{"id":"https://openalex.org/W4410104757","doi":"https://doi.org/10.1007/s40747-025-01893-x","title":"VLA-Grasp: a vision-language-action modeling with cross-modality fusion for task-oriented grasping","display_name":"VLA-Grasp: a vision-language-action modeling with cross-modality fusion for task-oriented grasping","publication_year":2025,"publication_date":"2025-05-06","ids":{"openalex":"https://openalex.org/W4410104757","doi":"https://doi.org/10.1007/s40747-025-01893-x"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-01893-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01893-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01893-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01893-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100561287","display_name":"Jianwei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianwei Zhu","raw_affiliation_strings":["College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388502","display_name":"Xueying Sun","orcid":"https://orcid.org/0000-0001-6485-9939"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Sun","raw_affiliation_strings":["College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088635841","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0002-7809-5818"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Jiangsu University of Science and Technology, No.666 Changhui Road, Zhenjiang, 212100, Jiangsu, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017613188","display_name":"Mingmin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingmin Liu","raw_affiliation_strings":["Central Research Institute, SIASUN Robot & Automation Co., Ltd., No. 16 Jinhui Street, Shenyang, 110168, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Central Research Institute, SIASUN Robot & Automation Co., Ltd., No. 16 Jinhui Street, Shenyang, 110168, Liaoning, China","institution_ids":["https://openalex.org/I142078773"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100561287"],"corresponding_institution_ids":["https://openalex.org/I4210096899"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":3.3489,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91742494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"11","issue":"6","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9914000034332275,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9534000158309937,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/grasp","display_name":"GRASP","score":0.7723292112350464},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.7179529070854187},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7036995887756348},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6589524149894714},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6364850997924805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5383554100990295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4977720081806183},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3972451686859131},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3915497660636902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33942529559135437},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.33226829767227173},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3126378059387207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26142555475234985},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11973187327384949},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09113383293151855}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7723292112350464},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7179529070854187},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7036995887756348},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6589524149894714},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6364850997924805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5383554100990295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977720081806183},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3972451686859131},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3915497660636902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33942529559135437},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33226829767227173},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3126378059387207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26142555475234985},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11973187327384949},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09113383293151855},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-01893-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01893-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01893-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6319680c4fc648309d1fee67f5b3c94c","is_oa":true,"landing_page_url":"https://doaj.org/article/6319680c4fc648309d1fee67f5b3c94c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 6, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-01893-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01893-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01893-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6987270915","display_name":null,"funder_award_id":"61903162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410104757.pdf","grobid_xml":"https://content.openalex.org/works/W4410104757.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2772168088","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2970710335","https://openalex.org/W2997150500","https://openalex.org/W3008770127","https://openalex.org/W3090727630","https://openalex.org/W3105769864","https://openalex.org/W3158216286","https://openalex.org/W4226399820","https://openalex.org/W4283359318","https://openalex.org/W4292779060","https://openalex.org/W4295224299","https://openalex.org/W4312818263","https://openalex.org/W4313003756","https://openalex.org/W4318620838","https://openalex.org/W4362655350","https://openalex.org/W4367834905","https://openalex.org/W4383101221","https://openalex.org/W4383108836","https://openalex.org/W4386076097","https://openalex.org/W4386436509","https://openalex.org/W4386790226","https://openalex.org/W4386874741","https://openalex.org/W4387092545","https://openalex.org/W4387559800","https://openalex.org/W4387790173","https://openalex.org/W4389666125","https://openalex.org/W4389666604","https://openalex.org/W4391800422","https://openalex.org/W4392817107","https://openalex.org/W4394906292","https://openalex.org/W4401397468","https://openalex.org/W4402727766","https://openalex.org/W4403562331","https://openalex.org/W4403564299","https://openalex.org/W4405785307"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2515493494"],"abstract_inverted_index":{"Task-oriented":[0],"grasping":[1,10,56,99,107],"(TOG)":[2],"aims":[3],"to":[4,26,29,37,78,122,136],"predict":[5],"the":[6,35,80,87,91,153],"appropriate":[7],"pose":[8],"for":[9,66,152],"based":[11],"on":[12,114],"a":[13,52,97,115,133,147],"specific":[14],"task.":[15,155],"While":[16],"recent":[17],"approaches":[18],"have":[19],"incorporated":[20],"semantic":[21],"knowledge":[22],"into":[23],"TOG":[24,154],"models":[25],"enable":[27],"robots":[28],"understand":[30],"linguistic":[31],"commands,":[32],"they":[33],"lack":[34],"ability":[36,89],"leverage":[38],"relevant":[39],"information":[40],"from":[41],"vision,":[42],"language,":[43],"and":[44,69,73,119,149],"action.":[45],"To":[46],"address":[47],"this":[48],"problem,":[49],"we":[50,95,127],"propose":[51],"novel":[53],"multimodal":[54,71],"fusion":[55],"framework":[57],"called":[58],"VLA-Grasp.":[59],"VLA-Grasp":[60],"utilizes":[61],"prompted":[62],"large":[63],"language":[64],"model":[65,131],"task":[67],"inference,":[68],"multi-channel":[70],"encoders":[72],"cross-attention":[74],"modules":[75],"are":[76],"proposed":[77],"capture":[79],"intrinsic":[81],"links":[82],"between":[83],"vision-language-action,":[84],"thus":[85],"improving":[86],"generalization":[88],"of":[90],"model.":[92],"In":[93,125],"addition,":[94,126],"introduce":[96],"multiple":[98,105],"decision":[100],"method":[101,145],"that":[102,143],"can":[103],"provide":[104],"feasible":[106],"actions.":[108],"We":[109],"experimentally":[110,128],"evaluate":[111,137],"our":[112,130,144],"approach":[113],"publicly":[116],"available":[117,159],"dataset":[118],"compare":[120],"it":[121],"state-of-the-art":[123],"methods.":[124],"validate":[129],"in":[132],"real-world":[134],"scenario":[135],"its":[138],"performance.":[139],"The":[140,156],"results":[141],"show":[142],"provides":[146],"reliable":[148],"efficient":[150],"solution":[151],"code":[157],"is":[158],"at":[160],"https://github.com/Jianwei915/VLA-Grasp":[161],".":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}