[46],"embeddings":[48],"to":[49,85,103,121,153],"process":[50],"long,":[51],"high-resolution":[52],"inputs,":[53],"but":[54],"these":[55,67],"methods":[56],"memory-intensive":[58],"impractical":[60],"locally":[62],"deployable":[63],"solutions.":[64],"To":[65,141],"address":[66],"issues,":[68],"we":[69],"propose":[70],"SCoPE":[71,147],"VLM,":[72],"navigation":[75],"expert":[76],"that":[77],"leverages":[78],"novel":[80],"Chain":[81,106],"of":[82,107,144,167],"Scroll":[83,108],"mechanism":[84],"selectively":[86],"recursively":[88],"navigate":[89],"focusing":[91],"exclusively":[92],"on":[93],"relevant":[94],"segments.":[95],"We":[96],"introduce":[97],"dedicated":[99],"data":[100],"generation":[101],"pipeline":[102],"construct":[104],"informative":[105],"trajectories":[109],"Episodic":[111],"Group":[112],"Relative":[113],"Policy":[114],"Optimization,":[115],"tailored":[117],"reinforcement":[118],"learning":[119],"method":[120,130],"bridge":[122],"the":[123,142,150,165],"gap":[124],"between":[125],"inference.":[128],"Our":[129],"substantially":[131],"reduces":[132],"memory":[133],"usage":[134],"effectively":[136],"models":[137],"human-like":[138],"reading":[139,157],"behaviors.":[140],"best":[143],"our":[145],"knowledge,":[146],"VLM":[148],"is":[149],"first":[151],"framework":[152],"explicitly":[154],"model":[155],"patterns":[158],"multi-page":[160],"question":[162],"answering,":[163],"advancing":[164],"capabilities":[166],"multimodal":[168],"agents.":[169]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-02-02T00:00:00"}