{"id":"https://openalex.org/W7213373602","doi":"https://doi.org/10.48550/arxiv.2609.13812","title":"GeomVLA: Unifying Scene, Motion, and Action in 3D","display_name":"GeomVLA: Unifying Scene, Motion, and Action in 3D","publication_year":2026,"publication_date":"2026-09-12","ids":{"openalex":"https://openalex.org/W7213373602","doi":"https://doi.org/10.48550/arxiv.2609.13812"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.13812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.13812","pdf_url":"https://arxiv.org/pdf/2609.13812","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/2609.13812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133006031","display_name":"Ziyin Xiong","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":"Xiong, Ziyin","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/A5013545319","display_name":"Nikos Gkanatsios","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":"Gkanatsios, Nikolaos","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/A5056556464","display_name":"Moritz Reuss","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Reuss, Moritz","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008661738","display_name":"Katerina Fragkiadaki","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":"Fragkiadaki, Katerina","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"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":true,"cited_by_count":2,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9932000041007996,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.003599999938160181,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.9300000071525574},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.640999972820282},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6460000276565552},{"id":"https://openalex.org/keywords/geometric-consistency","display_name":"geometric consistency","score":0.4779999852180481},{"id":"https://openalex.org/keywords/libero-benchmark","display_name":"LIBERO benchmark","score":0.8659999966621399}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8101999759674072},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7343999743461609},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7117999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6898000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865000128746033},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6553999781608582},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6315000057220459},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2599000036716461}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.13812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.13812","pdf_url":"https://arxiv.org/pdf/2609.13812","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.2609.13812","doi":"https://doi.org/10.48550/arxiv.2609.13812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.13812","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:2609.13812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.13812","pdf_url":"https://arxiv.org/pdf/2609.13812","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213373602.pdf","grobid_xml":"https://content.openalex.org/works/W7213373602.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W4382334328","https://openalex.org/W4385473486","https://openalex.org/W4391949089","https://openalex.org/W4400267248","https://openalex.org/W4400601172","https://openalex.org/W4400612090","https://openalex.org/W4402354026","https://openalex.org/W4403622102","https://openalex.org/W4405434146","https://openalex.org/W4405655184","https://openalex.org/W4406072763","https://openalex.org/W4407384835","https://openalex.org/W4413145792","https://openalex.org/W4413156213","https://openalex.org/W4414051092","https://openalex.org/W4414674749","https://openalex.org/W4414761587","https://openalex.org/W4414975320","https://openalex.org/W4415183980","https://openalex.org/W4415272059","https://openalex.org/W4416261407","https://openalex.org/W4417080391","https://openalex.org/W4417219570","https://openalex.org/W4417453644","https://openalex.org/W6891880646","https://openalex.org/W6929480010","https://openalex.org/W6948104436","https://openalex.org/W7081569152","https://openalex.org/W7117563859","https://openalex.org/W7123340428","https://openalex.org/W7128767882","https://openalex.org/W7140999116","https://openalex.org/W7160553818","https://openalex.org/W7161684655"],"related_works":["https://openalex.org/W7223236592","https://openalex.org/W4417094684","https://openalex.org/W7168375719","https://openalex.org/W4417531254","https://openalex.org/W7167675971","https://openalex.org/W6910626880","https://openalex.org/W7165792067","https://openalex.org/W7162784169","https://openalex.org/W7133222765","https://openalex.org/W7140999116"],"abstract_inverted_index":{"We":[0,50],"present":[1],"GeomVLA,":[2],"a":[3,18,53,58,63,100],"Vision-Language-Action":[4],"(VLA)":[5],"model":[6],"that":[7,61,134],"unifies":[8],"perception,":[9],"latent":[10,64],"scene":[11,34,68,150],"motion":[12,89,152],"prediction,":[13,153],"and":[14,38,95,118,120,154],"action":[15,103],"generation":[16],"within":[17],"shared":[19],"robot-centric":[20],"3D":[21,33,54,101],"coordinate":[22],"frame.":[23],"Our":[24],"approach":[25],"lifts":[26],"pretrained":[27],"VLM":[28,48],"features":[29],"into":[30],"spatially":[31],"grounded":[32],"tokens":[35,90],"using":[36],"depth":[37],"camera":[39],"calibration,":[40],"while":[41],"retaining":[42],"the":[43,79,92,140,158],"semantic":[44],"representations":[45],"learned":[46],"during":[47],"pretraining.":[49,130],"further":[51],"introduce":[52],"Scene":[55],"Trajectory":[56],"Denoiser,":[57],"task-conditioned":[59],"module":[60],"learns":[62],"representation":[65],"of":[66],"how":[67],"points":[69],"are":[70,143],"expected":[71],"to":[72,98],"move":[73],"in":[74,124],"3D.":[75],"Rather":[76],"than":[77],"executing":[78],"predicted":[80],"trajectory":[81,93],"as":[82],"an":[83],"open-loop":[84],"plan,":[85],"GeomVLA":[86,108],"extracts":[87],"intermediate":[88],"from":[91],"denoiser":[94,104],"uses":[96],"them":[97],"condition":[99],"flow-based":[102],"through":[105],"geometry-aware":[106],"attention.":[107],"achieves":[109],"state-of-the-art":[110],"performance":[111,115],"on":[112,116],"CALVIN,":[113],"competitive":[114],"LIBERO":[117],"RoboTwin2.0,":[119],"outperforms":[121],"strong":[122],"baselines":[123],"real-world":[125],"manipulation":[126],"settings":[127],"without":[128],"robot-action":[129],"Extensive":[131],"ablations":[132],"show":[133],"future-motion":[135],"reasoning":[136],"alone":[137],"is":[138],"insufficient:":[139],"primary":[141],"gains":[142],"associated":[144],"with":[145],"maintaining":[146],"geometric":[147],"consistency":[148],"among":[149],"representation,":[151],"robot":[155],"actions":[156],"throughout":[157],"perception-to-action":[159],"pipeline.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-16T00:00:00"}