{"id":"https://openalex.org/W7162458606","doi":"https://doi.org/10.48550/arxiv.2605.24642","title":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","display_name":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-05-23","ids":{"openalex":"https://openalex.org/W7162458606","doi":"https://doi.org/10.48550/arxiv.2605.24642"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24642","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.2605.24642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103116438","display_name":"Yurou Yang","orcid":"https://orcid.org/0000-0001-5794-2769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yurou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069278373","display_name":"Muyuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Muyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137028494","display_name":"Roberto Martin-Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin-Martin, Roberto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079838311","display_name":"Martin Labrie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Labrie, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053446578","display_name":"Shreekant Gayaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gayaka, Shreekant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137023849","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuo, Cheng-Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137036935","display_name":"Luca Carlone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlone, Luca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.6047000288963318,"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":0.6047000288963318,"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":0.07900000363588333,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.06310000270605087,"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/intuition","display_name":"Intuition","score":0.6437000036239624},{"id":"https://openalex.org/keywords/geometric-design","display_name":"Geometric design","score":0.5753999948501587},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.557699978351593},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/geometric-series","display_name":"Geometric series","score":0.4902999997138977},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/geometric-shape","display_name":"Geometric shape","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C40319758","wikidata":"https://www.wikidata.org/wiki/Q5535477","display_name":"Geometric design","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C153363305","wikidata":"https://www.wikidata.org/wiki/Q1306887","display_name":"Geometric series","level":3,"score":0.4902999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4805999994277954},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C49777392","wikidata":"https://www.wikidata.org/wiki/Q5535495","display_name":"Geometric networks","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3253999948501587},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C154968394","wikidata":"https://www.wikidata.org/wiki/Q5535474","display_name":"Geometric analysis","level":5,"score":0.3073999881744385},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2777000069618225}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24642","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.2605.24642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24642","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5545035004615784}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"work":[1],"explores":[2],"new":[3],"opportunities":[4],"at":[5],"the":[6,24,50,64,127,130,160,166,185,199,202],"intersection":[7],"of":[8,66,93,187,194,201],"vision-language-action":[9],"models":[10,15],"(VLAs)":[11],"and":[12,60,96,135,143],"geometric":[13,26,42,55,72,112,203],"foundation":[14],"(GFMs)":[16],"for":[17,89,126],"3D":[18],"reconstruction,":[19],"such":[20],"as":[21,173,175],"VGGT.":[22],"While":[23],"resulting":[25],"VLAs":[27,38,110,134],"often":[28],"show":[29],"improved":[30],"performance,":[31],"it":[32],"remains":[33],"unclear":[34],"(i)":[35],"if":[36],"modern":[37],"already":[39],"have":[40],"sufficient":[41],"understanding":[43,56],"to":[44,53,83,103,141,147,177],"start":[45],"with,":[46],"(ii)":[47],"what":[48,62],"is":[49,63,102,140],"best":[51],"architecture":[52],"inject":[54,163],"into":[57],"a":[58,79,90,116,179],"VLA,":[59,167],"(iii)":[61],"effect":[65],"other":[67],"design":[68],"choices":[69,189],"that":[70,108],"affect":[71],"VLAs.":[73,151,204],"In":[74],"this":[75],"paper":[76],"we":[77,183],"provide":[78],"rigorous":[80,117],"experimental":[81],"analysis":[82,118,124],"shed":[84],"light":[85],"on":[86,120,198],"these":[87],"questions,":[88],"specific":[91],"choice":[92],"VLA":[94],"(GR00T-N1.5)":[95],"GFM":[97],"(VGGT).":[98],"Our":[99,137],"first":[100,128],"contribution":[101,139],"formalize":[104],"prior":[105],"work's":[106],"intuition":[107],"current":[109],"lack":[111],"understanding,":[113],"by":[114],"providing":[115],"based":[119],"linear":[121],"probing.":[122],"The":[123],"quantifies,":[125],"time,":[129],"\"geometric":[131],"gap\"":[132],"between":[133],"GFMs.":[136],"second":[138],"identify":[142],"compare":[144],"different":[145,155],"strategies":[146],"bridge":[148],"GFMs":[149],"with":[150],"We":[152],"implement":[153],"three":[154],"architectures,":[156],"which":[157],"differ":[158],"in":[159,165],"way":[161],"they":[162],"geometry":[164],"while":[168],"keeping":[169],"low-level":[170],"implementation":[171],"details":[172],"similar":[174],"possible,":[176],"ensure":[178],"fair":[180],"comparison.":[181],"Finally,":[182],"analyze":[184],"impact":[186],"non-architectural":[188],"(e.g.,":[190],"training":[191],"data,":[192],"number":[193],"cameras,":[195],"reconstruction":[196],"quality)":[197],"performance":[200]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}