{"id":"https://openalex.org/W4416551879","doi":"https://doi.org/10.1109/iccv51701.2025.01306","title":"On-Device Diffusion Transformer Policy for Efficient Robot Manipulation","display_name":"On-Device Diffusion Transformer Policy for Efficient Robot Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416551879","doi":"https://doi.org/10.1109/iccv51701.2025.01306"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01306","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00697","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101719195","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0002-3764-0322"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332013","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0002-6480-9568"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Wang","raw_affiliation_strings":["School of Engineering, Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064120901","display_name":"Zhenghao Chen","orcid":"https://orcid.org/0000-0003-0155-4462"},"institutions":[{"id":"https://openalex.org/I4210113003","display_name":"Physical Sciences (United States)","ror":"https://ror.org/021qvjc46","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113003"]},{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Zhenghao Chen","raw_affiliation_strings":["School of Information and Physical Sciences, The University of Newcastle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Physical Sciences, The University of Newcastle","institution_ids":["https://openalex.org/I78757542","https://openalex.org/I4210113003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072158745","display_name":"Jianxin Pang","orcid":"https://orcid.org/0000-0002-0053-2723"},"institutions":[{"id":"https://openalex.org/I4210135242","display_name":"Omnitech Robotics (United States)","ror":"https://ror.org/03dhfj813","country_code":"US","type":"company","lineage":["https://openalex.org/I4210135242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianxin Pang","raw_affiliation_strings":["UBTech Robotics Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTech Robotics Corp","institution_ids":["https://openalex.org/I4210135242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341924","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0001-9469-0150"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18489935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14073","last_page":"14083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6804999709129333,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6804999709129333,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.0851999968290329,"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":0.02810000069439411,"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/bottleneck","display_name":"Bottleneck","score":0.6432999968528748},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4650000035762787},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4140999913215637},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4081999957561493},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.39010000228881836},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.37290000915527344},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.34709998965263367},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.33719998598098755},{"id":"https://openalex.org/keywords/computational-resource","display_name":"Computational resource","score":0.3255999982357025}],"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/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01306","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:2508.00697","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00697","pdf_url":"https://arxiv.org/pdf/2508.00697","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.2508.00697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00697","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:2508.00697","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00697","pdf_url":"https://arxiv.org/pdf/2508.00697","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":[{"id":"https://openalex.org/G7400432085","display_name":null,"funder_award_id":"62202431","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0,41,80,187],"Policies":[1,42],"have":[2],"significantly":[3],"advanced":[4],"robotic":[5],"manipulation":[6],"tasks":[7],"via":[8],"imitation":[9],"learning,":[10],"but":[11],"their":[12],"application":[13],"on":[14,46,78,137,154],"resource-constrained":[15],"mobile":[16,47,155],"platforms":[17],"remains":[18],"challenging":[19],"due":[20],"to":[21,39,91,125,185],"computational":[22,52,76],"inefficiency":[23],"and":[24,64,108,145],"extensive":[25,75],"memory":[26],"footprint.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,103,118],"propose":[32],"LightDP,":[33],"a":[34,105],"novel":[35],"framework":[36],"specifically":[37],"designed":[38],"accelerate":[40],"for":[43],"real-time":[44,151],"deployment":[45,166],"devices.":[48],"LightDP":[49,149,180],"addresses":[50],"the":[51,61,67,84,88,112,138,178],"bottleneck":[53],"through":[54],"two":[55],"core":[56],"strategies:":[57],"network":[58,86],"compression":[59],"of":[60,66,167],"denoising":[62,85],"modules":[63],"reduction":[65],"required":[68],"sampling":[69,128],"steps.":[70],"We":[71],"first":[72],"conduct":[73],"an":[74,161],"analysis":[77],"existing":[79],"Policy":[81],"architectures,":[82],"identifying":[83],"as":[87],"primary":[89],"contributor":[90],"latency.":[92],"To":[93],"overcome":[94],"performance":[95,183],"degradation":[96],"typically":[97],"associated":[98],"with":[99,122,157],"conventional":[100],"pruning":[101,107,120],"methods,":[102],"introduce":[104],"unified":[106],"retraining":[109],"pipeline,":[110],"optimizing":[111],"model's":[113],"post-pruning":[114],"recoverability":[115],"explicitly.":[116],"Furthermore,":[117],"combine":[119],"techniques":[121],"consistency":[123],"distillation":[124],"effectively":[126],"reduce":[127],"steps":[129],"while":[130],"maintaining":[131],"action":[132,152],"prediction":[133,153],"accuracy.":[134],"Experimental":[135],"evaluations":[136],"standard":[139],"datasets,":[140],"\\ie,":[141],"PushT,":[142],"Robomimic,":[143],"CALVIN,":[144],"LIBERO,":[146],"demonstrate":[147],"that":[148],"achieves":[150],"devices":[156],"competitive":[158],"performance,":[159],"marking":[160],"important":[162],"step":[163],"toward":[164],"practical":[165],"diffusion-based":[168],"policies":[169],"in":[170],"resource-limited":[171],"environments.":[172],"Extensive":[173],"real-world":[174],"experiments":[175],"also":[176],"show":[177],"proposed":[179],"can":[181],"achieve":[182],"comparable":[184],"state-of-the-art":[186],"Policies.":[188]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}