{"id":"https://openalex.org/W4415593660","doi":"https://doi.org/10.1109/lra.2025.3625497","title":"S$^{2}$-Diffusion: Generalizing From Instance-Level to Category-Level Skills in Robot Manipulation","display_name":"S$^{2}$-Diffusion: Generalizing From Instance-Level to Category-Level Skills in Robot Manipulation","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415593660","doi":"https://doi.org/10.1109/lra.2025.3625497"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3625497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3625497","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":["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/A5021059709","display_name":"Quantao Yang","orcid":"https://orcid.org/0000-0001-5655-0990"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Quantao Yang","raw_affiliation_strings":["Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-5655-0990","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020344044","display_name":"Michael C. Welle","orcid":"https://orcid.org/0000-0003-3827-3824"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Michael C. Welle","raw_affiliation_strings":["Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3827-3824","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2965-2953","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014501729","display_name":"Olov Andersson","orcid":"https://orcid.org/0000-0001-7248-1112"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Olov Andersson","raw_affiliation_strings":["Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-7248-1112","affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021059709"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":2.1998,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89690338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"10","issue":"12","first_page":"12995","last_page":"13002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9803000092506409,"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":0.9803000092506409,"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":0.9068999886512756,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6819000244140625},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6277999877929688},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4350999891757965},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.40400001406669617},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.357699990272522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110000252723694},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6819000244140625},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6277999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021000146865845},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.357699990272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3625497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3625497","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W3035624836","https://openalex.org/W3039055967","https://openalex.org/W4293498911","https://openalex.org/W4383108895","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4386075561","https://openalex.org/W4390874575","https://openalex.org/W4401607567","https://openalex.org/W4402354003","https://openalex.org/W4402354045","https://openalex.org/W4402354126","https://openalex.org/W4402354155","https://openalex.org/W4402727359","https://openalex.org/W4403919020","https://openalex.org/W4407874080","https://openalex.org/W4415003139","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,45,146,149,165],"skill":[3],"learning":[4],"has":[5],"propelled":[6],"robot":[7,142],"manipulation":[8,18,143],"to":[9,15,32,53,81,85,121,163],"new":[10],"heights":[11],"by":[12],"enabling":[13,83],"it":[14,183],"learn":[16],"complex":[17],"tasks":[19],"from":[20,77],"a":[21,105,111,127,138],"practical":[22],"number":[23,140],"of":[24,56,90,99,125,141],"demonstrations.":[25],"However,":[26],"these":[27],"skills":[28,84,100],"are":[29,43],"often":[30],"limited":[31],"the":[33,46,57,91,123,150,178],"particular":[34],"action,":[35],"object,":[36],"and":[37,49,135,148],"environment":[38],"<italic":[39],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[40,71,158,194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">instances</i>":[41],"that":[42,96,156,188],"shown":[44],"training":[47,79],"data,":[48],"have":[50],"trouble":[51],"transferring":[52],"other":[54,175],"instances":[55,89,176],"same":[58,92,179],"category.":[59,93],"In":[60],"this":[61],"work":[62],"we":[63],"present":[64],"an":[65],"open-vocabulary":[66],"Spatial-Semantic":[67],"Diffusion":[68],"policy":[69],"(S<inline-formula":[70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[72,159],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>-Diffusion)":[73],"which":[74],"enables":[75,171],"generalization":[76],"instance-level":[78],"data":[80],"category-level,":[82],"be":[86,102],"transferable":[87],"between":[88],"We":[94,114],"show":[95,155],"functional":[97],"aspects":[98],"can":[101],"captured":[103],"via":[104],"promptable":[106],"semantic":[107],"module":[108],"combined":[109],"with":[110],"spatial":[112],"representation.":[113],"further":[115],"propose":[116],"leveraging":[117],"depth":[118],"estimation":[119],"networks":[120],"allow":[122],"use":[124],"only":[126],"single":[128],"RGB":[129],"camera.":[130],"Our":[131,153],"approach":[132],"is":[133,161],"evaluated":[134],"compared":[136],"on":[137,174,187],"diverse":[139],"tasks,":[144],"both":[145],"simulation":[147],"real":[151],"world.":[152],"results":[154],"S<inline-formula":[157],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>-Diffusion":[160],"invariant":[162],"changes":[164],"category-irrelevant":[166],"factors":[167],"as":[168,170],"well":[169],"satisfying":[172],"performance":[173],"within":[177],"category,":[180],"even":[181],"if":[182],"was":[184],"not":[185],"trained":[186],"specific":[189],"instance.":[190],"Project":[191],"website:":[192],"<uri":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://s2-diffusion.github.io</uri>.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-07T23:20:04.922697","created_date":"2025-10-28T00:00:00"}