{"id":"https://openalex.org/W4409262207","doi":"https://doi.org/10.1109/wacv61041.2025.00201","title":"Transferring Foundation Models for Generalizable Robotic Manipulation","display_name":"Transferring Foundation Models for Generalizable Robotic Manipulation","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4409262207","doi":"https://doi.org/10.1109/wacv61041.2025.00201"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61041.2025.00201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","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/A5015582569","display_name":"Jiange Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiange Yang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102648115","display_name":"Wenhui Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Tan","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050979121","display_name":"Chuhao Jin","orcid":"https://orcid.org/0000-0002-3362-5600"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuhao Jin","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102560389","display_name":"Keling Yao","orcid":null},"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":"Keling Yao","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/A5104145177","display_name":"Bei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436544","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0003-3810-5994"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4253,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95646702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1999","last_page":"2010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9934999942779541,"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":0.9934999942779541,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9817000031471252,"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/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6118232607841492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5848223567008972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3641901910305023},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34810173511505127}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6118232607841492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5848223567008972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3641901910305023},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34810173511505127},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61041.2025.00201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1999156278","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2953249127","https://openalex.org/W3138516171","https://openalex.org/W3189699967","https://openalex.org/W3207187156","https://openalex.org/W4224912544","https://openalex.org/W4285218426","https://openalex.org/W4293498911","https://openalex.org/W4312805142","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4383109478","https://openalex.org/W4385245566","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4385431288","https://openalex.org/W4386076256","https://openalex.org/W4387764390","https://openalex.org/W4388660746","https://openalex.org/W4389519620","https://openalex.org/W4389667470","https://openalex.org/W4401417162","https://openalex.org/W4402354026","https://openalex.org/W4403337227","https://openalex.org/W6740802823","https://openalex.org/W6741798502","https://openalex.org/W6757817989","https://openalex.org/W6760439459","https://openalex.org/W6766978945","https://openalex.org/W6774479972","https://openalex.org/W6791353385","https://openalex.org/W6796524941","https://openalex.org/W6801810553","https://openalex.org/W6802366246","https://openalex.org/W6804277579","https://openalex.org/W6809509765","https://openalex.org/W6810080435","https://openalex.org/W6810536332","https://openalex.org/W6838540985","https://openalex.org/W6839928859","https://openalex.org/W6842751340","https://openalex.org/W6843759960","https://openalex.org/W6845226490","https://openalex.org/W6845793730","https://openalex.org/W6846007759","https://openalex.org/W6846512445","https://openalex.org/W6847034507","https://openalex.org/W6847159501","https://openalex.org/W6850300045","https://openalex.org/W6850343319","https://openalex.org/W6850503672","https://openalex.org/W6850787431","https://openalex.org/W6851416138","https://openalex.org/W6851578965","https://openalex.org/W6851724587","https://openalex.org/W6851950068","https://openalex.org/W6852835101","https://openalex.org/W6852884379","https://openalex.org/W6853053110","https://openalex.org/W6853054754","https://openalex.org/W6854091356","https://openalex.org/W6854108904","https://openalex.org/W6854362512","https://openalex.org/W6854738657","https://openalex.org/W6854929498","https://openalex.org/W6855741238","https://openalex.org/W6859297042","https://openalex.org/W6860803839","https://openalex.org/W6862928075","https://openalex.org/W6872965269","https://openalex.org/W6873475144","https://openalex.org/W6874425386","https://openalex.org/W6875489822"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"Improving":[0],"the":[1,80,97,183],"generalization":[2,113],"capabilities":[3],"of":[4,36,129,185],"general-purpose":[5],"robotic":[6,24],"manipulation":[7,76],"in":[8,45,195],"real":[9],"world":[10],"has":[11],"long":[12],"been":[13],"a":[14,59,127,143,164,173,178],"significant":[15],"challenge.":[16],"Existing":[17],"approaches":[18],"often":[19],"rely":[20],"on":[21,149,172],"collecting":[22],"large-scale":[23],"data":[25],"which":[26,83,152],"is":[27],"costly":[28],"and":[29,51,87,105,110,121,156,177,189,201],"time-consuming.":[30],"However,":[31],"due":[32],"to":[33,73,132,159],"insufficient":[34],"diversity":[35],"data,":[37],"they":[38],"typically":[39],"suffer":[40],"from":[41,92],"limiting":[42],"their":[43],"capability":[44],"open-domain":[46],"scenarios":[47],"with":[48,163],"new":[49,116],"objects":[50],"diverse":[52],"environments.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,141],"propose":[58],"novel":[60],"paradigm":[61,188],"that":[62],"effectively":[63,104],"leverages":[64],"language-reasoning":[65],"segmentation":[66],"mask":[67,81],"generated":[68],"by":[69],"internet-scale":[70],"foundation":[71,94,130],"models,":[72,95],"condition":[74],"robot":[75,161,176,181],"tasks.":[77,139],"By":[78],"integrating":[79],"modality,":[82],"incorporates":[84],"semantic,":[85],"geometric,":[86],"temporal":[88],"correlation":[89],"priors":[90],"derived":[91],"vision":[93],"into":[96],"end-to-end":[98],"policy":[99,146],"model,":[100],"our":[101,186,202],"approach":[102],"can":[103,192],"robustly":[106],"perceive":[107],"object":[108,117,157],"pose":[109],"enable":[111],"sample-efficient":[112],"learning,":[114,151],"including":[115],"instances,":[118],"semantic":[119],"categories,":[120],"unseen":[122],"backgrounds.":[123],"We":[124],"first":[125],"introduce":[126],"series":[128],"models":[131],"ground":[133],"natural":[134],"language":[135],"demands":[136],"across":[137],"multiple":[138],"Secondly,":[140],"develop":[142],"two-stream":[144],"2D":[145],"model":[147],"based":[148],"imitation":[150],"processes":[153],"raw":[154],"images":[155],"masks":[158],"predict":[160],"actions":[162],"local-global":[165],"perception":[166],"manner.":[167],"Extensive":[168],"real-world":[169],"experiments":[170],"conducted":[171],"Franka":[174],"Emika":[175],"low-cost":[179],"dual-arm":[180],"demonstrate":[182],"effectiveness":[184],"proposed":[187],"policy.":[190],"Demos":[191],"be":[193,205],"found":[194],"link":[196,199],"1":[197],"or":[198],"2":[200],"code":[203],"will":[204],"released":[206],"at":[207],"https://github.com/MCG-NJU/TPM.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}