{"id":"https://openalex.org/W7204487596","doi":"https://doi.org/10.48550/arxiv.2608.25924","title":"Visual General Intelligence: A White Paper","display_name":"Visual General Intelligence: A White Paper","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204487596","doi":"https://doi.org/10.48550/arxiv.2608.25924"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25924","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25924","pdf_url":"https://arxiv.org/pdf/2608.25924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011507481","display_name":"Hirokatsu Kataoka","orcid":"https://orcid.org/0000-0001-8844-165X","observed_orcids":["https://orcid.org/0000-0001-8844-165X"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Kataoka, Hirokatsu","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)","Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069581739","display_name":"Yoshihiro Fukuhara","orcid":"https://orcid.org/0000-0001-8892-5339","observed_orcids":["https://orcid.org/0000-0001-8892-5339"]},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fukuhara, Yoshihiro","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148457334","display_name":"Yonglong Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian, Yonglong","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032886186","display_name":"Shangzhe Wu","orcid":"https://orcid.org/0000-0003-1011-5963","observed_orcids":["https://orcid.org/0000-0003-1011-5963"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wu, Shangzhe","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115539448","display_name":"Oishi Deb","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deb, Oishi","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121601510","display_name":"Ryousuke Yamada","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153582","display_name":"University of Technology Nuremberg","ror":"https://ror.org/02sv65x64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4387153582"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Yamada, Ryousuke","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)","University of Technology Nuremberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"University of Technology Nuremberg","institution_ids":["https://openalex.org/I4387153582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083153177","display_name":"Christian Rupprecht","orcid":"https://orcid.org/0000-0003-3994-8045","observed_orcids":["https://orcid.org/0000-0003-3994-8045"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rupprecht, Christian","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148456157","display_name":"Jianyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wang, Jianyuan","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121680674","display_name":"Kohsuke Ide","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ide, Kohsuke","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)","University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093775162","display_name":"Koichi Namekata","orcid":"https://orcid.org/0009-0001-6146-5659","observed_orcids":["https://orcid.org/0009-0001-6146-5659"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Namekata, Koichi","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148445139","display_name":"Xianzheng Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ma, Xianzheng","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103016306","display_name":"Yiming Chen","orcid":"https://orcid.org/0000-0002-0720-4642","observed_orcids":["https://orcid.org/0000-0002-0720-4642"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen, Yiming","raw_affiliation_strings":["Visual Geometry Group (VGG) , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group (VGG) , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043113119","display_name":"Robert Geirhos","orcid":"https://orcid.org/0000-0001-7698-3187","observed_orcids":["https://orcid.org/0000-0001-7698-3187"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geirhos, Robert","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031731960","display_name":"Aditi Raghunathan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghunathan, Aditi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102985946","display_name":"Yuki M. Asano","orcid":"https://orcid.org/0000-0002-8533-4020","observed_orcids":["https://orcid.org/0000-0002-8533-4020","https://orcid.org/0000-0003-2115-1417"]},"institutions":[{"id":"https://openalex.org/I4387153582","display_name":"University of Technology Nuremberg","ror":"https://ror.org/02sv65x64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4387153582"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asano, Yuki M.","raw_affiliation_strings":["University of Technology Nuremberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Nuremberg","institution_ids":["https://openalex.org/I4387153582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732373","display_name":"Deva Ramanan","orcid":"https://orcid.org/0009-0008-9180-8983","observed_orcids":["https://orcid.org/0009-0008-9180-8983","https://orcid.org/0009-0007-3773-0954"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramanan, Deva","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134817267","display_name":"David Fouhey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fouhey, David","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665482","display_name":"Andrew J. Davison","orcid":"https://orcid.org/0000-0002-3784-099X","observed_orcids":["https://orcid.org/0000-0002-3784-099X"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Davison, Andrew J.","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041777043","display_name":"Yilun Du","orcid":"https://orcid.org/0000-0001-6792-5946","observed_orcids":["https://orcid.org/0000-0001-6792-5946"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du, Yilun","raw_affiliation_strings":["Harvard University 13"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University 13","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X","observed_orcids":["https://orcid.org/0000-0002-4176-343X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Jiajun","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135384573","display_name":"Zhuang Liu","orcid":"https://orcid.org/0000-0001-6898-5908","observed_orcids":["https://orcid.org/0000-0001-6898-5908"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Zhuang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.7056000232696533,"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":0.7056000232696533,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1842000037431717,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.040300000458955765,"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/artificial-general-intelligence","display_name":"artificial general intelligence","score":0.9259999990463257},{"id":"https://openalex.org/keywords/visual-intelligence","display_name":"visual intelligence","score":0.8450000286102295},{"id":"https://openalex.org/keywords/visual-modality","display_name":"visual modality","score":0.5789999961853027},{"id":"https://openalex.org/keywords/geometry-understanding","display_name":"geometry understanding","score":0.6320000290870667},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"multimodal learning","score":0.597000002861023}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5074999928474426},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.46939998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43860000371932983},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37229999899864197},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C63075964","wikidata":"https://www.wikidata.org/wiki/Q3277307","display_name":"Visual rhetoric","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25924","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25924","pdf_url":"https://arxiv.org/pdf/2608.25924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25924","doi":"https://doi.org/10.48550/arxiv.2608.25924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25924","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25924","pdf_url":"https://arxiv.org/pdf/2608.25924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"},{"id":"https://openalex.org/F4320321679","display_name":"Ministry of Economy, Trade and Industry","ror":"https://ror.org/055tm7f07"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320334833","display_name":"Agency for Natural Resources and Energy","ror":"https://ror.org/055tm7f07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204487596.pdf","grobid_xml":"https://content.openalex.org/works/W7204487596.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2794549886","https://openalex.org/W2982534705","https://openalex.org/W4385430554","https://openalex.org/W4391555771","https://openalex.org/W4392270920","https://openalex.org/W4392828142","https://openalex.org/W4394972242","https://openalex.org/W4402354127","https://openalex.org/W4414681495","https://openalex.org/W4417172999","https://openalex.org/W4417534140","https://openalex.org/W7083319242","https://openalex.org/W7106121179","https://openalex.org/W7131428269","https://openalex.org/W7133498487","https://openalex.org/W7147657823","https://openalex.org/W7148869130","https://openalex.org/W7160927230","https://openalex.org/W7161276074","https://openalex.org/W7161581047","https://openalex.org/W7164586008","https://openalex.org/W7164814104","https://openalex.org/W7167059631"],"related_works":["https://openalex.org/W4380993802","https://openalex.org/W7139114521","https://openalex.org/W7108654851","https://openalex.org/W7109002114","https://openalex.org/W4404003099","https://openalex.org/W7220842771","https://openalex.org/W4392867136","https://openalex.org/W7106264755","https://openalex.org/W4221167444","https://openalex.org/W6910561986"],"abstract_inverted_index":{"This":[0,56],"paper":[1,98],"reconsiders":[2],"intelligence":[3,11,67,86,102],"from":[4,13,70,108],"a":[5,20,58,90,119],"vision-centered":[6],"perspective":[7],"and":[8,16,64,77,111,148,158],"examines":[9],"whether":[10,84],"emerging":[12],"visual":[14,71,85,100,123,140],"experience":[15],"learning":[17,146],"may":[18],"provide":[19],"pathway":[21,91],"toward":[22,92],"AGI.":[23],"In":[24,79],"the":[25,30,33,36,128,136,139,143,145,149,156],"language":[26,47],"domain,":[27],"beginning":[28],"with":[29,53],"introduction":[31],"of":[32,66,122],"Transformer":[34],"architecture,":[35],"GPT":[37],"series":[38],"has":[39],"demonstrated":[40],"transfer":[41],"to":[42,95,117,126],"unseen":[43],"tasks":[44],"through":[45],"autoregressive":[46],"modeling":[48],"on":[49],"web-scale":[50],"text":[51],"combined":[52],"aggressive":[54],"scaling.":[55],"raises":[57],"natural":[59],"question,":[60],"namely,":[61],"what":[62],"capabilities":[63],"forms":[65],"can":[68,87],"emerge":[69],"modalities":[72,160],"such":[73,161],"as":[74,89,99,155,162],"images,":[75],"videos,":[76],"geometry?":[78],"this":[80,97],"paper,":[81],"we":[82],"discuss":[83],"serve":[88],"AGI,":[93],"referred":[94],"in":[96,135],"general":[101],"(VGI),":[103],"by":[104],"bringing":[105],"together":[106],"contributors":[107],"diverse":[109],"standpoints":[110],"affiliations.":[112],"Our":[113],"aim":[114],"is":[115],"not":[116],"offer":[118],"single":[120],"definition":[121],"intelligence,":[124],"but":[125],"clarify":[127],"principles":[129],"that":[130],"computer":[131],"vision":[132],"should":[133],"pursue":[134],"AGI":[137],"era,":[138],"input":[141],"modalities,":[142],"benchmarks,":[144],"paradigms,":[147],"relationship":[150],"between":[151],"vision,":[152],"when":[153],"taken":[154],"core,":[157],"other":[159],"language.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}
