{"id":"https://openalex.org/W4414763559","doi":"https://doi.org/10.1109/iccv51701.2025.00721","title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","display_name":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414763559","doi":"https://doi.org/10.1109/iccv51701.2025.00721"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.19757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109541494","display_name":"Zhi Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Hou","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102920485","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0009-0006-8963-4561"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105932883","display_name":"Yuwen Xiong","orcid":"https://orcid.org/0009-0007-7780-3986"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwen Xiong","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030831087","display_name":"Haonan Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Duan","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114534503","display_name":"Hengjun Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengjun Pu","raw_affiliation_strings":["The Chinese University of Hong Kong,MMLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,MMLab","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049807367","display_name":"Rui\u2010jie Tong","orcid":"https://orcid.org/0000-0002-3780-8308"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronglei Tong","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454935","display_name":"Chunjian Zhao","orcid":"https://orcid.org/0000-0003-2827-1999"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyang Zhao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xizhou Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizhou Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620176","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-2191-3875"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026944066","display_name":"Jifeng Dai","orcid":"https://orcid.org/0000-0002-6785-0785"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Dai","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087248329","display_name":"Yuntao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I186995768","display_name":"Universit\u00e0 degli studi di Cassino e del Lazio Meridionale","ror":"https://ror.org/04nxkaq16","country_code":"IT","type":"education","lineage":["https://openalex.org/I186995768"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yuntao Chen","raw_affiliation_strings":["HKISI,CAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKISI,CAS","institution_ids":["https://openalex.org/I186995768"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"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":"7686","last_page":"7697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12227","display_name":"Environmental and Social Impact Assessments","score":0.09610000252723694,"subfield":{"id":"https://openalex.org/subfields/2308","display_name":"Management, Monitoring, Policy and Law"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12227","display_name":"Environmental and Social Impact Assessments","score":0.09610000252723694,"subfield":{"id":"https://openalex.org/subfields/2308","display_name":"Management, Monitoring, Policy and Law"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6837999820709229},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5906999707221985},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5153999924659729},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.47769999504089355},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4302999973297119},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4228000044822693},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6837999820709229},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.28850001096725464}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.19757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19757","pdf_url":"https://arxiv.org/pdf/2503.19757","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.19757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19757","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.19757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19757","pdf_url":"https://arxiv.org/pdf/2503.19757","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1],"vision-language-action":[2],"models":[3,91],"trained":[4],"on":[5,19,64],"diverse":[6,113],"robot":[7,180],"datasets":[8,111],"exhibit":[9],"promising":[10],"generalization":[11],"capabilities":[12],"with":[13],"limited":[14],"in-domain":[15],"data,":[16],"their":[17],"reliance":[18],"compact":[20],"action":[21,33,49,92,101,120],"heads":[22],"to":[23,31,45,154],"predict":[24],"discretized":[25],"or":[26,143],"continuous":[27,48],"actions":[28,80],"constrains":[29],"adaptability":[30],"heterogeneous":[32],"spaces.":[34,121],"We":[35],"present":[36],"Dita,":[37],"a":[38,52,172],"scalable":[39],"framework":[40],"that":[41,61],"leverages":[42],"Transformer":[43],"architectures":[44],"directly":[46],"denoise":[47],"sequences":[50],"through":[51,161],"unified":[53],"multimodal":[54],"diffusion":[55,100],"process.":[56],"Departing":[57],"from":[58,85],"prior":[59],"methods":[60],"condition":[62],"denoising":[63],"fused":[65],"embeddings":[66],"via":[67],"shallow":[68],"networks,":[69],"Dita":[70,107,149],"employs":[71],"in-context":[72],"conditioning":[73],"--":[74],"enabling":[75],"fine-grained":[76],"alignment":[77],"between":[78],"denoised":[79],"and":[81,94,119,129,157,175],"raw":[82],"visual":[83],"tokens":[84],"historical":[86],"observations.":[87],"This":[88],"design":[89],"explicitly":[90],"deltas":[93],"environmental":[95,155],"nuances.":[96],"By":[97],"scaling":[98],"the":[99,104,131],"denoiser":[102],"alongside":[103],"Transformer's":[105],"scalability,":[106],"effectively":[108],"integrates":[109],"cross-embodiment":[110],"across":[112,138],"camera":[114,167],"perspectives,":[115],"observation":[116],"scenes,":[117],"tasks,":[118],"Such":[122],"synergy":[123],"enhances":[124],"robustness":[125],"against":[126],"various":[127],"variances":[128,156],"facilitates":[130],"successful":[132],"execution":[133],"of":[134],"long-horizon":[135,159],"tasks.":[136],"Evaluations":[137],"extensive":[139],"benchmarks":[140],"demonstrate":[141],"state-of-the-art":[142],"comparative":[144],"performance":[145],"in":[146],"simulation.":[147],"Notably,":[148],"achieves":[150],"robust":[151],"real-world":[152],"adaptation":[153],"complex":[158],"tasks":[160],"10-shot":[162],"finetuning,":[163],"using":[164],"only":[165],"third-person":[166],"inputs.":[168],"The":[169],"architecture":[170],"establishes":[171],"versatile,":[173],"lightweight":[174],"open-source":[176],"baseline":[177],"for":[178],"generalist":[179],"policy":[181],"learning.":[182],"Project":[183],"Page:":[184],"https://robodita.github.io.":[185]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
