{"id":"https://openalex.org/W7161128781","doi":"https://doi.org/10.48550/arxiv.2605.13276","title":"D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models","display_name":"D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161128781","doi":"https://doi.org/10.48550/arxiv.2605.13276"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.13276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125221891","display_name":"Yucheng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136152141","display_name":"Yongjian Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yongjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125195887","display_name":"Zhong Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136131664","display_name":"Wen Huang","orcid":"https://orcid.org/0009-0001-7302-9096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136177941","display_name":"Haoran Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124895814","display_name":"Haodong Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136129351","display_name":"Xiaolong Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041877213","display_name":"Shuai Di","orcid":"https://orcid.org/0000-0001-7466-9709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136186689","display_name":"Zhen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136137251","display_name":"Luqiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Luqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102937576","display_name":"Junwu Xiong","orcid":"https://orcid.org/0009-0008-2028-510X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Junwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136122110","display_name":"Yicheng Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Yicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"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":0.8263000249862671,"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":0.8263000249862671,"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":0.04639999940991402,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01360000018030405,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8205000162124634},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6804999709129333},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6460999846458435},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5199000239372253},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3785000145435333},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.3637000024318695},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8205000162124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7290999889373779},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6804999709129333},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6460999846458435},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.13276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"The":[0],"rapid":[1],"evolution":[2],"of":[3,51,114],"Embodied":[4],"AI":[5],"has":[6],"enabled":[7],"Vision-Language-Action":[8],"(VLA)":[9],"models":[10,27],"to":[11,24,38,95],"excel":[12],"in":[13,28,151],"multimodal":[14],"perception":[15],"and":[16,46,100,119,128,134,153,169],"task":[17],"execution.":[18],"However,":[19],"applying":[20],"Reinforcement":[21],"Learning":[22],"(RL)":[23],"these":[25,66],"massive":[26],"large-scale":[29,78],"distributed":[30,74],"environments":[31],"faces":[32],"severe":[33],"systemic":[34],"bottlenecks,":[35],"primarily":[36],"due":[37],"the":[39,47],"resource":[40],"conflict":[41,55],"between":[42,98],"high-fidelity":[43],"physical":[44],"simulation":[45,99],"intensive":[48],"VRAM/bandwidth":[49],"demands":[50],"deep":[52],"learning.":[53],"This":[54],"often":[56],"leaves":[57],"overall":[58],"throughput":[59,152],"constrained":[60],"by":[61],"execution-phase":[62],"inefficiencies.":[63],"To":[64],"address":[65],"challenges,":[67],"we":[68],"propose":[69],"D-VLA,":[70],"a":[71,105,123,173],"high-concurrency,":[72],"low-latency":[73],"RL":[75,149],"framework":[76,165],"for":[77,156,176],"embodied":[79,179],"foundation":[80],"models.":[81,159],"D-VLA":[82,145],"introduces":[83],"\"Plane":[84],"Decoupling,\"":[85],"physically":[86],"isolating":[87],"high-frequency":[88],"training":[89],"data":[90],"from":[91],"low-frequency":[92],"weight":[93],"control":[94],"eliminate":[96],"interference":[97],"optimization.":[101],"We":[102],"further":[103],"design":[104],"four-thread":[106],"asynchronous":[107],"\"Swimlane\"":[108],"pipeline,":[109],"enabling":[110],"full":[111],"parallel":[112],"overlap":[113],"sampling,":[115],"inference,":[116],"gradient":[117],"computation,":[118],"parameter":[120],"distribution.":[121],"Additionally,":[122],"dual-pool":[124],"VRAM":[125],"management":[126],"model":[127],"topology-aware":[129],"replication":[130],"resolve":[131],"memory":[132],"fragmentation":[133],"optimize":[135],"communication":[136],"efficiency.":[137],"Experiments":[138],"on":[139],"benchmarks":[140],"like":[141],"LIBERO":[142],"show":[143],"that":[144],"significantly":[146],"outperforms":[147],"mainstream":[148],"frameworks":[150],"sampling":[154],"efficiency":[155],"billion-parameter":[157],"VLA":[158],"In":[160],"trillion-parameter":[161],"scalability":[162],"tests,":[163],"our":[164],"maintains":[166],"exceptional":[167],"stability":[168],"linear":[170],"speedup,":[171],"providing":[172],"robust":[174],"system":[175],"high-performance":[177],"general-purpose":[178],"agents.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}