{"id":"https://openalex.org/W4414008295","doi":"https://doi.org/10.1109/tase.2025.3606549","title":"Efficient Alignment of Unconditioned Action Prior for Language-Conditioned Pick and Place in Clutter","display_name":"Efficient Alignment of Unconditioned Action Prior for Language-Conditioned Pick and Place in Clutter","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414008295","doi":"https://doi.org/10.1109/tase.2025.3606549"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3606549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3606549","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-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/A5062930488","display_name":"Kechun Xu","orcid":"https://orcid.org/0000-0002-3632-917X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kechun Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114196519","display_name":"Xunlong Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunlong Xia","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619525","display_name":"Kaixuan Wang","orcid":"https://orcid.org/0000-0001-9210-0233"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002539987","display_name":"Yifei Yang","orcid":"https://orcid.org/0009-0001-3460-8394"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113204587","display_name":"Yunxuan Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxuan Mao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074924505","display_name":"Bing Deng","orcid":"https://orcid.org/0000-0001-7591-9749"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Deng","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019081110","display_name":"Rong Xiong","orcid":"https://orcid.org/0000-0001-9318-9014"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5062930488"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.0178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88203888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":null,"first_page":"21256","last_page":"21268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.979200005531311,"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/clutter","display_name":"Clutter","score":0.8019574880599976},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6750104427337646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5401261448860168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4398939609527588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38746124505996704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32195448875427246},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.205856591463089},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.19468653202056885}],"concepts":[{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.8019574880599976},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6750104427337646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5401261448860168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4398939609527588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38746124505996704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32195448875427246},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.205856591463089},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.19468653202056885},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3606549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3606549","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2103542852","display_name":null,"funder_award_id":"U24A20128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3720780789","display_name":null,"funder_award_id":"Grant No. U24A20128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8757401803","display_name":null,"funder_award_id":"LD25F030001","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2415216611","https://openalex.org/W2904207885","https://openalex.org/W2904246096","https://openalex.org/W2962837436","https://openalex.org/W2966615203","https://openalex.org/W3004047800","https://openalex.org/W3035198432","https://openalex.org/W3090814639","https://openalex.org/W3109585842","https://openalex.org/W3132114951","https://openalex.org/W3173991492","https://openalex.org/W3175388581","https://openalex.org/W3176770340","https://openalex.org/W3201276757","https://openalex.org/W3212977909","https://openalex.org/W4285102336","https://openalex.org/W4292972737","https://openalex.org/W4312891162","https://openalex.org/W4312960937","https://openalex.org/W4319068933","https://openalex.org/W4382366145","https://openalex.org/W4383066282","https://openalex.org/W4383097638","https://openalex.org/W4383108836","https://openalex.org/W4383108845","https://openalex.org/W4385245566","https://openalex.org/W4385318467","https://openalex.org/W4385430678","https://openalex.org/W4385431115","https://openalex.org/W4386160361","https://openalex.org/W4388979610","https://openalex.org/W4390830078","https://openalex.org/W4390874575","https://openalex.org/W4394828156","https://openalex.org/W4400904825","https://openalex.org/W4401413802","https://openalex.org/W4401415428","https://openalex.org/W4402354093","https://openalex.org/W4403277141","https://openalex.org/W4404520163","https://openalex.org/W4405022569","https://openalex.org/W4414079054"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W2011939812","https://openalex.org/W4394861761","https://openalex.org/W1977371217","https://openalex.org/W2035264131","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,89,129],"study":[1],"the":[2,142,155,165],"task":[3,173],"of":[4,158],"language-conditioned":[5],"pick":[6,137,181],"and":[7,22,61,87,124,138,147,164,182,192,196],"place":[8,139,183],"in":[9,19,47,162,185],"clutter,":[10,186],"where":[11],"a":[12,16,26,48,132,149],"robot":[13],"should":[14],"grasp":[15],"target":[17],"object":[18],"open":[20],"clutter":[21],"move":[23],"it":[24],"to":[25,75,119,153,189],"specified":[27],"place.":[28],"Some":[29],"approaches":[30],"learn":[31],"end-to-end":[32],"policies":[33],"with":[34,104,121,176],"features":[35],"from":[36,52,84],"vision":[37,60],"foundation":[38,45,63,82],"models,":[39,64],"requiring":[40],"large":[41],"datasets.":[42],"Others":[43],"combine":[44],"models":[46],"zero-shot":[49,126],"setting,":[50],"suffering":[51],"cascading":[53],"errors.":[54],"In":[55,70],"addition,":[56],"they":[57],"primarily":[58],"leverage":[59],"language":[62,193],"focusing":[65],"less":[66,122],"on":[67],"action":[68,95,102],"priors.":[69],"this":[71],"paper,":[72],"we":[73],"aim":[74],"develop":[76],"an":[77,94],"effective":[78],"policy":[79,118,134,150,170],"by":[80,108],"integrating":[81],"priors":[83,103,107],"vision,":[85],"language,":[86],"action.":[88],"propose":[90],"A<sup":[91],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>,":[93],"prior":[96],"alignment":[97,114],"method":[98],"that":[99,131,168],"aligns":[100],"unconditioned":[101],"3D":[105],"vision-language":[106],"learning":[109],"one":[110],"attention":[111],"layer.":[112],"The":[113],"formulation":[115],"enables":[116],"our":[117,169],"train":[120],"data":[123],"preserve":[125],"generalization":[127],"capabilities.":[128],"show":[130,167],"shared":[133],"for":[135,144,179],"both":[136,180],"actions":[140],"enhances":[141],"performance":[143],"each":[145],"task,":[146],"introduce":[148],"adaptation":[151],"scheme":[152],"accommodate":[154],"multi-modal":[156],"nature":[157],"actions.":[159],"Extensive":[160],"experiments":[161],"simulation":[163],"real-world":[166],"achieves":[171],"higher":[172],"success":[174],"rates":[175],"fewer":[177],"steps":[178],"tasks":[184],"effectively":[187],"generalizing":[188],"unseen":[190],"objects":[191],"instructions.":[194],"Videos":[195],"codes":[197],"are":[198],"available":[199],"at":[200],"https://xukechun.github.io/papers/A2.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
