{"id":"https://openalex.org/W4412945600","doi":"https://doi.org/10.18653/v1/2025.acl-long.387","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","display_name":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945600","doi":"https://doi.org/10.18653/v1/2025.acl-long.387"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.387","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.387","pdf_url":"https://aclanthology.org/2025.acl-long.387.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.387.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092149159","display_name":"Michael Ogezi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Ogezi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076446804","display_name":"Freda Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freda Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8059,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86355789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7855","last_page":"7875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9671000242233276,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9279999732971191,"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/spare-part","display_name":"Spare part","score":0.7443736791610718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6748756766319275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333497881889343},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.43124711513519287},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42887216806411743},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3846035599708557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3386969566345215},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32946544885635376},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17219018936157227},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1405545175075531}],"concepts":[{"id":"https://openalex.org/C194648553","wikidata":"https://www.wikidata.org/wiki/Q1364774","display_name":"Spare part","level":2,"score":0.7443736791610718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6748756766319275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333497881889343},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.43124711513519287},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42887216806411743},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3846035599708557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3386969566345215},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32946544885635376},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17219018936157227},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1405545175075531},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.387","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.387","pdf_url":"https://aclanthology.org/2025.acl-long.387.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.387","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.387","pdf_url":"https://aclanthology.org/2025.acl-long.387.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945600.pdf","grobid_xml":"https://content.openalex.org/works/W4412945600.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2376859990","https://openalex.org/W2912704652","https://openalex.org/W2381161177","https://openalex.org/W2319226115","https://openalex.org/W830772239","https://openalex.org/W2970750595","https://openalex.org/W2366601680","https://openalex.org/W4295074292","https://openalex.org/W2392193501","https://openalex.org/W2738649048"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"work":[3,138],"well":[4,51],"in":[5,41,88,153,168],"tasks":[6,155],"ranging":[7],"from":[8,84],"image":[9,86],"captioning":[10],"to":[11,66,121,162],"visual":[12],"question":[13],"answering":[14],"(VQA),":[15],"yet":[16],"they":[17],"struggle":[18],"with":[19,46],"spatial":[20,36,69,81,116,146],"reasoning,":[21],"a":[22,48,56,75,122],"key":[23],"skill":[24],"for":[25],"understanding":[26],"our":[27,107,164],"physical":[28],"world":[29],"that":[30,35],"humans":[31],"excel":[32],"at.We":[33],"find":[34],"relations":[37],"are":[38],"generally":[39],"rare":[40],"widely":[42],"used":[43],"VL":[44],"datasets,":[45],"only":[47],"few":[49],"being":[50],"represented":[52],"while":[53,131],"most":[54],"form":[55],"long":[57],"tail":[58],"of":[59,96],"underrepresented":[60],"relations.This":[61],"gap":[62,141],"leaves":[63],"VLMs":[64,111,150],"ill-equipped":[65],"handle":[67],"diverse":[68],"relationships.To":[70],"bridge":[71],"it,":[72],"we":[73],"construct":[74],"synthetic":[76],"VQA":[77],"dataset":[78,94,167],"focused":[79],"on":[80,104,115,126,135],"reasoning":[82,117,147],"generated":[83],"hyperdetailed":[85],"descriptions":[87],"Localized":[89],"Narratives,":[90],"DOCCI,":[91],"and":[92,144,148,159,166],"PixMo-Cap.Our":[93],"consists":[95],"455k":[97],"samples":[98],"containing":[99],"3.4":[100],"million":[101],"QA":[102],"pairs.Trained":[103],"this":[105],"dataset,":[106],"Spatial-Reasoning":[108],"Enhanced":[109],"(SpaRE)":[110],"show":[112],"strong":[113,133],"improvements":[114],"benchmarks,":[118],"achieving":[119],"up":[120],"49%":[123],"performance":[124],"gain":[125],"the":[127,140],"What's":[128],"Up":[129],"benchmark,":[130],"maintaining":[132],"results":[134],"general":[136],"tasks.Our":[137],"narrows":[139],"between":[142],"human":[143],"VLM":[145],"makes":[149],"more":[151],"capable":[152],"real-world":[154],"such":[156],"as":[157],"robotics":[158],"navigation.We":[160],"plan":[161],"share":[163],"code":[165],"due":[169],"course.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}