{"id":"https://openalex.org/W7141467982","doi":"https://doi.org/10.48550/arxiv.2603.25411","title":"HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models","display_name":"HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141467982","doi":"https://doi.org/10.48550/arxiv.2603.25411"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130753287","display_name":"Huizhi Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liang, Huizhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130783263","display_name":"Yichao Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yichao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130761869","display_name":"Yu Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130804104","display_name":"Sicheng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Sicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130753109","display_name":"Zhiyuan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zhiyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130740440","display_name":"Tong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678419","display_name":"Yaobo Liang","orcid":"https://orcid.org/0000-0002-6595-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yaobo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130797307","display_name":"Jiaolong Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiaolong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5130753287"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9358000159263611,"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":0.9358000159263611,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.008500000461935997,"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/spatial-intelligence","display_name":"Spatial intelligence","score":0.6995999813079834},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6758999824523926},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.620199978351593},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5787000060081482},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4821000099182129},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.46630001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268999814987183},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6995999813079834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6758999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6510000228881836},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C2781179811","wikidata":"https://www.wikidata.org/wiki/Q28134081","display_name":"Spatial configuration","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.25411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"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":{"Achieving":[0],"human-like":[1],"spatial":[2,26,43,57,80,108,121,128,162],"intelligence":[3],"for":[4,88],"vision-language":[5],"models":[6,129],"(VLMs)":[7],"requires":[8],"inferring":[9],"3D":[10,21,42,79,161],"structures":[11],"from":[12,52],"2D":[13],"observations,":[14],"recognizing":[15],"object":[16],"properties":[17],"and":[18,23,86,123,130,137],"relations":[19],"in":[20,45],"space,":[22],"performing":[24],"high-level":[25],"reasoning.":[27,58],"In":[28],"this":[29,61],"paper,":[30],"we":[31,63],"propose":[32],"a":[33],"principled":[34],"hierarchical":[35,146],"framework":[36],"that":[37,68,113],"decomposes":[38],"the":[39,158],"learning":[40],"of":[41,160],"understanding":[44,122],"VLMs":[46],"into":[47,152],"four":[48],"progressively":[49],"complex":[50],"levels,":[51,148],"geometric":[53],"perception":[54],"to":[55,77,105],"abstract":[56],"Guided":[59],"by":[60],"framework,":[62],"construct":[64],"an":[65,95],"automated":[66],"pipeline":[67],"processes":[69],"approximately":[70],"5M":[71],"images":[72],"with":[73],"over":[74],"45M":[75],"objects":[76],"generate":[78],"VQA":[81],"pairs":[82],"across":[83],"diverse":[84],"tasks":[85],"scenes":[87],"VLM":[89,97],"supervised":[90],"fine-tuning.":[91],"We":[92],"also":[93],"develop":[94],"RGB-D":[96],"incorporating":[98],"metric-scale":[99],"point":[100],"maps":[101],"as":[102,135],"auxiliary":[103],"inputs":[104],"further":[106],"enhance":[107],"understanding.":[109],"Extensive":[110],"experiments":[111],"demonstrate":[112],"our":[114,140],"approach":[115],"achieves":[116],"state-of-the-art":[117],"performance":[118],"on":[119],"multiple":[120],"reasoning":[124],"benchmarks,":[125],"surpassing":[126],"specialized":[127],"large":[131],"proprietary":[132],"systems":[133],"such":[134],"Gemini-2.5-pro":[136],"GPT-5.":[138],"Moreover,":[139],"analysis":[141],"reveals":[142],"clear":[143],"dependencies":[144],"among":[145],"task":[147,155],"offering":[149],"new":[150],"insights":[151],"how":[153],"multi-level":[154],"design":[156],"facilitates":[157],"emergence":[159],"intelligence.":[163]},"counts_by_year":[],"updated_date":"2026-03-28T06:16:51.555046","created_date":"2026-03-28T00:00:00"}