{"id":"https://openalex.org/W4416891949","doi":"https://doi.org/10.1109/iccv51701.2025.01032","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","display_name":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416891949","doi":"https://doi.org/10.1109/iccv51701.2025.01032"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102838052","display_name":"Yating Wang","orcid":"https://orcid.org/0009-0007-7127-4825"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yating Wang","raw_affiliation_strings":["Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101301823","display_name":"Haoyi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyi Zhu","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000903991","display_name":"Mingyu Liu","orcid":"https://orcid.org/0000-0002-8752-7950"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Liu","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015582569","display_name":"Jiange Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jiange Yang","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077175165","display_name":"Haoshu Fang","orcid":"https://orcid.org/0000-0003-3108-6305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao-Shu Fang","raw_affiliation_strings":["SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SJTU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066737763","display_name":"Tong He","orcid":"https://orcid.org/0000-0002-1248-0975"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tong He","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34895878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11089","last_page":"11099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.415800005197525,"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":0.415800005197525,"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":0.23739999532699585,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.13519999384880066,"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/scalability","display_name":"Scalability","score":0.6496999859809875},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6216999888420105},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5091000199317932},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46630001068115234},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6496999859809875},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6216999888420105},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.01016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01016","pdf_url":"https://arxiv.org/pdf/2507.01016","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01016","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01016","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":"pmh:oai:arXiv.org:2507.01016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01016","pdf_url":"https://arxiv.org/pdf/2507.01016","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416891949.pdf","grobid_xml":"https://content.openalex.org/works/W4416891949.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,125],"introduce":[4],"an":[5],"innovative":[6],"vector":[7],"quantization":[8],"based":[9],"action":[10,16,57,100,183],"tokenizer":[11,35,62,154,184],"built":[12],"upon":[13],"the":[14,61,93,143,150,179,197],"largest-scale":[15],"trajectory":[17,147],"dataset":[18,32],"to":[19,36,67,82,106,163],"date,":[20],"leveraging":[21],"over":[22],"100":[23],"times":[24],"more":[25,55,200],"data":[26,114,148],"than":[27],"previous":[28],"approaches.":[29],"This":[30],"extensive":[31,127],"enables":[33],"our":[34,89,123,153,182],"capture":[37],"rich":[38],"spatiotemporal":[39],"dynamics,":[40],"resulting":[41],"in":[42,74,129,173,206],"a":[43,68,75,109,164,186],"model":[44],"that":[45,92,141],"not":[46],"only":[47],"accelerates":[48],"inference":[49],"but":[50],"also":[51],"generates":[52],"smoother":[53],"and":[54,98,133,188,202],"coherent":[56],"outputs.":[58],"Once":[59],"trained,":[60],"can":[63],"be":[64],"seamlessly":[65],"adapted":[66],"wide":[69],"range":[70],"of":[71,88,112,145,152,181],"downstream":[72,156],"tasks":[73,157,172],"zero-shot":[76],"manner,":[77],"from":[78],"short-horizon":[79],"reactive":[80],"behaviors":[81],"long-horizon":[83,174],"planning.":[84],"A":[85],"key":[86],"finding":[87],"work":[90],"is":[91,102],"domain":[94],"gap":[95],"between":[96],"synthetic":[97,113,146],"real":[99,135],"trajectories":[101],"marginal,":[103],"allowing":[104],"us":[105],"effectively":[107],"utilize":[108],"vast":[110],"amount":[111],"during":[115],"training":[116],"without":[117],"compromising":[118],"real-world":[119,171],"performance.":[120],"To":[121],"validate":[122],"approach,":[124],"conducted":[126],"experiments":[128],"both":[130],"simulated":[131],"environments":[132],"on":[134,155,169],"robotic":[136,204],"platforms.":[137],"The":[138],"results":[139],"demonstrate":[140],"as":[142,185],"volume":[144],"increases,":[149],"performance":[151],"improves":[158],"significantly-most":[159],"notably,":[160],"achieving":[161],"up":[162],"30%":[165],"higher":[166],"success":[167],"rate":[168],"two":[170],"scenarios.":[175],"These":[176],"findings":[177],"highlight":[178],"potential":[180],"robust":[187],"scalable":[189],"solution":[190],"for":[191,199],"real-time":[192],"embodied":[193],"intelligence":[194],"systems,":[195],"paving":[196],"way":[198],"efficient":[201],"reliable":[203],"control":[205],"diverse":[207],"application":[208],"domains.Project":[209],"website:":[210],"https://xiaoxiao0406.github.io/vqvla.github.io":[211]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}