{"id":"https://openalex.org/W7214937700","doi":"https://doi.org/10.48550/arxiv.2609.38078","title":"MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation","display_name":"MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214937700","doi":"https://doi.org/10.48550/arxiv.2609.38078"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38078","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38078","pdf_url":"https://arxiv.org/pdf/2609.38078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.38078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153625088","display_name":"Bingxuan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153583604","display_name":"Siqi Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293264","display_name":"Yizhuo Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yizhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153641545","display_name":"Jiarui Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jiarui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558","observed_orcids":["https://orcid.org/0000-0002-5511-2558","https://orcid.org/0000-0001-5818-4285","https://orcid.org/0000-0002-7025-6365","https://orcid.org/0000-0002-8838-4963","https://orcid.org/0000-0001-6212-4891","https://orcid.org/0000-0002-3506-0180","https://orcid.org/0000-0002-6807-0641","https://orcid.org/0000-0003-1148-4322","https://orcid.org/0000-0002-0131-0129","https://orcid.org/0000-0001-8163-3050","https://orcid.org/0000-0002-3481-6062"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153558688","display_name":"Huan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Huan","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":true,"cited_by_count":1,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0005000000237487257,"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":0.0003000000142492354,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.8500000238418579},{"id":"https://openalex.org/keywords/asynchronous-execution","display_name":"asynchronous execution","score":0.40700000524520874},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.5479999780654907},{"id":"https://openalex.org/keywords/robustness-to-disturbances","display_name":"robustness to disturbances","score":0.7110000252723694},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.5479999780654907},{"id":"https://openalex.org/keywords/embodied-reasoning","display_name":"embodied reasoning","score":0.8059999942779541},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72079998254776},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855000019073486},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.3677000105381012},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.3158000111579895},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3091000020503998},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.26589998602867126},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38078","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38078","pdf_url":"https://arxiv.org/pdf/2609.38078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38078","doi":"https://doi.org/10.48550/arxiv.2609.38078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38078","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38078","pdf_url":"https://arxiv.org/pdf/2609.38078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214937700.pdf","grobid_xml":"https://content.openalex.org/works/W7214937700.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W4383097638","https://openalex.org/W4402353985","https://openalex.org/W4414050921","https://openalex.org/W4414079054","https://openalex.org/W4414970058","https://openalex.org/W4417276882","https://openalex.org/W7108228588","https://openalex.org/W7140328093","https://openalex.org/W7153046097","https://openalex.org/W7160304585","https://openalex.org/W7163380451","https://openalex.org/W7164000068","https://openalex.org/W7164891033","https://openalex.org/W7165126606","https://openalex.org/W7167029019","https://openalex.org/W7167900256","https://openalex.org/W7168276635","https://openalex.org/W7168379487","https://openalex.org/W7172485217","https://openalex.org/W7212325948","https://openalex.org/W7214028830"],"related_works":["https://openalex.org/W7221549768","https://openalex.org/W7128744708","https://openalex.org/W4416054496","https://openalex.org/W7128056300","https://openalex.org/W7157292097","https://openalex.org/W4416433219","https://openalex.org/W4415274508","https://openalex.org/W4416258814","https://openalex.org/W4405031329","https://openalex.org/W7163515543"],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,34,59,102],"have":[3],"advanced":[4],"robotic":[5,40,256],"manipulation,":[6],"but":[7,53],"their":[8,19],"zero-shot":[9,180,255],"generalization":[10],"in":[11],"new":[12],"tasks":[13],"and":[14,18,60,65,92,134,139,165,174,199,224,248],"environments":[15],"remains":[16],"limited,":[17],"reliance":[20],"on":[21,56,100,160,191],"specialized":[22],"training":[23],"keeps":[24],"them":[25],"from":[26,29,88],"benefiting":[27],"directly":[28,87],"rapidly":[30],"advancing":[31],"general-purpose":[32,74,238],"vision-language":[33],"(VLMs).":[35],"In":[36,115],"parallel,":[37],"recent":[38],"agentic":[39],"systems":[41],"leverage":[42],"VLMs":[43],"for":[44,50,177],"high-level":[45],"reasoning":[46,86],"or":[47,110,149],"coding":[48,108,147],"agents":[49,109],"robot":[51,79,122,132,195],"control,":[52],"often":[54],"depend":[55],"extensive":[57],"external":[58,101],"tools,":[61],"introducing":[62],"additional":[63,150],"complexity":[64],"cost.":[66],"This":[67],"motivates":[68],"us":[69],"to":[70,95,130,219],"ask:":[71],"Can":[72],"a":[73,78,121,192,206,237],"VLM":[75,208,230],"itself":[76],"operate":[77],"more":[80],"like":[81,113],"the":[82,161,178,203,213],"human":[83],"teleoperator":[84],"by":[85],"observations,":[89],"issuing":[90],"actions,":[91],"continuously":[93],"adapting":[94],"execution":[96,250],"feedback,":[97,135],"without":[98],"relying":[99],"such":[103,153],"as":[104,154,229],"learned":[105],"action":[106,225,246],"experts,":[107],"grounding":[111,151],"tools":[112,152],"SAM3?":[114],"this":[116],"work,":[117],"we":[118,182],"introduce":[119],"MotorMind,":[120],"manipulation":[123,198],"harness":[124],"that":[125,236],"connects":[126],"VLM-proposed":[127],"mid-level":[128,245],"actions":[129],"deterministic":[131],"control":[133],"with":[136,170,205,242],"asynchronous":[137,249],"monitoring":[138],"background":[140],"memory":[141],"updates.":[142],"Without":[143],"task-specific":[144],"policy":[145],"training,":[146],"agents,":[148],"SAM3,":[155],"MotorMind":[156],"achieves":[157],"66.7%":[158],"success":[159,190],"base":[162],"LIBERO-PRO":[163],"suites":[164],"53.8%":[166],"under":[167],"perturbations,":[168],"compared":[169],"at":[171],"most":[172],"13.3%":[173],"19.2%,":[175],"respectively,":[176],"prior":[179],"methods":[181],"evaluate.":[183],"The":[184],"same":[185],"interface":[186],"reaches":[187],"95%":[188],"average":[189],"real":[193],"xArm6":[194],"across":[196],"direct":[197],"human-perturbation":[200],"settings.":[201],"Replacing":[202],"backbone":[204],"stronger":[207],"further":[209],"improves":[210],"performance,":[211],"while":[212],"remaining":[214],"failures":[215],"-":[216,227],"primarily":[217],"due":[218],"visual":[220],"grounding,":[221],"embodied":[222],"reasoning,":[223],"knowledge":[226],"decrease":[228],"capability":[231],"improves.":[232],"These":[233],"results":[234],"show":[235],"VLM,":[239],"when":[240],"equipped":[241],"an":[243],"appropriate":[244],"representation":[247],"harness,":[251],"can":[252],"perform":[253],"effective":[254],"manipulation.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-01T00:00:00"}