{"id":"https://openalex.org/W4416749283","doi":"https://doi.org/10.1109/iros60139.2025.11246478","title":"CLAP: A Closed-Loop Diffusion Transformer Action Foundation Model for Robotic Manipulation","display_name":"CLAP: A Closed-Loop Diffusion Transformer Action Foundation Model for Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749283","doi":"https://doi.org/10.1109/iros60139.2025.11246478"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100399465","display_name":"Mu Li","orcid":"https://orcid.org/0000-0002-7109-3166"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692750","display_name":"Dong Ye","orcid":"https://orcid.org/0000-0003-3715-5885"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubo Dong","raw_affiliation_strings":["South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053970344","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0002-9823-8468"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Application Innovation Laboratory,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Application Innovation Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019906827","display_name":"Chenguang Yang","orcid":"https://orcid.org/0000-0001-5255-5559"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"9808","last_page":"9815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7885000109672546,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7885000109672546,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08829999715089798,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.028300000354647636,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6741999983787537},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6247000098228455},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49230000376701355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6859999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851999759674072},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6741999983787537},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6247000098228455},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3099096615","https://openalex.org/W4383097638","https://openalex.org/W4383109488","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4390872297","https://openalex.org/W4390873312","https://openalex.org/W4392405809","https://openalex.org/W4402354045","https://openalex.org/W4402713111","https://openalex.org/W4402716288","https://openalex.org/W4403337227","https://openalex.org/W4403878347","https://openalex.org/W4405784982","https://openalex.org/W4405786528","https://openalex.org/W4407874080","https://openalex.org/W4410706720","https://openalex.org/W4411449683","https://openalex.org/W4411528087","https://openalex.org/W4413917780"],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,94],"large":[3],"Vision-Language-Action":[4],"(VLA)":[5],"models":[6],"has":[7],"enhanced":[8],"the":[9,70,80,91,104,129],"robot\u2019s":[10],"ability":[11,130],"to":[12,110,131,138],"manipulate":[13],"objects":[14,140],"in":[15,28,98],"unseen":[16,139],"scenarios":[17],"based":[18],"on":[19,79,117],"language":[20],"instructions.":[21],"While":[22],"existing":[23,126],"VLAs":[24],"have":[25],"demonstrated":[26],"promise":[27],"various":[29],"scenarios,":[30],"they":[31],"still":[32],"struggle":[33],"with":[34,73,103,128],"effective":[35],"multi-modal":[36],"data":[37],"feature":[38],"extraction":[39],"and":[40,83,136,141],"lack":[41],"a":[42,74,84,112],"closed-loop":[43,113],"inference":[44,109],"framework.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,68],"propose":[50],"an":[51],"advanced":[52],"VLA":[53,71],"model.":[54,114],"Unlike":[55],"previous":[56],"works":[57],"that":[58,121],"repurpose":[59],"VLM":[60],"for":[61,87],"action":[62,66,76,96],"prediction":[63],"using":[64],"simple":[65],"quantization,":[67],"componentized":[69],"architecture":[72],"specialized":[75],"module":[77,86,106],"conditioned":[78],"model":[81,123],"output":[82],"critic":[85,105],"inference.":[88],"We":[89],"demonstrate":[90,120],"performance":[92],"improvement":[93],"diffusion":[95],"transformers":[97],"modeling":[99],"continuous":[100],"temporal":[101],"actions,":[102],"applied":[107],"during":[108],"form":[111],"Extensive":[115],"experiments":[116],"real":[118],"robots":[119],"our":[122],"significantly":[124],"outperforms":[125],"methods,":[127],"handle":[132],"complex,":[133],"high-precision":[134],"tasks":[135],"generalize":[137],"backgrounds.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}