{"id":"https://openalex.org/W4414754983","doi":"https://doi.org/10.1109/iccv51701.2025.01067","title":"Diffusion-Based Imaginative Coordination for Bimanual Manipulation","display_name":"Diffusion-Based Imaginative Coordination for Bimanual Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414754983","doi":"https://doi.org/10.1109/iccv51701.2025.01067"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01067","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/2507.11296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120311985","display_name":"Huilin Xu","orcid":"https://orcid.org/0000-0003-1307-4896"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilin Xu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009464910","display_name":"Jian Ding","orcid":"https://orcid.org/0000-0002-5823-1069"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Jian Ding","raw_affiliation_strings":["King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058215007","display_name":"Jin-hong XU","orcid":"https://orcid.org/0000-0002-6909-2738"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jiakun Xu","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968566","display_name":"Ruixiang Wang","orcid":"https://orcid.org/0009-0007-6022-761X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiang Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730479","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-6568-8801"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015794955","display_name":"Jinjie Mai","orcid":"https://orcid.org/0000-0002-3396-1970"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Jinjie Mai","raw_affiliation_strings":["King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024763828","display_name":"Bernard Ghanem","orcid":"https://orcid.org/0000-0002-5534-587X"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Bernard Ghanem","raw_affiliation_strings":["King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017904348","display_name":"Feng Xu","orcid":"https://orcid.org/0000-0003-2145-651X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Xu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["King Abdullah University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"11469","last_page":"11479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.7634000182151794,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.7634000182151794,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6104999780654907},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5810999870300293},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4546000063419342},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4074999988079071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39809998869895935},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337000131607056},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6104999780654907},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406999945640564},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3910999894142151},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01067","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:2507.11296","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11296","pdf_url":"https://arxiv.org/pdf/2507.11296","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.2507.11296","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.11296","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:2507.11296","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11296","pdf_url":"https://arxiv.org/pdf/2507.11296","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":[{"id":"https://openalex.org/F4320334860","display_name":"Global Collaborative Research, King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bimanual":[0],"manipulation":[1],"is":[2,109],"crucial":[3],"in":[4,9,91,148,175],"robotics,":[5],"enabling":[6],"complex":[7],"tasks":[8],"industrial":[10],"automation":[11],"and":[12,26,40,49,76,140,171,180],"household":[13],"services.":[14],"However,":[15],"it":[16],"poses":[17],"significant":[18,146],"challenges":[19],"due":[20],"to":[21,45,126],"the":[22,71,112,149,153],"high-dimensional":[23],"action":[24,77,115],"space":[25],"intricate":[27],"coordination":[28,57],"requirements.":[29],"While":[30],"video":[31,75,107,120,128],"prediction":[32,85,108,116,129],"has":[33],"been":[34],"recently":[35],"studied":[36],"for":[37,54,70],"representation":[38],"learning":[39],"control,":[41],"leveraging":[42],"its":[43,52],"ability":[44],"capture":[46],"rich":[47],"dynamic":[48],"behavioral":[50],"information,":[51],"potential":[53],"enhancing":[55,133],"bimanual":[56],"remains":[58,117],"underexplored.":[59],"To":[60],"bridge":[61],"this":[62],"gap,":[63],"we":[64,80,100],"propose":[65,81],"a":[66,82,92,102,141,145,161,172],"unified":[67],"diffusion-based":[68],"framework":[69],"joint":[72],"optimization":[73],"of":[74,119],"prediction.":[78,121],"Specifically,":[79],"multi-frame":[83],"latent":[84,94],"strategy":[86],"that":[87],"encodes":[88],"future":[89],"states":[90],"compressed":[93],"space,":[95],"preserving":[96],"task-relevant":[97],"features.":[98],"Furthermore,":[99],"introduce":[101],"unidirectional":[103],"attention":[104],"mechanism":[105],"where":[106],"conditioned":[110],"on":[111,136,164,169],"action,":[113],"while":[114],"independent":[118],"This":[122],"design":[123],"allows":[124],"us":[125],"omit":[127],"during":[130],"inference,":[131],"significantly":[132],"efficiency.":[134],"Experiments":[135],"two":[137],"simulated":[138],"benchmarks":[139],"real-world":[142,176],"setting":[143],"demonstrate":[144],"improvement":[147],"success":[150],"rate":[151],"over":[152],"strong":[154],"baseline":[155],"ACT":[156],"using":[157],"our":[158],"method,":[159],"achieving":[160],"\\textbf{24.9\\%}":[162],"increase":[163,168,174],"ALOHA,":[165],"an":[166],"\\textbf{11.1\\%}":[167],"RoboTwin,":[170],"\\textbf{32.5\\%}":[173],"experiments.":[177],"Our":[178],"models":[179],"code":[181],"are":[182],"publicly":[183],"available":[184],"at":[185],"https://github.com/return-sleep/Diffusion_based_imaginative_Coordination.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
