{"id":"https://openalex.org/W7137920361","doi":"https://doi.org/10.1609/aaai.v40i12.37937","title":"Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models","display_name":"Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137920361","doi":"https://doi.org/10.1609/aaai.v40i12.37937"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i12.37937","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37937","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37937/41899","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37937/41899","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129643584","display_name":"Hanqing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150405","display_name":"Hongzhiwei Technology (China)","ror":"https://ror.org/04bapa014","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150405"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Hanqing Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (GZ)\nShanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (GZ)\nShanghai AI Laboratory","institution_ids":["https://openalex.org/I4210150405","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129667928","display_name":"Shaoyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shaoyang Wang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129731787","display_name":"Yiming Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhong","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684571","display_name":"Zemin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zemin Yang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650538","display_name":"Jiamin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Wang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689640","display_name":"Zhiqing Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqing Cui","raw_affiliation_strings":["Nanjing University of Information Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641399","display_name":"Jiahao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Yuan","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663325","display_name":"Yifan Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Han","raw_affiliation_strings":["Institute of automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669504","display_name":"Mingyu Liu","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":"Mingyu Liu","raw_affiliation_strings":["Zhejiang University\nShanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nShanghai AI Laboratory","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129678468","display_name":"Yuexin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexin Ma","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"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":0.23369116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"9738","last_page":"9746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4595000147819519,"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":0.4595000147819519,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.19990000128746033,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.11320000141859055,"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/affordance","display_name":"Affordance","score":0.8934999704360962},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7782999873161316},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6847000122070312},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6775000095367432},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5857999920845032},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.47620001435279846},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.8934999704360962},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7782999873161316},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6847000122070312},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330999732017517},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699999928474426},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.47620001435279846},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.351500004529953},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i12.37937","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37937","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37937/41899","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37937","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37937","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37937","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37937/41899","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137920361.pdf","grobid_xml":"https://content.openalex.org/works/W7137920361.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Affordance":[0],"grounding":[1,75],"focuses":[2],"on":[3],"predicting":[4],"the":[5,14,27,43,52,71],"specific":[6],"regions":[7],"of":[8,29],"objects":[9,48],"that":[10,77,149],"are":[11],"associated":[12],"with":[13,128],"actions":[15],"to":[16,106,120],"be":[17],"performed":[18],"by":[19],"robots.":[20],"It":[21],"plays":[22],"a":[23,88,95,114],"vital":[24],"role":[25],"in":[26],"fields":[28],"human-robot":[30],"interaction,":[31,33],"human-object":[32],"embodied":[34,37],"manipulation,":[35],"and":[36,60,103,130,140,155],"perception.":[38],"Existing":[39],"models":[40],"often":[41],"neglect":[42],"affordance":[44,74,97],"shared":[45],"among":[46],"different":[47],"because":[49],"they":[50],"lack":[51],"Chain-of-Thought(CoT)":[53],"reasoning":[54,62,117,133,144],"abilities,":[55],"limiting":[56],"their":[57],"out-of-domain":[58],"generalization":[59,139],"explicit":[61,132],"capabilities.":[63,145],"To":[64],"address":[65],"these":[66],"challenges,":[67],"we":[68,93,112],"propose":[69],"Affordance-R1,":[70],"first":[72],"unified":[73],"framework":[76],"integrates":[78],"cognitive":[79],"CoT":[80],"guided":[81],"Group":[82],"Relative":[83],"Policy":[84],"Optimization":[85],"(GRPO)":[86],"within":[87],"reinforcement":[89,126],"learning":[90,127],"paradigm.":[91],"Specifically,":[92],"designed":[94],"sophisticated":[96],"function,":[98],"which":[99],"contains":[100],"format,":[101],"perception,":[102],"cognition":[104],"rewards":[105],"effectively":[107],"guide":[108],"optimization":[109],"directions.":[110],"Furthermore,":[111],"constructed":[113],"high-quality":[115],"affordance-centric":[116],"dataset,":[118],"ReasonAff,":[119],"support":[121],"training.":[122],"Trained":[123],"exclusively":[124],"via":[125],"GRPO":[129],"without":[131],"data,":[134],"Affordance-R1":[135],"achieves":[136],"robust":[137],"zero-shot":[138],"exhibits":[141,156],"emergent":[142],"test-time":[143],"Comprehensive":[146],"experiments":[147],"demonstrate":[148],"our":[150],"model":[151],"outperforms":[152],"well-established":[153],"methods":[154],"open-world":[157],"generalization.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}
