{"id":"https://openalex.org/W7083292721","doi":"https://doi.org/10.48550/arxiv.2509.19480","title":"OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation","display_name":"OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation","publication_year":2025,"publication_date":"2025-09-23","ids":{"openalex":"https://openalex.org/W7083292721","doi":"https://doi.org/10.48550/arxiv.2509.19480"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2509.19480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19480","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,"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.2509.19480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hirose, Noriaki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirose, Noriaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Glossop, Catherine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Glossop, Catherine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shah, Dhruv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Dhruv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Levine, Sergey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levine, Sergey","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":true,"primary_topic":{"id":"https://openalex.org/T10492","display_name":"Microtubule and mitosis dynamics","score":0.9104999899864197,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10492","display_name":"Microtubule and mitosis dynamics","score":0.9104999899864197,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10301","display_name":"Mitochondrial Function and Pathology","score":0.018400000408291817,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10587","display_name":"Autophagy in Disease and Therapy","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5659999847412109},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5232999920845032},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5156999826431274},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.508400022983551},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5066999793052673},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4936999976634979},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47620001435279846},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4442000091075897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.572700023651123},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5307000279426575},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5232999920845032},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4442000091075897},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.32749998569488525},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2509.19480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19480","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,"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.2509.19480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19480","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,"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":{"Humans":[0],"can":[1],"flexibly":[2],"interpret":[3],"and":[4,50,80,91,125,142,160,170,181,185,201,206],"compose":[5],"different":[6,43],"goal":[7,46,67,85],"specifications,":[8],"such":[9],"as":[10,94,96],"language":[11,149],"instructions,":[12],"spatial":[13],"coordinates,":[14],"or":[15],"visual":[16,126],"references,":[17],"when":[18],"navigating":[19],"to":[20,39,120,135,139,145,167],"a":[21,33,57,75,100,162,176,186],"destination.":[22],"In":[23,52],"contrast,":[24],"most":[25],"existing":[26],"robotic":[27,61,192],"navigation":[28,183],"policies":[29],"are":[30,48],"trained":[31],"on":[32,209],"single":[34],"modality,":[35],"limiting":[36],"their":[37,97],"adaptability":[38],"real-world":[40],"scenarios":[41],"where":[42],"forms":[44],"of":[45,112],"specification":[47],"natural":[49,92,148],"complementary.":[51],"this":[53],"work,":[54],"we":[55],"present":[56,196],"training":[58,207],"framework":[59],"for":[60,69,165,189],"foundation":[62,164,193],"models":[63],"that":[64,153],"enables":[65],"omni-modal":[66,191],"conditioning":[68],"vision-based":[70],"navigation.":[71],"Our":[72],"approach":[73],"leverages":[74],"high-capacity":[76],"vision-language-action":[77],"(VLA)":[78],"backbone":[79],"trains":[81],"with":[82],"three":[83],"primary":[84],"modalities:":[86],"2D":[87],"poses,":[88],"egocentric":[89],"images,":[90],"language,":[93],"well":[95],"combinations,":[98],"through":[99],"randomized":[101],"modality":[102],"fusion":[103],"strategy.":[104],"This":[105],"design":[106],"not":[107],"only":[108],"expands":[109],"the":[110,118,143],"pool":[111],"usable":[113],"datasets":[114],"but":[115],"also":[116],"encourages":[117],"policy":[119],"develop":[121],"richer":[122],"geometric,":[123],"semantic,":[124],"representations.":[127],"The":[128],"resulting":[129],"model,":[130],"OmniVLA,":[131],"achieves":[132],"strong":[133],"generalization":[134],"unseen":[136],"environments,":[137],"robustness":[138],"scarce":[140],"modalities,":[141],"ability":[144],"follow":[146],"novel":[147],"instructions.":[150],"We":[151,172,195],"demonstrate":[152],"OmniVLA":[154,174,199],"outperforms":[155],"specialist":[156],"baselines":[157],"across":[158],"modalities":[159,169],"offers":[161],"flexible":[163,182],"fine-tuning":[166],"new":[168],"tasks.":[171],"believe":[173],"provides":[175],"step":[177],"toward":[178],"broadly":[179],"generalizable":[180],"policies,":[184],"scalable":[187],"path":[188],"building":[190],"models.":[194],"videos":[197],"showcasing":[198],"performance":[200],"will":[202],"release":[203],"its":[204],"checkpoints":[205],"code":[208],"our":[210],"project":[211],"page.":[212]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}