{"id":"https://openalex.org/W7155031436","doi":"https://doi.org/10.48550/arxiv.2604.17706","title":"OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL","display_name":"OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155031436","doi":"https://doi.org/10.48550/arxiv.2604.17706"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17706","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.2604.17706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002766256","display_name":"Haoxiang Jie","orcid":"https://orcid.org/0000-0001-6434-8119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie, Haoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005451910","display_name":"Yan Yaoyuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062694794","display_name":"Xiangyu Wei","orcid":"https://orcid.org/0000-0002-1504-2137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134153062","display_name":"Kailin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kailin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973346","display_name":"Hongjie Yan","orcid":"https://orcid.org/0009-0000-2553-2183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134189623","display_name":"Zhiyou Heng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng, Zhiyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084812005","display_name":"Daocheng Chen","orcid":"https://orcid.org/0000-0003-3101-6833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Daocheng","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":0.7871000170707703,"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":0.7871000170707703,"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":0.07729999721050262,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.583299994468689},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5824999809265137},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5374000072479248},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.42660000920295715},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4025000035762787},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924999952316284},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17706","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.2604.17706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17706","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":{"Visual-Language-Action":[0],"(VLA)":[1],"models":[2],"represent":[3],"a":[4,34,39,60],"paradigm":[5],"shift":[6],"in":[7,24],"embodied":[8],"AI,":[9],"yet":[10],"existing":[11,100],"frameworks":[12],"often":[13],"struggle":[14],"with":[15,69],"imprecise":[16],"spatial":[17],"perception,":[18],"suboptimal":[19],"multimodal":[20],"fusion,":[21],"and":[22,48,66,79,87,97],"instability":[23],"reinforcement":[25],"learning.":[26],"To":[27],"bridge":[28],"these":[29],"gaps,":[30],"we":[31,52],"propose":[32],"OmniVLA-RL,":[33],"novel":[35],"architecture":[36],"that":[37,91],"leverages":[38],"Mix-of-Transformers":[40],"(MoT)":[41],"design":[42],"to":[43,75],"synergistically":[44],"integrate":[45],"reasoning,":[46],"spatial,":[47],"action":[49,77],"experts.":[50],"Furthermore,":[51],"introduce":[53],"Flow-GSPO,":[54],"which":[55],"reformulates":[56],"flow":[57],"matching":[58],"as":[59],"Stochastic":[61],"Differential":[62],"Equation":[63],"(SDE)":[64],"process":[65],"integrates":[67],"it":[68],"Group":[70],"Segmented":[71],"Policy":[72],"Optimization":[73],"(GSPO)":[74],"enhance":[76],"precision":[78],"training":[80],"robustness.":[81],"Extensive":[82],"evaluations":[83],"on":[84],"the":[85,104],"LIBERO":[86],"LIBERO-Plus":[88],"benchmarks":[89],"demonstrate":[90],"OmniVLA-RL":[92],"achieves":[93],"decent":[94],"overall":[95],"performance":[96],"surpasses":[98],"mainstream":[99],"methods,":[101],"effectively":[102],"overcoming":[103],"fundamental":[105],"limitations":[106],"of":[107],"current":[108],"VLA":[109],"models.":[110]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}