{"id":"https://openalex.org/W4392886475","doi":"https://doi.org/10.48550/arxiv.2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","display_name":"3D-VLA: A 3D Vision-Language-Action Generative World Model","publication_year":2024,"publication_date":"2024-03-14","ids":{"openalex":"https://openalex.org/W4392886475","doi":"https://doi.org/10.48550/arxiv.2403.09631"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.09631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09631","pdf_url":"https://arxiv.org/pdf/2403.09631","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":null,"license_id":null,"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/2403.09631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109625651","display_name":"Haoyu Zhen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen, Haoyu","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiu, Xiaowen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xiaowen","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004837552","display_name":"Peihao Chen","orcid":"https://orcid.org/0000-0002-6847-1621","observed_orcids":["https://orcid.org/0000-0002-6847-1621","https://orcid.org/0009-0001-1683-3870","https://orcid.org/0009-0001-9061-5206"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Peihao","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085178091","display_name":"Jincheng Yang","orcid":"https://orcid.org/0000-0001-7755-8019","observed_orcids":["https://orcid.org/0000-0001-7755-8019"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jincheng","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan, Xin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xin","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041777043","display_name":"Yilun Du","orcid":"https://orcid.org/0000-0001-6792-5946","observed_orcids":["https://orcid.org/0000-0001-6792-5946"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yilun","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000069468","display_name":"Yining Hong","orcid":"https://orcid.org/0000-0002-0518-2099","observed_orcids":["https://orcid.org/0000-0002-0518-2099"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Yining","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886","observed_orcids":["https://orcid.org/0000-0003-4031-5886"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Chuang","raw_affiliation_strings":["https:// vis - www"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"https:// vis - www","institution_ids":[]}]}],"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":277,"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":0.7250999808311462,"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":0.7250999808311462,"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":0.25119999051094055,"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":0.008799999952316284,"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":0.9810000061988831},{"id":"https://openalex.org/keywords/action-prediction","display_name":"action prediction","score":0.5149999856948853},{"id":"https://openalex.org/keywords/point-cloud-generation","display_name":"point cloud generation","score":0.652999997138977},{"id":"https://openalex.org/keywords/robot-planning","display_name":"robot planning","score":0.3959999978542328},{"id":"https://openalex.org/keywords/multimodal-generation","display_name":"multimodal generation","score":0.7310000061988831}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7375234961509705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6321475505828857},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46763041615486145},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4204745590686798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3877311050891876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3219592571258545},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.15106156468391418},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10641655325889587},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.09631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09631","pdf_url":"https://arxiv.org/pdf/2403.09631","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.09631","doi":"https://doi.org/10.48550/arxiv.2403.09631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.09631","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.09631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09631","pdf_url":"https://arxiv.org/pdf/2403.09631","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392886475.pdf","grobid_xml":"https://content.openalex.org/works/W4392886475.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W3168867926","https://openalex.org/W3178987284","https://openalex.org/W4246233237","https://openalex.org/W4312045746","https://openalex.org/W4318718936","https://openalex.org/W4322616103","https://openalex.org/W4323572061","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4382490555","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4386655647","https://openalex.org/W4386942465","https://openalex.org/W4387764390","https://openalex.org/W4387947644","https://openalex.org/W4388482284","https://openalex.org/W4388964408","https://openalex.org/W4389116645","https://openalex.org/W4401415042","https://openalex.org/W4401415888","https://openalex.org/W4402778507","https://openalex.org/W7133185515","https://openalex.org/W7133246057"],"related_works":["https://openalex.org/W7163539710","https://openalex.org/W7167675971","https://openalex.org/W7201861962","https://openalex.org/W7102060555","https://openalex.org/W7213373602","https://openalex.org/W4417094684","https://openalex.org/W6891886405","https://openalex.org/W6910626880","https://openalex.org/W7133222765","https://openalex.org/W4415269881"],"abstract_inverted_index":{"Recent":[0],"vision-language-action":[1],"(VLA)":[2],"models":[3,55,80,136],"rely":[4],"on":[5,98,174],"2D":[6],"inputs,":[7],"lacking":[8],"integration":[9],"with":[10,53,117],"the":[11,15,34,38,41,118,127,141,145,182],"broader":[12],"realm":[13],"of":[14,37,77,100,110,133],"3D":[16,84,159],"physical":[17],"world.":[18],"Furthermore,":[19,121],"they":[20],"perform":[21],"action":[22,88],"prediction":[23],"by":[24,72,163],"learning":[25],"a":[26,74,90,101,108,131,157],"direct":[27],"mapping":[28],"from":[29,168],"perception":[30],"to":[31,62,115,122],"action,":[32],"neglecting":[33],"vast":[35,165],"dynamics":[36],"world":[39,54,92],"and":[40,45,87,107,137,148,186],"relations":[42],"between":[43],"actions":[44,64],"dynamics.":[46],"In":[47],"contrast,":[48],"human":[49],"beings":[50],"are":[51],"endowed":[52],"that":[56,81,178],"depict":[57],"imagination":[58],"about":[59],"future":[60],"scenarios":[61],"plan":[63],"accordingly.":[65],"To":[66,151],"this":[67],"end,":[68],"we":[69,129,155],"propose":[70],"3D-VLA":[71,95,179],"introducing":[73],"new":[75],"family":[76],"embodied":[78,119,134,160,190],"foundation":[79],"seamlessly":[82],"link":[83],"perception,":[85],"reasoning,":[86,183],"through":[89],"generative":[91],"model.":[93],"Specifically,":[94],"is":[96,113],"built":[97],"top":[99],"3D-based":[102],"large":[103],"language":[104],"model":[105],"(LLM),":[106],"set":[109],"interaction":[111],"tokens":[112],"introduced":[114],"engage":[116],"environment.":[120],"inject":[123],"generation":[124],"abilities":[125],"into":[126,140],"model,":[128],"train":[130,152],"series":[132],"diffusion":[135],"align":[138],"them":[139],"LLM":[142],"for":[143],"predicting":[144],"goal":[146],"images":[147],"point":[149],"clouds.":[150],"our":[153],"3D-VLA,":[154],"curate":[156],"large-scale":[158],"instruction":[161],"dataset":[162],"extracting":[164],"3D-related":[166],"information":[167],"existing":[169],"robotics":[170],"datasets.":[171],"Our":[172],"experiments":[173],"held-in":[175],"datasets":[176],"demonstrate":[177],"significantly":[180],"improves":[181],"multimodal":[184],"generation,":[185],"planning":[187],"capabilities":[188],"in":[189,195],"environments,":[191],"showcasing":[192],"its":[193],"potential":[194],"real-world":[196],"applications.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":139},{"year":2025,"cited_by_count":121},{"year":2024,"cited_by_count":17}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2024-03-17T00:00:00"}