{"id":"https://openalex.org/W7131819932","doi":"https://doi.org/10.48550/arxiv.2602.22663","title":"Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline","display_name":"Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131819932","doi":"https://doi.org/10.48550/arxiv.2602.22663"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.22663","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127183206","display_name":"Wenxuan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Song, Wenxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127413898","display_name":"Jiayi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiayi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127371310","display_name":"Xiaoquan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xiaoquan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111348803","display_name":"Huashuo Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Huashuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121223992","display_name":"Yikai Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Yikai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127304081","display_name":"Wei Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127456253","display_name":"Pengxiang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Pengxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127090568","display_name":"Han Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079050779","display_name":"Tongxin Wang","orcid":"https://orcid.org/0000-0001-5826-1842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tongxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217786","display_name":"Pengxu Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Pengxu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102548895","display_name":"Zhide Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Zhide","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109886746","display_name":"Haodong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Haodong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127472032","display_name":"Donglin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Donglin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127379422","display_name":"Jun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127136279","display_name":"Haoang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5127183206"],"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":0.863099992275238,"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":0.863099992275238,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.03920000046491623,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.016599999740719795,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8751000165939331},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7455999851226807},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6220999956130981},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6172000169754028},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5436000227928162},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5221999883651733},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8751000165939331},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7455999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333999872207642},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6172000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.536899983882904},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2780210234","wikidata":"https://www.wikidata.org/wiki/Q422638","display_name":"Action plan","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.22663","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.22663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22663","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.22663","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"emerged":[4],"as":[5,83,180],"a":[6,36,47,106,121,141],"generalist":[7],"robotic":[8],"agent.":[9],"However,":[10],"existing":[11],"VLAs":[12],"are":[13],"hindered":[14],"by":[15,100],"excessive":[16],"parameter":[17],"scales,":[18],"prohibitive":[19],"pre-training":[20],"requirements,":[21],"and":[22,39,56,70,94,130,147,158,168,195,202],"limited":[23],"applicability":[24],"to":[25,75,155,199],"diverse":[26,51],"embodiments.":[27],"To":[28,133],"improve":[29],"the":[30,57,152,164,181],"practicality":[31,93],"of":[32,62,91,166,170],"VLAs,":[33],"we":[34,44,86,103],"propose":[35,45],"comprehensive":[37],"benchmark":[38,49],"an":[40],"improved":[41],"baseline.":[42],"First,":[43],"CEBench,":[46],"new":[48],"spanning":[50],"embodiments":[52,162],"in":[53],"both":[54],"simulation":[55],"real":[58],"world":[59],"with":[60,125],"consideration":[61],"domain":[63],"randomization.":[64],"We":[65,189],"collect":[66],"14.4k":[67],"simulated":[68],"trajectories":[69,74],"1.6k":[71],"real-world":[72,174],"expert-curated":[73],"support":[76],"training":[77,143],"on":[78,115,136],"CEBench.":[79],"Second,":[80],"using":[81],"CEBench":[82],"our":[84],"testbed,":[85],"study":[87],"three":[88],"critical":[89],"aspects":[90],"VLAs'":[92],"offer":[95],"several":[96],"key":[97],"findings.":[98],"Informed":[99],"these":[101],"findings,":[102],"introduce":[104],"LLaVA-VLA,":[105],"lightweight":[107],"yet":[108],"powerful":[109],"VLA":[110,184],"designed":[111],"for":[112,186],"practical":[113],"deployment":[114],"consumer-grade":[116],"GPUs.":[117],"Architecturally,":[118],"it":[119,179],"integrates":[120],"compact":[122],"VLM":[123],"backbone":[124],"multi-view":[126],"perception,":[127],"proprioceptive":[128],"tokenization,":[129],"action":[131,153],"chunking.":[132],"eliminate":[134],"reliance":[135],"costly":[137],"pre-training,":[138],"LLaVA-VLA":[139,150,171],"adopts":[140],"two-stage":[142],"paradigm":[144],"including":[145],"post-training":[146],"fine-tuning.":[148],"Furthermore,":[149],"extends":[151],"space":[154],"unify":[156],"navigation":[157],"manipulation.":[159,188],"Experiments":[160],"across":[161],"demonstrate":[163],"capabilities":[165],"generalization":[167],"versatility":[169],",":[172],"while":[173],"mobile":[175,187],"manipulation":[176],"experiments":[177],"establish":[178],"first":[182],"end-to-end":[183],"model":[185],"will":[190],"open-source":[191],"all":[192],"datasets,":[193],"codes,":[194],"checkpoints":[196],"upon":[197],"acceptance":[198],"foster":[200],"reproducibility":[201],"future":[203],"research.":[204]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-28T00:00:00"}