{"id":"https://openalex.org/W4406094089","doi":"https://doi.org/10.1109/lra.2025.3526436","title":"GR-MG: Leveraging Partially-Annotated Data via Multi-Modal Goal-Conditioned Policy","display_name":"GR-MG: Leveraging Partially-Annotated Data via Multi-Modal Goal-Conditioned Policy","publication_year":2025,"publication_date":"2025-01-06","ids":{"openalex":"https://openalex.org/W4406094089","doi":"https://doi.org/10.1109/lra.2025.3526436"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3526436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3526436","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/A5101867545","display_name":"Peiyan Li","orcid":"https://orcid.org/0009-0005-8404-5779"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyan Li","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China","New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0005-8404-5779","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044013282","display_name":"Hongtao Wu","orcid":"https://orcid.org/0000-0002-6442-8159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongtao Wu","raw_affiliation_strings":["ByteDance Research, Beijing, China","ByteDance Research, China"],"raw_orcid":"https://orcid.org/0000-0002-6442-8159","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"ByteDance Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-8239-7229","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107437437","display_name":"Chilam Cheang","orcid":"https://orcid.org/0000-0003-1992-4644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chilam Cheang","raw_affiliation_strings":["ByteDance Research, Beijing, China","ByteDance Research, China"],"raw_orcid":"https://orcid.org/0000-0003-1992-4644","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"ByteDance Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-8647","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065667064","display_name":"Tao Kong","orcid":"https://orcid.org/0000-0002-9412-1457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Kong","raw_affiliation_strings":["ByteDance Research, Beijing, China","ByteDance Research, China"],"raw_orcid":"https://orcid.org/0000-0002-9412-1457","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"ByteDance Research, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.3371,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98301486,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"10","issue":"2","first_page":"1912","last_page":"1919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7609999775886536,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7609999775886536,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.6751000285148621,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.6592000126838684,"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/modal","display_name":"Modal","score":0.5993804931640625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4814831018447876},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12888970971107483}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5993804931640625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4814831018447876},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12888970971107483},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3526436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3526436","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":[{"id":"https://openalex.org/G1383591865","display_name":null,"funder_award_id":"62276261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G296931599","display_name":null,"funder_award_id":"2021128","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G5156147101","display_name":null,"funder_award_id":"62236010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8053739178","display_name":null,"funder_award_id":"62322607","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"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2625366777","https://openalex.org/W2984008963","https://openalex.org/W3176484337","https://openalex.org/W3205786327","https://openalex.org/W4285218426","https://openalex.org/W4293498911","https://openalex.org/W4313156423","https://openalex.org/W4383109478","https://openalex.org/W4385403811","https://openalex.org/W4385430451","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4386076215","https://openalex.org/W4401416041","https://openalex.org/W4402354155","https://openalex.org/W4402673453","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6802366246","https://openalex.org/W6810080435","https://openalex.org/W6810655313","https://openalex.org/W6840133048","https://openalex.org/W6846242362","https://openalex.org/W6848903804","https://openalex.org/W6851416138","https://openalex.org/W6853468020","https://openalex.org/W6854738657","https://openalex.org/W6857236505","https://openalex.org/W6857274923","https://openalex.org/W6857479877","https://openalex.org/W6857711900","https://openalex.org/W6858376594","https://openalex.org/W6860545845","https://openalex.org/W6860622411","https://openalex.org/W6861392586","https://openalex.org/W6868136577","https://openalex.org/W6869853401"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"robotics":[1],"community":[2],"has":[3],"consistently":[4],"aimed":[5],"to":[6,55,62,149,160,205,213,225,229],"achieve":[7],"generalizable":[8],"robot":[9,22,47],"manipulation":[10],"with":[11,26],"flexible":[12],"natural":[13],"language":[14],"instructions.":[15],"One":[16],"primary":[17],"challenge":[18],"is":[19,31,114,123,211],"that":[20],"obtaining":[21],"trajectories":[23,48,96],"fully":[24],"annotated":[25],"both":[27,100,138],"actions":[28],"and":[29,33,46,85,97,103,135,141,218,227,233,252],"texts":[30],"time-consuming":[32],"labor-intensive.":[34],"However,":[35],"partially-annotated":[36,154],"data,":[37],"such":[38],"as":[39],"human":[40],"activity":[41],"videos":[42],"without":[43,49],"action":[44],"labels":[45],"text":[50,83,102,113,122,140],"labels,":[51],"are":[52,254],"much":[53],"easier":[54],"collect.":[56],"Can":[57],"we":[58,72,169],"leverage":[59,150],"these":[60],"data":[61,155],"enhance":[63],"the":[64,101,104,110,121,127,139,142,184,192,220,257],"generalization":[65,234],"capabilities":[66],"of":[67,153,195,201,246],"robots?":[68],"In":[69,187,207],"this":[70],"paper,":[71],"propose":[73,170],"GR-MG,":[74],"a":[75,82,86,131,171,199],"novel":[76,172,247],"method":[77],"which":[78,178],"supports":[79],"conditioning":[80],"on":[81,99,109,137,256],"instruction":[84],"goal":[87,93,105,128,167,174],"image.":[88,144],"During":[89,117],"training,":[90],"GR-MG":[91,125,148,190,210],"samples":[92],"images":[94],"from":[95,203,223],"conditions":[98,136],"image":[106,111,129,175],"or":[107],"solely":[108],"when":[112],"not":[115],"available.":[116],"inference,":[118],"where":[119],"only":[120],"provided,":[124],"generates":[126],"via":[130],"diffusion-based":[132],"image-editing":[133],"model":[134,177],"generated":[143],"This":[145],"approach":[146],"enables":[147],"large":[151],"amounts":[152],"while":[156],"still":[157],"using":[158],"languages":[159],"flexibly":[161],"specify":[162],"tasks.":[163],"To":[164],"generate":[165],"accurate":[166],"images,":[168],"progress-guided":[173],"generation":[176,185],"injects":[179],"task":[180],"progress":[181],"information":[182],"into":[183],"process.":[186],"simulation":[188],"experiments,":[189,209],"improves":[191,219],"average":[193],"number":[194],"tasks":[196,217],"completed":[197],"in":[198,231,243],"row":[200],"5":[202],"3.35":[204],"4.04.":[206],"real-robot":[208],"able":[212],"perform":[214],"58":[215],"different":[216],"success":[221],"rate":[222],"68.7%":[224],"78.1%":[226],"44.4%":[228],"60.6%":[230],"simple":[232],"settings,":[235],"respectively.":[236],"It":[237],"also":[238],"outperforms":[239],"comparing":[240],"baseline":[241],"methods":[242],"few-shot":[244],"learning":[245],"skills.":[248],"Video":[249],"demos,":[250],"code,":[251],"checkpoints":[253],"available":[255],"project":[258],"page:":[259],"<uri":[260],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[261],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://gr-mg.github.io/</uri>":[262],".":[263]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}