{"id":"https://openalex.org/W4413926128","doi":"https://doi.org/10.1109/icra55743.2025.11128074","title":"Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation","display_name":"Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926128","doi":"https://doi.org/10.1109/icra55743.2025.11128074"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5100848746","display_name":"Minjie Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjie Zhu","raw_affiliation_strings":["School of Computer Science, East China Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054623682","display_name":"Yichen Zhu","orcid":"https://orcid.org/0000-0001-5126-838X"},"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, AI Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group, AI Research Center,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679105","display_name":"Jinming Li","orcid":"https://orcid.org/0000-0003-4910-7362"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Li","raw_affiliation_strings":["School of Future Technology, Shanghai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040021240","display_name":"Junjie Wen","orcid":"https://orcid.org/0000-0002-2230-8933"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wen","raw_affiliation_strings":["School of Computer Science, East China Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102218958","display_name":"Zhiyuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Xu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics,China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597119","display_name":"Ning Liu","orcid":"https://orcid.org/0000-0003-0884-0058"},"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":"Ning Liu","raw_affiliation_strings":["Midea Group, AI Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group, AI Research Center,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004036087","display_name":"Ran Cheng","orcid":"https://orcid.org/0000-0001-9410-8263"},"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":"Ran Cheng","raw_affiliation_strings":["Midea Group, AI Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group, AI Research Center,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008090356","display_name":"Chaomin Shen","orcid":"https://orcid.org/0000-0001-9389-6472"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaomin Shen","raw_affiliation_strings":["School of Computer Science, East China Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033203506","display_name":"Yaxin Peng","orcid":"https://orcid.org/0000-0002-2983-555X"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Peng","raw_affiliation_strings":["School of Future Technology, Shanghai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Technology, Shanghai University,China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041753664","display_name":"Feifei Feng","orcid":"https://orcid.org/0000-0001-5534-5928"},"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":"Feifei Feng","raw_affiliation_strings":["Midea Group, AI Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group, AI Research Center,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067590443","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0003-1324-2466"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics,China","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10838","last_page":"10845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11301","display_name":"Advanced Surface Polishing Techniques","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11301","display_name":"Advanced Surface Polishing Techniques","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11222","display_name":"Magnetic Properties and Applications","score":0.932699978351593,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11661","display_name":"Copper Interconnects and Reliability","score":0.9298999905586243,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.7526403665542603},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5689018964767456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4458518624305725},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4306893050670624},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.26718366146087646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16922414302825928},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14150789380073547},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12400180101394653},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.10440629720687866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07881662249565125}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7526403665542603},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5689018964767456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4458518624305725},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4306893050670624},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.26718366146087646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16922414302825928},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14150789380073547},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12400180101394653},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.10440629720687866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07881662249565125},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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":24,"referenced_works":["https://openalex.org/W2962770929","https://openalex.org/W3172942063","https://openalex.org/W4312933868","https://openalex.org/W4328007461","https://openalex.org/W4380434618","https://openalex.org/W4383109488","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4385430497","https://openalex.org/W4385430674","https://openalex.org/W4390872297","https://openalex.org/W4401414095","https://openalex.org/W4401414111","https://openalex.org/W4401414275","https://openalex.org/W4402354007","https://openalex.org/W4402354045","https://openalex.org/W4402354047","https://openalex.org/W4402354140","https://openalex.org/W4402354155","https://openalex.org/W4402783855","https://openalex.org/W4403021114","https://openalex.org/W4403793633","https://openalex.org/W4403878024","https://openalex.org/W4403878347"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Diffusion":[0,17,44,70,90,116,171],"Policy":[1,18,45,72,91,117,172],"is":[2,14,263],"a":[3,21],"powerful":[4],"technique":[5],"tool":[6],"for":[7,24,73,253,257],"learning":[8],"end-to-end":[9],"visuomotor":[10,74,258],"robot":[11,223],"control.":[12],"It":[13],"expected":[15],"that":[16,30,43,84,105,164,208],"possesses":[19],"scalability,":[20],"key":[22],"attribute":[23],"deep":[25],"neural":[26],"networks,":[27],"typically":[28],"suggesting":[29],"increasing":[31],"model":[32,190],"size":[33,191],"would":[34],"lead":[35],"to":[36,51,96,151,158,176],"enhanced":[37],"performance.":[38],"However,":[39],"our":[40,142,165,209,225,248],"observations":[41],"indicate":[42],"in":[46],"transformer":[47,139],"architecture":[48],"(DP-T)":[49],"struggles":[50],"scale":[52,187],"effectively;":[53],"even":[54],"minor":[55],"additions":[56],"of":[57,89,115,128,218,231],"layers":[58],"can":[59,185],"deteriorate":[60],"training":[61,87],"outcomes.":[62],"To":[63,119],"address":[64],"this":[65,121],"issue,":[66,122],"we":[67,103,123],"introduce":[68],"Scalable":[69],"Transformer":[71],"learning.":[75,259],"Our":[76],"proposed":[77,166],"method,":[78],"namely":[79],"ScaleDP,":[80,184],"introduces":[81],"two":[82],"modules":[83],"improve":[85],"the":[86,94,113,125,138,148,170,189,251],"dynamic":[88],"and":[92,134,195,206,240],"allow":[93],"network":[95,150],"better":[97],"handle":[98],"multimodal":[99],"action":[100],"distribution.":[101],"First,":[102],"identify":[104],"DPT":[106],"suffers":[107],"from":[108,173,204],"large":[109],"gradient":[110],"issues,":[111],"making":[112],"optimization":[114],"unstable.":[118],"resolve":[120],"factorize":[124],"feature":[126],"embedding":[127],"observation":[129],"into":[130,137],"multiple":[131],"affine":[132],"layers,":[133],"integrate":[135],"it":[136],"blocks.":[140],"Additionally,":[141],"utilize":[143],"non-causal":[144],"attention":[145],"which":[146],"allows":[147],"policy":[149],"\u201csee\u201d":[152],"future":[153],"actions":[154],"during":[155],"prediction,":[156],"helping":[157],"reduce":[159],"compounding":[160],"errors.":[161],"We":[162,197,246],"demonstrate":[163],"method":[167],"successfully":[168],"scales":[169],"10":[174],"million":[175],"1":[177],"billion":[178],"parameters.":[179],"This":[180],"new":[181],"model,":[182],"named":[183],"effectively":[186],"up":[188,255],"with":[192,214],"improved":[193],"performance":[194],"generalization.":[196],"benchmark":[198],"ScaleDP":[199,211,226],"across":[200],"50":[201],"different":[202],"tasks":[203,239],"MetaWorld":[205],"find":[207],"largest":[210],"outperforms":[212],"DP-T":[213,235],"an":[215,228],"average":[216,229],"improvement":[217,230],"21.6%.":[219],"Across":[220],"7":[221],"real-world":[222],"tasks,":[224],"demonstrates":[227],"36.":[232],"25%":[233],"over":[234],"on":[236,242],"four":[237],"single-arm":[238],"75%":[241],"three":[243],"bimanual":[244],"tasks.":[245],"believe":[247],"work":[249],"paves":[250],"way":[252],"scaling":[254],"models":[256],"The":[260],"project":[261],"page":[262],"available":[264],"at":[265],"https://scaling-diffusion-policy.github.io/.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}