{"id":"https://openalex.org/W4414359430","doi":"https://doi.org/10.24963/ijcai.2025/1200","title":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","display_name":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359430","doi":"https://doi.org/10.24963/ijcai.2025/1200"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1200","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108014814","display_name":"Jirong Zha","orcid":"https://orcid.org/0009-0006-4824-6976"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jirong Zha","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102618106","display_name":"Yuxuan Fan","orcid":"https://orcid.org/0009-0000-3470-7897"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxuan Fan","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guang Zhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guang Zhou)","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039657406","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0003-2401-5197"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Yang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guang Zhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guang Zhou)","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078622343","display_name":"Chen Gao","orcid":"https://orcid.org/0000-0002-7561-5646"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Gao","raw_affiliation_strings":["BNRist, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlei Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10817","last_page":"10825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9726999998092651,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9726999998092651,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9539999961853027,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9477999806404114,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5198000073432922},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4950999915599823},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.483599990606308},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.44780001044273376},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4068000018596649},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3986999988555908},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714900016784668},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4124999940395355},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779433544","wikidata":"https://www.wikidata.org/wiki/Q1435226","display_name":"Focal point","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1200","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,35,59,76,88,118],"spatial":[1,60,137],"understanding":[2,36,77],"is":[3],"essential":[4],"in":[5,136],"real-world":[6,142],"applications":[7],"such":[8],"as":[9],"robotics,":[10],"autonomous":[11],"vehicles,":[12],"virtual":[13],"reality,":[14],"and":[15,90,111,117,128,141],"medical":[16],"imaging.":[17],"Recently,":[18],"Large":[19],"Language":[20],"Models":[21],"(LLMs),":[22],"having":[23],"demonstrated":[24],"remarkable":[25],"success":[26],"across":[27],"various":[28],"domains,":[29],"have":[30],"been":[31],"leveraged":[32],"to":[33,40],"enhance":[34],"tasks,":[37],"showing":[38],"potential":[39],"surpass":[41],"traditional":[42],"computer":[43],"vision":[44],"methods.":[45],"In":[46],"this":[47],"survey,":[48],"we":[49,121],"present":[50],"a":[51,64],"comprehensive":[52],"review":[53,100],"of":[54],"methods":[55,69,74,84,93,102],"integrating":[56],"LLMs":[57],"with":[58,87],"understanding.":[61],"We":[62,98],"propose":[63],"taxonomy":[65],"that":[66,114],"categorizes":[67],"existing":[68],"into":[70],"three":[71],"branches:":[72],"image-based":[73],"deriving":[75],"from":[78],"2D":[79],"visual":[80],"data,":[81],"point":[82],"cloud-based":[83],"working":[85],"directly":[86],"representations,":[89,108],"hybrid":[91],"modality-based":[92],"combining":[94],"multiple":[95],"data":[96,107],"streams.":[97],"systematically":[99],"representative":[101],"along":[103],"these":[104],"categories,":[105],"covering":[106],"architectural":[109],"modifications,":[110],"training":[112],"strategies":[113],"bridge":[115],"textual":[116],"modalities.":[119],"Finally,":[120],"discuss":[122],"current":[123],"limitations,":[124],"including":[125],"dataset":[126],"scarcity":[127],"computational":[129],"challenges,":[130],"while":[131],"highlighting":[132],"promising":[133],"research":[134],"directions":[135],"perception,":[138],"multi-modal":[139],"fusion,":[140],"applications.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
