{"id":"https://openalex.org/W7139912747","doi":"https://doi.org/10.48550/arxiv.2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","display_name":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139912747","doi":"https://doi.org/10.48550/arxiv.2603.19235"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19235","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19235","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.19235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130229212","display_name":"Xianjin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xianjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130252306","display_name":"Dingkang Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Dingkang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130250094","display_name":"Tianrui Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Tianrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100983750","display_name":"Kui Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Kui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071673122","display_name":"Yumeng Zhang","orcid":"https://orcid.org/0000-0002-0174-4824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yumeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130250617","display_name":"Xiaofan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130216040","display_name":"Xiao Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130214675","display_name":"Xiang Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xiang","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":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":0.4325000047683716,"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":0.4325000047683716,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.23420000076293945,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0575999990105629,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/prior-probability","display_name":"Prior probability","score":0.7455000281333923},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5794000029563904},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5080000162124634},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4740999937057495},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4634000062942505},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4034999907016754},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38359999656677246},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3833000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778000235557556},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7455000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6072999835014343},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4740999937057495},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4034999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38359999656677246},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19235","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19235","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.19235","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19235","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"demonstrate":[5,148],"impressive":[6],"semantic":[7,116],"capabilities,":[8],"they":[9],"often":[10],"suffer":[11],"from":[12,108],"spatial":[13,56,142],"blindness,":[14],"struggling":[15],"with":[16,115,128],"fine-grained":[17],"geometric":[18,33,130],"reasoning":[19],"and":[20,41,79,112,144],"physical":[21,80],"dynamics.":[22],"Existing":[23],"solutions":[24],"typically":[25],"rely":[26],"on":[27],"explicit":[28,133],"3D":[29,76,134,139],"modalities":[30],"or":[31],"complex":[32],"scaffolding,":[34],"which":[35],"are":[36],"limited":[37],"by":[38,52],"data":[39],"scarcity":[40],"generalization":[42],"challenges.":[43],"In":[44],"this":[45],"work,":[46],"we":[47,125],"propose":[48],"a":[49,89,94,100,119,160],"paradigm":[50],"shift":[51],"leveraging":[53],"the":[54],"implicit":[55],"prior":[57],"within":[58],"large-scale":[59],"video":[60,96],"generation":[61],"models.":[62],"We":[63,82],"posit":[64],"that":[65,92,149,156],"to":[66],"synthesize":[67],"temporally":[68],"coherent":[69],"videos,":[70],"these":[71],"models":[72],"inherently":[73],"learn":[74],"robust":[75],"structural":[77],"priors":[78,158],"laws.":[81],"introduce":[83],"VEGA-3D":[84],"(Video":[85],"Extracted":[86],"Generative":[87],"Awareness),":[88],"plug-and-play":[90],"framework":[91],"repurposes":[93],"pre-trained":[95],"diffusion":[97],"model":[98],"as":[99],"Latent":[101],"World":[102],"Simulator.":[103],"By":[104],"extracting":[105],"spatiotemporal":[106],"features":[107],"intermediate":[109],"noise":[110],"levels":[111],"integrating":[113],"them":[114],"representations":[117],"via":[118],"token-level":[120],"adaptive":[121],"gated":[122],"fusion":[123],"mechanism,":[124],"enrich":[126],"MLLMs":[127],"dense":[129],"cues":[131],"without":[132],"supervision.":[135],"Extensive":[136],"experiments":[137],"across":[138],"scene":[140],"understanding,":[141],"reasoning,":[143],"embodied":[145],"manipulation":[146],"benchmarks":[147],"our":[150],"method":[151],"outperforms":[152],"state-of-the-art":[153],"baselines,":[154],"validating":[155],"generative":[157],"provide":[159],"scalable":[161],"foundation":[162],"for":[163],"physical-world":[164],"understanding.":[165],"Code":[166],"is":[167],"publicly":[168],"available":[169],"at":[170],"https://github.com/H-EmbodVis/VEGA-3D.":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-21T00:00:00"}