{"id":"https://openalex.org/W7147084562","doi":"https://doi.org/10.48550/arxiv.2603.28565","title":"StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation","display_name":"StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147084562","doi":"https://doi.org/10.48550/arxiv.2603.28565"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28565","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.2603.28565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132575256","display_name":"Yiran Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071570622","display_name":"Dongqi Guo","orcid":"https://orcid.org/0000-0002-2952-7047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Dongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132682184","display_name":"Tianchen Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Tianchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132648330","display_name":"Feng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132582789","display_name":"Liangzhi Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Liangzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132579379","display_name":"Chao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361565","display_name":"Zhijian Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, ZhiJian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132675711","display_name":"Qihua Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Qihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132618585","display_name":"XiaoShuai Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, XiaoShuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132703071","display_name":"Qingmin Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Qingmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445182","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-2448-3049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"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":0.970300018787384,"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":0.970300018787384,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006599999964237213,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8266000151634216},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6101999878883362},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.4643000066280365},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.41110000014305115},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3610000014305115},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.33970001339912415}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8266000151634216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230000138282776},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28220000863075256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28565","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.2603.28565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28565","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,20],"have":[3],"demonstrated":[4],"exceptional":[5],"performance":[6],"in":[7,30,95],"natural":[8],"language-driven":[9],"perception":[10],"and":[11,42,47,62,79,82,107,131,148,157,170],"control.":[12],"However,":[13,33],"the":[14,50,53,56,75,87,102,114,126,144,159],"high":[15,63],"computational":[16],"cost":[17],"of":[18,37,52,116,128,146,161],"VLA":[19,38,93],"poses":[21],"significant":[22],"efficiency":[23],"challenges,":[24],"particularly":[25],"for":[26,49,77],"resource-constrained":[27],"edge":[28],"platforms":[29],"real-world":[31],"deployments.":[32],"since":[34],"different":[35],"stages":[36,94],"(observation,":[39],"action":[40,105,109,117,129,137],"generation":[41,130],"execution)":[43],"must":[44],"proceed":[45],"sequentially,":[46],"wait":[48],"completion":[51],"preceding":[54],"stage,":[55],"system":[57],"suffers":[58],"from":[59],"frequent":[60],"halting":[61,173],"latency.":[64],"To":[65],"address":[66],"this,":[67],"We":[68],"conduct":[69],"a":[70,96,165],"systematic":[71],"analysis":[72],"to":[73,89],"identify":[74],"challenges":[76],"fast":[78],"fluent":[80],"generation,":[81],"propose":[83],"enabling":[84],"VLAs":[85],"with":[86],"ability":[88],"asynchronously":[90],"parallelize":[91],"across":[92],"\"streaming\"":[97],"manner.":[98],"First,":[99],"we":[100,134],"eliminate":[101],"reliance":[103],"on":[104],"chunking":[106],"adopt":[108],"flow":[110],"matching,":[111],"which":[112],"learns":[113],"trajectory":[115],"flows":[118],"rather":[119],"than":[120],"denoising":[121],"chunk-wise":[122],"actions.":[123],"It":[124,163],"overlaps":[125],"latency":[127,145,168],"execution.":[132,162],"Second,":[133],"design":[135],"an":[136],"saliency-aware":[138],"adaptive":[139],"observation":[140],"mechanism,":[141],"thereby":[142],"overlapping":[143],"execution":[147,172],"observation.":[149],"Without":[150],"sacrificing":[151],"performance,":[152],"StreamingVLA":[153],"achieves":[154,164],"substantial":[155],"speedup":[156,169],"improves":[158],"fluency":[160],"2.4":[166],"$\\times$":[167],"reduces":[171],"by":[174],"6.5":[175],"$\\times$.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}