{"id":"https://openalex.org/W7166836506","doi":"https://doi.org/10.18653/v1/2026.acl-long.1514","title":"Diagnosing Spatial Consistency across Perspectives and Viewpoints in Large Vision-Language Models","display_name":"Diagnosing Spatial Consistency across Perspectives and Viewpoints in Large Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166836506","doi":"https://doi.org/10.18653/v1/2026.acl-long.1514"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1514","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1514","pdf_url":"https://aclanthology.org/2026.acl-long.1514.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1514.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100660525","display_name":"Yoonji Kim","orcid":"https://orcid.org/0000-0002-1664-3137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoonji Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839668","display_name":"Jieun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778646","display_name":"Yujin Jeong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujin Jeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139809537","display_name":"Sung-Bae Cho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung-Bae Cho","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":0.8688805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32803","last_page":"32827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7300999760627747,"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":0.7300999760627747,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.02419999986886978,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5105999708175659},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26820001006126404},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2547999918460846},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24169999361038208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5636000037193298},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24169999361038208},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24070000648498535}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1514","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1514","pdf_url":"https://aclanthology.org/2026.acl-long.1514.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1514","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1514","pdf_url":"https://aclanthology.org/2026.acl-long.1514.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":[{"id":"https://openalex.org/G2257911995","display_name":null,"funder_award_id":"RS-2020-II201361","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3182541678","display_name":null,"funder_award_id":"RS-2020-II201361","funder_id":"https://openalex.org/F4320321314","funder_display_name":"Yonsei University"},{"id":"https://openalex.org/G3212097187","display_name":null,"funder_award_id":"RS-2020-II201361","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3530982869","display_name":null,"funder_award_id":"RS-2022-II220113","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5616276691","display_name":null,"funder_award_id":"RS-2022-II220113","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8007358912","display_name":null,"funder_award_id":"RS-2022-II220113","funder_id":"https://openalex.org/F4320321314","funder_display_name":"Yonsei University"}],"funders":[{"id":"https://openalex.org/F4320321314","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166836506.pdf","grobid_xml":"https://content.openalex.org/works/W7166836506.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Consistent":[0],"reasoning":[1,80,106],"about":[2,173],"3D":[3,117],"spatial":[4,31,41,58,79,88,111,134,144],"relations":[5],"across":[6,33,68,136],"changing":[7],"viewpoints":[8],"is":[9],"fundamental":[10,129],"for":[11],"Embodied":[12],"AI":[13],"agents":[14],"operating":[15],"in":[16,82,163],"dynamic":[17,54],"environments.While":[18],"Large":[19],"Vision-Language":[20],"Models":[21],"(LVLMs)":[22],"have":[23],"advanced":[24],"multimodal":[25],"perception,":[26],"their":[27],"ability":[28],"to":[29,51,76,99],"maintain":[30],"consistency":[32],"diverse":[34],"perspectives":[35],"remains":[36],"underexplored.Existing":[37],"benchmarks":[38],"primarily":[39],"assess":[40],"capabilities":[42],"from":[43,115],"a":[44,72,148],"static,":[45],"single-view,":[46],"and":[47,70,104],"egocentric":[48,105],"perspective,":[49],"failing":[50],"capture":[52],"the":[53,92,141,161,164],"nature":[55],"of":[56,86,122,143],"real-world":[57],"cognition.To":[59],"address":[60],"this":[61],"gap,":[62],"we":[63,126],"introduce":[64],"SCOPE":[65,90,139],"(Spatial":[66],"COnsistency":[67],"PErspectives":[69],"Viewpoints),":[71],"comprehensive":[73],"benchmark":[74],"designed":[75],"rigorously":[77],"diagnose":[78],"capabilities.Grounded":[81],"human":[83],"cognitive":[84],"theories":[85],"dual":[87],"representations,":[89],"discretizes":[91],"360":[93],"\u2022":[94],"field":[95],"into":[96],"multiview":[97],"scenarios":[98],"systematically":[100],"evaluate":[101],"both":[102],"allocentric":[103],"capabilities.Our":[107],"dataset":[108],"comprises":[109],"20.1K":[110],"VQA":[112],"pairs":[113],"derived":[114],"high-quality":[116],"environments.Through":[118],"an":[119,174],"extensive":[120],"evaluation":[121],"26":[123],"state-of-the-art":[124],"LVLMs,":[125],"identify":[127,182],"two":[128],"limitations":[130],"that":[131],"prevent":[132],"consistent":[133],"understanding":[135],"viewpoints.We":[137],"hope":[138],"facilitates":[140],"diagnosis":[142],"reasoning,":[145],"serving":[146],"as":[147],"stepping":[149],"stone":[150],"toward":[151],"reliable":[152],"embodied":[153],"action.":[154],"WildRGB-D":[155],"DL3DV-10K":[156],"Data":[157],"Collection":[158],"QA":[159],"GenerationList":[160],"objects":[162],"image.If":[165],"you":[166,180],"are":[167],"not":[168,177],"more":[169],"than":[170],"90%":[171],"confident":[172],"object,":[175],"do":[176],"include":[178],"it.If":[179],"cannot":[181],"any":[183],"objects,":[184],"answer":[185],"with":[186],"\"None\".":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}