{"id":"https://openalex.org/W4417297116","doi":"https://doi.org/10.1109/lra.2026.3710031","title":"ImplicitRDP: An End-to-End Visual-Force Diffusion Policy With Structural Slow-Fast Learning","display_name":"ImplicitRDP: An End-to-End Visual-Force Diffusion Policy With Structural Slow-Fast Learning","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W4417297116","doi":"https://doi.org/10.1109/lra.2026.3710031"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3710031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3710031","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.10946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060498865","display_name":"Wendi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-2128-4438","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103170398","display_name":"Xue Han","orcid":"https://orcid.org/0000-0002-7849-0228"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xue","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0847-1750","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710570","display_name":"Yibin Wang","orcid":"https://orcid.org/0000-0003-0852-0767"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-7085-9771","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fangyuan Zhou","orcid":"https://orcid.org/0009-0006-0747-7671"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-0747-7671","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081067243","display_name":"Jun Lv","orcid":"https://orcid.org/0000-0001-9438-7581"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lv","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4328-0420","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019869909","display_name":"Yang Jin","orcid":"https://orcid.org/0009-0000-7353-9849"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Jin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-3254-0400","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shirun Tang","orcid":"https://orcid.org/0009-0004-4506-8321"},"institutions":[{"id":"https://openalex.org/I1310269161","display_name":"Citrix (Switzerland)","ror":"https://ror.org/02kf1yd19","country_code":"CH","type":"company","lineage":["https://openalex.org/I1310269161","https://openalex.org/I4210149897"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shirun Tang","raw_affiliation_strings":["Noematrix Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-4506-8321","affiliations":[{"raw_affiliation_string":"Noematrix Ltd., Shanghai, China","institution_ids":["https://openalex.org/I1310269161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061022665","display_name":"Chuan Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Wen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-6699-0739","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101470275","display_name":"Cewu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cewu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1533-8576","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0186325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"8","first_page":"10010","last_page":"10017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7448999881744385,"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":0.7448999881744385,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0640999972820282,"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/T10982","display_name":"Motor Control and Adaptation","score":0.03009999915957451,"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":0.5963000059127808},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5493999719619751},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/haptic-technology","display_name":"Haptic technology","score":0.5185999870300293},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4864000082015991},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.38999998569488525},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.37959998846054077},{"id":"https://openalex.org/keywords/contact-force","display_name":"Contact force","score":0.37389999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786999702453613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5963000059127808},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C81302111","wikidata":"https://www.wikidata.org/wiki/Q2916417","display_name":"Contact force","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C199723944","wikidata":"https://www.wikidata.org/wiki/Q3041998","display_name":"Force dynamics","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2026.3710031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3710031","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2512.10946","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.10946","pdf_url":"https://arxiv.org/pdf/2512.10946","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.2512.10946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10946","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:2512.10946","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.10946","pdf_url":"https://arxiv.org/pdf/2512.10946","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/F7351031327","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417297116.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human-level":[0],"contact-rich":[1,151],"manipulation":[2],"relies":[3],"on":[4,150],"the":[5,85,93,98,115,132,136],"distinct":[6],"roles":[7],"of":[8,101],"two":[9],"key":[10],"modalities:":[11],"vision":[12],"provides":[13],"spatially":[14],"rich":[15],"but":[16],"temporally":[17],"slow":[18],"global":[19],"context,":[20],"while":[21,96],"force":[22,60,82,90,129,146],"sensing":[23],"captures":[24],"rapid":[25,89],"local":[26],"contact":[27],"dynamics.":[28],"Integrating":[29],"these":[30],"signals":[31],"is":[32],"challenging":[33],"due":[34],"to":[35,76,87,105,113],"their":[36],"fundamental":[37],"frequency":[38],"and":[39,58,81,160,166,175],"informational":[40],"disparities.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,120],"propose":[46,121],"ImplicitRDP,":[47],"a":[48,63,71,139,170],"unified":[49],"end-to-end":[50,110],"visual-force":[51],"diffusion":[52],"policy":[53,86],"that":[54,154],"integrates":[55],"visual":[56,80],"planning":[57],"reactive":[59],"control":[61,91],"within":[62],"single":[64],"network.":[65],"We":[66],"introduce":[67],"Structural":[68],"Slow-Fast":[69],"Learning,":[70],"mechanism":[72],"utilizing":[73],"causal":[74],"attention":[75],"simultaneously":[77],"process":[78],"asynchronous":[79],"tokens,":[83],"allowing":[84],"perform":[88],"at":[92,179],"action":[94,102],"rate":[95],"maintaining":[97],"temporal":[99],"coherence":[100],"chunks.":[103],"Furthermore,":[104],"mitigate":[106],"modality":[107],"collapse":[108],"where":[109],"models":[111],"fail":[112],"adjust":[114],"weights":[116],"across":[117],"different":[118],"modalities,":[119],"Virtual-target-based":[122],"Representation":[123],"Regularization.":[124],"This":[125],"auxiliary":[126],"objective":[127],"maps":[128],"feedback":[130],"into":[131],"same":[133],"space":[134],"as":[135],"action,":[137],"providing":[138],"stronger,":[140],"physics-grounded":[141],"learning":[142],"signal":[143],"than":[144],"raw":[145],"prediction.":[147],"Extensive":[148],"experiments":[149],"tasks":[152],"demonstrate":[153],"ImplicitRDP":[155],"significantly":[156],"outperforms":[157],"both":[158],"vision-only":[159],"hierarchical":[161],"baselines,":[162],"achieving":[163],"superior":[164],"reactivity":[165],"success":[167],"rates":[168],"with":[169],"streamlined":[171],"training":[172],"pipeline.":[173],"Code":[174],"videos":[176],"are":[177],"available":[178],"https://implicit-rdp.github.io.":[180]},"counts_by_year":[],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-12-13T00:00:00"}