{"id":"https://openalex.org/W4415538382","doi":"https://doi.org/10.1145/3746027.3755703","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","display_name":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538382","doi":"https://doi.org/10.1145/3746027.3755703"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755703","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043924969","display_name":"Baining Zhao","orcid":"https://orcid.org/0000-0002-9653-3316"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baining Zhao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9653-3316","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073471363","display_name":"Ziyou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyou Wang","raw_affiliation_strings":["Northeastern University, Qinghuangdao, China"],"raw_orcid":"https://orcid.org/0009-0005-2297-1830","affiliations":[{"raw_affiliation_string":"Northeastern University, Qinghuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111303041","display_name":"J. Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjie Fang","raw_affiliation_strings":["Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0008-2599-9929","affiliations":[{"raw_affiliation_string":"Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078622343","display_name":"Chen Gao","orcid":"https://orcid.org/0000-0002-7561-5646"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Gao","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7561-5646","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026025438","display_name":"Fanhang Man","orcid":"https://orcid.org/0000-0002-5830-0685"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanhang Man","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5830-0685","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062631244","display_name":"Jinqiang Cui","orcid":"https://orcid.org/0000-0002-7833-1876"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiang Cui","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7833-1876","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlei Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8271-5023","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355277","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-5617-1659"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5617-1659","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93352927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11071","last_page":"11080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9643999934196472,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9643999934196472,"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/embodied-cognition","display_name":"Embodied cognition","score":0.8388000130653381},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6897000074386597},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6273000240325928},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6180999875068665},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.557699978351593},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3855000138282776},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8388000130653381},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6897000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5583000183105469},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C20693621","wikidata":"https://www.wikidata.org/wiki/Q6667502","display_name":"Logical framework","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1549290346","https://openalex.org/W2032340090","https://openalex.org/W2038445360","https://openalex.org/W2999156928","https://openalex.org/W3175099349","https://openalex.org/W3205786327","https://openalex.org/W4230240367","https://openalex.org/W4281643269","https://openalex.org/W4311076232","https://openalex.org/W4381802186","https://openalex.org/W4390991722","https://openalex.org/W4392866731","https://openalex.org/W4394862905","https://openalex.org/W4399324146","https://openalex.org/W4402716288","https://openalex.org/W4402727142","https://openalex.org/W4405013818","https://openalex.org/W4405808695","https://openalex.org/W4406793847","https://openalex.org/W4410068177","https://openalex.org/W4412945400","https://openalex.org/W4414320956"],"related_works":[],"abstract_inverted_index":{"Humans":[0],"can":[1],"perceive":[2],"and":[3,43,95,111,129,138],"reason":[4],"about":[5],"spatial":[6,98],"relationships":[7],"from":[8],"sequential":[9],"visual":[10],"observations,":[11],"such":[12,22,107],"as":[13,108],"egocentric":[14],"video":[15,78],"streams.":[16],"However,":[17],"how":[18],"pretrained":[19],"models":[20,89],"acquire":[21],"abilities,":[23],"especially":[24],"high-level":[25],"reasoning,":[26],"remains":[27],"unclear.":[28],"This":[29],"paper":[30],"introduces":[31],"Embodied-R,":[32],"a":[33,55,82],"collaborative":[34],"framework":[35],"combining":[36],"large-scale":[37],"Vision-Language":[38],"Models":[39,46],"(VLMs)":[40],"for":[41,48,126],"perception":[42],"small-scale":[44],"Language":[45],"(LMs)":[47],"reasoning.":[49],"Using":[50],"Reinforcement":[51],"Learning":[52],"(RL)":[53],"with":[54,68,81],"novel":[56],"reward":[57,127],"system":[58],"considering":[59],"think-answer":[60],"logical":[61],"consistency,":[62],"the":[63],"model":[64,132],"achieves":[65],"slow-thinking":[66],"capabilities":[67],"limited":[69],"computational":[70],"resources.":[71],"After":[72],"training":[73,122],"on":[74,92,123],"only":[75],"5k":[76],"embodied":[77,97],"samples,":[79],"Embodied-R":[80,101],"3B":[83],"LM":[84],"matches":[85],"state-of-the-art":[86],"multimodal":[87],"reasoning":[88,99],"(OpenAI-o1,":[90],"Gemini-2.5-pro)":[91],"both":[93],"in-distribution":[94],"out-of-distribution":[96],"tasks.":[100],"also":[102],"exhibits":[103],"emergent":[104],"thinking":[105],"patterns":[106],"systematic":[109],"analysis":[110],"contextual":[112],"integration.":[113],"We":[114],"further":[115],"explore":[116],"research":[117],"questions":[118],"including":[119],"response":[120],"length,":[121],"VLM,":[124],"strategies":[125],"design,":[128],"differences":[130],"in":[131],"generalization":[133],"after":[134],"SFT":[135],"(Supervised":[136],"Fine-Tuning)":[137],"RL":[139],"training.":[140],"The":[141],"project":[142],"page":[143],"is":[144],"available":[145],"at:":[146],"https://embodiedcity.github.io/Embodied-R/.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}