{"id":"https://openalex.org/W7151926737","doi":"https://doi.org/10.48550/arxiv.2604.05672","title":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","display_name":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151926737","doi":"https://doi.org/10.48550/arxiv.2604.05672"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.05672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05672","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.2604.05672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133227905","display_name":"Kaidong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409897","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-8604-6760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133194055","display_name":"Rongtao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Rongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133158574","display_name":"Yu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108303726","display_name":"Shuoshuo Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Shuoshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133209572","display_name":"Youpeng Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Youpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133185597","display_name":"Xiaoyu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133221885","display_name":"Minghao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133187219","display_name":"Weijia Liufu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liufu, Weijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133175433","display_name":"Liu Zihou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihou, Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043750444","display_name":"Kangyi Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Kangyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036187685","display_name":"Yangsong Zhang","orcid":"https://orcid.org/0000-0002-6764-3567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yangsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133229004","display_name":"Jiarun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jiarun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133203702","display_name":"Jingzhi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jingzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133233150","display_name":"Zihang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133199495","display_name":"Ruiyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ruiyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133192080","display_name":"Meng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133221117","display_name":"Jingming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jingming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133187787","display_name":"Shen Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133219538","display_name":"Xiaojun Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Xiaojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133220059","display_name":"Feng Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133194617","display_name":"Ivan Laptev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laptev, Ivan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133196162","display_name":"Xiaodan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Xiaodan","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":0.250900000333786,"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":0.250900000333786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.18060000240802765,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11460000276565552,"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/inference","display_name":"Inference","score":0.7663999795913696},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4318999946117401},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.39820000529289246},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3847000002861023},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.38339999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663999795913696},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7663999795913696},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45890000462532043},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37529999017715454},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.05672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05672","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.2604.05672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05672","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":{"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],"have":[3],"emerged":[4],"as":[5],"a":[6,45,106],"powerful":[7],"paradigm":[8],"for":[9,53,71,180],"open-world":[10],"robot":[11],"manipulation,":[12],"but":[13],"their":[14],"practical":[15],"deployment":[16],"is":[17],"often":[18],"constrained":[19],"by":[20,104],"cost:":[21],"billion-scale":[22],"VLM":[23,96,127],"backbones":[24],"and":[25,33,48,86,116,133,158,183,210],"iterative":[26],"diffusion/flow-based":[27],"action":[28,72,118,123],"heads":[29],"incur":[30],"high":[31],"latency":[32,179],"compute,":[34],"making":[35],"real-time":[36],"control":[37],"expensive":[38],"on":[39],"commodity":[40],"hardware.":[41],"We":[42,74],"present":[43],"A1,":[44],"fully":[46],"open-source":[47],"transparent":[49],"VLA":[50],"framework":[51],"designed":[52],"low-cost,":[54],"high-throughput":[55],"inference":[56,102,109,171,182],"without":[57],"sacrificing":[58],"manipulation":[59],"success;":[60],"Our":[61],"approach":[62],"leverages":[63],"pretrained":[64],"VLMs":[65],"that":[66,111,139],"provide":[67],"implicit":[68],"affordance":[69],"priors":[70],"generation.":[73],"release":[75],"the":[76,95,100,114,117],"full":[77,101],"training":[78],"stack":[79],"(training":[80],"code,":[81],"data/data-processing":[82],"pipeline,":[83],"intermediate":[84,126],"checkpoints,":[85],"evaluation":[87],"scripts)":[88],"to":[89,129,175,185],"enable":[90],"end-to-end":[91],"reproducibility.":[92],"Beyond":[93],"optimizing":[94],"alone,":[97],"A1":[98,163,196],"targets":[99],"pipeline":[103],"introducing":[105],"budget-aware":[107],"adaptive":[108],"scheme":[110],"jointly":[112],"accelerates":[113],"backbone":[115,187],"head.":[119],"Specifically,":[120],"we":[121],"monitor":[122],"consistency":[124],"across":[125,142],"layers":[128],"trigger":[130],"early":[131],"termination,":[132],"propose":[134],"Inter-Layer":[135],"Truncated":[136],"Flow":[137],"Matching":[138],"warm-starts":[140],"denoising":[141,151],"layers,":[143],"enabling":[144],"accurate":[145],"actions":[146],"with":[147,190],"substantially":[148],"fewer":[149],"effective":[150],"iterations.":[152],"Across":[153],"simulation":[154],"benchmarks":[155],"(LIBERO,":[156],"VLABench)":[157],"real":[159],"robots":[160],"(Franka,":[161],"AgiBot),":[162],"achieves":[164,197],"state-of-the-art":[165],"success":[166,200],"rates":[167],"while":[168],"significantly":[169],"reducing":[170],"cost":[172],"(e.g.,":[173],"up":[174,184],"72%":[176],"lower":[177],"per-episode":[178],"flow-matching":[181],"76.6%":[186],"computation":[188],"reduction":[189],"minor":[191],"performance":[192],"degradation).":[193],"On":[194],"RoboChallenge,":[195],"an":[198],"average":[199],"rate":[201],"of":[202],"29.00%,":[203],"outperforming":[204],"baselines":[205],"including":[206],"pi0(28.33%),":[207],"X-VLA":[208],"(21.33%),":[209],"RDT-1B":[211],"(15.00%).":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-09T00:00:00"}