{"id":"https://openalex.org/W7123340428","doi":"https://doi.org/10.1109/lra.2026.3653303","title":"PointVLA: Injecting the 3D World Into Vision-Language-Action Models","display_name":"PointVLA: Injecting the 3D World Into Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123340428","doi":"https://doi.org/10.1109/lra.2026.3653303"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3653303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3653303","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chengmeng Li","orcid":"https://orcid.org/0009-0000-3549-1055"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengmeng Li","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-3549-1055","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Wen","orcid":"https://orcid.org/0009-0004-1660-3268"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wen","raw_affiliation_strings":["Midea Group, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0004-1660-3268","affiliations":[{"raw_affiliation_string":"Midea Group, Guangdong, China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122845295","display_name":"Yaxin Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Peng","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2983-555X","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan Peng","orcid":"https://orcid.org/0000-0003-1312-9527"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Peng","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1312-9527","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122859335","display_name":"Yichen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Zhu","raw_affiliation_strings":["Midea Group, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5126-838X","affiliations":[{"raw_affiliation_string":"Midea Group, Guangdong, China","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":40.4346,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.99746122,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"11","issue":"3","first_page":"2506","last_page":"2513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.659600019454956,"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":0.659600019454956,"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":0.09749999642372131,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05009999871253967,"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/point-cloud","display_name":"Point cloud","score":0.7379999756813049},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6137999892234802},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5651000142097473},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.527999997138977},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49149999022483826},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.46129998564720154},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.45210000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576000094413757},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7379999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212999820709229},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3653303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3653303","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5250615477561951},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4734854996204376}],"awards":[{"id":"https://openalex.org/G3852915482","display_name":null,"funder_award_id":"62225308","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3930171800","display_name":null,"funder_award_id":"12471501","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3212960520","https://openalex.org/W4285218426","https://openalex.org/W4401415042","https://openalex.org/W4402353985","https://openalex.org/W4402354045","https://openalex.org/W4402354047","https://openalex.org/W4402713111","https://openalex.org/W4403337227","https://openalex.org/W4404783087","https://openalex.org/W4407874080","https://openalex.org/W4409365821","https://openalex.org/W4413144615","https://openalex.org/W4413917998","https://openalex.org/W4413926128","https://openalex.org/W4413944794","https://openalex.org/W4414050589","https://openalex.org/W4414051092","https://openalex.org/W4414079054","https://openalex.org/W4416748905","https://openalex.org/W4416749759"],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,28],"excel":[3],"at":[4,204],"robotic":[5,141],"tasks":[6,163],"by":[7,152],"leveraging":[8,179],"large-scale":[9],"2D":[10,38,125,193],"vision-language":[11],"pretraining,":[12],"but":[13],"their":[14,177],"reliance":[15],"on":[16],"RGB":[17],"images":[18],"limits":[19],"spatial":[20],"reasoning":[21],"critical":[22],"for":[23],"real-world":[24,140],"interaction.":[25],"Retraining":[26],"these":[27,112],"with":[29,56],"3D":[30,72,106,180],"data":[31],"is":[32],"computationally":[33],"prohibitive,":[34],"while":[35],"discarding":[36],"existing":[37],"datasets":[39],"wastes":[40],"valuable":[41],"resources.":[42],"To":[43,78],"bridge":[44],"this":[45],"gap,":[46],"we":[47,89,144],"propose":[48],"PointVLA,":[49],"a":[50,91,229],"framework":[51],"that":[52,105,121,208],"enhances":[53],"pre-trained":[54,116],"VLAs":[55],"point":[57,86,153],"cloud":[58,87,154],"inputs":[59],"without":[60],"requiring":[61],"retraining.":[62],"Our":[63],"method":[64],"freezes":[65],"the":[66,80,100],"vanilla":[67,101],"action":[68,102],"expert":[69],"and":[70,134,139,186,225],"injects":[71],"features":[73,107],"via":[74],"alightweight":[75],"modular":[76],"block.":[77],"identify":[79],"most":[81],"effective":[82],"way":[83],"of":[84,149],"integrating":[85],"representations,":[88],"conduct":[90],"skip-block":[92],"analysis":[93],"to":[94,115,183,200,202,236],"pinpoint":[95],"less":[96],"useful":[97],"blocks":[98],"in":[99,211,219],"expert,":[103],"ensuring":[104],"are":[108],"injected":[109],"only":[110,165],"into":[111],"blocks\u2014minimizing":[113],"disruption":[114],"representations.":[117],"Extensive":[118],"experiments":[119],"demonstrate":[120],"PointVLA":[122,150,158,172,197,215],"outperforms":[123],"state-of-the-art":[124],"imitation":[126,194],"learning":[127,195],"methods,":[128,196],"such":[129,222],"as":[130,223],"OpenVLA,":[131],"Diffusion":[132],"Policy":[133],"DexVLA,":[135],"across":[136,238],"both":[137],"simulated":[138],"tasks.":[142],"Specifically,":[143],"highlight":[145],"several":[146],"key":[147],"advantages":[148],"enabled":[151],"integration:":[155],"(1)Few-shotmulti-tasking,":[156],"where":[157,171,190],"successfully":[159],"performs":[160],"four":[161],"different":[162],"using":[164],"20":[166],"demonstrations":[167],"each;":[168],"(2)Real-vs-photo":[169],"discrimination,":[170],"distinguishes":[173],"real":[174],"objects":[175,203,227],"from":[176,228],"images,":[178],"world":[181],"knowledge":[182],"improve":[184],"safety":[185],"reliability;":[187],"(3)Height":[188],"adaptability,":[189],"unlike":[191],"conventional":[192],"enables":[198],"robots":[199],"adapt":[201],"varying":[205],"table":[206],"heights":[207],"were":[209],"unseen":[210],"training":[212],"data.":[213],"Furthermore,":[214],"achieves":[216],"strong":[217],"performance":[218],"long-horizon":[220],"tasks,":[221],"picking":[224],"packing":[226],"moving":[230],"conveyor":[231],"belt,":[232],"showcasing":[233],"its":[234],"ability":[235],"generalize":[237],"complex,":[239],"dynamic":[240],"environments.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-01-14T00:00:00"}