{"id":"https://openalex.org/W4413925758","doi":"https://doi.org/10.1109/icra55743.2025.11127531","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","display_name":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925758","doi":"https://doi.org/10.1109/icra55743.2025.11127531"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5100759588","display_name":"Jianxiong Li","orcid":"https://orcid.org/0000-0002-1885-2549"},"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":true,"raw_author_name":"Jianxiong Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113887407","display_name":"Zhihao Wang","orcid":"https://orcid.org/0000-0001-7019-4398"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wang","raw_affiliation_strings":["College of Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102439585","display_name":"Jinliang Zheng","orcid":null},"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":"Jinliang Zheng","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056799282","display_name":"Xujuan Zhou","orcid":"https://orcid.org/0000-0002-1736-739X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaoai Zhou","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011001883","display_name":"G.F. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guanming Wang","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033877290","display_name":"Guanglu Song","orcid":"https://orcid.org/0000-0001-5391-5712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglu Song","raw_affiliation_strings":["Sensetime Research"],"affiliations":[{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588064","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0004-4454-9641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Sensetime Research"],"affiliations":[{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627504","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-3163-3420"},"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":"Jingjing Liu","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663313","display_name":"Ya-Qin Zhang","orcid":"https://orcid.org/0000-0003-1851-7932"},"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":"Ya-Qin Zhang","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073958329","display_name":"Junzhi Yu","orcid":"https://orcid.org/0000-0002-6347-572X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhi Yu","raw_affiliation_strings":["College of Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052921346","display_name":"Xianyuan Zhan","orcid":"https://orcid.org/0000-0002-3683-0554"},"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":"Xianyuan Zhan","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100759588"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13466626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4182","last_page":"4189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7049999833106995,"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/T12031","display_name":"Speech and dialogue systems","score":0.7049999833106995,"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":0.6736999750137329,"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/T13382","display_name":"Robotics and Automated Systems","score":0.6233999729156494,"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/computer-science","display_name":"Computer science","score":0.7172343730926514},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6944770812988281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5391595363616943},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5364459753036499},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32041293382644653},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13739031553268433},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06227108836174011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172343730926514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6944770812988281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391595363616943},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5364459753036499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32041293382644653},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13739031553268433},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06227108836174011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2625366777","https://openalex.org/W2760103357","https://openalex.org/W2963703448","https://openalex.org/W3005290098","https://openalex.org/W3009295642","https://openalex.org/W3153469116","https://openalex.org/W3174263371","https://openalex.org/W3176484337","https://openalex.org/W3205786327","https://openalex.org/W3211462570","https://openalex.org/W4249680818","https://openalex.org/W4293498911","https://openalex.org/W4312438583","https://openalex.org/W4385430559","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4385431288","https://openalex.org/W4385567053","https://openalex.org/W4400769217","https://openalex.org/W4402354047","https://openalex.org/W4402354083","https://openalex.org/W4402354098","https://openalex.org/W4402354155","https://openalex.org/W4403337227","https://openalex.org/W4403636136","https://openalex.org/W4404782964"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Multimodal":[0],"task":[1,19,60,109],"specification":[2],"is":[3],"essential":[4],"for":[5,25],"enhanced":[6],"robotic":[7,75,117,159],"performance,":[8],"where":[9],"Cross-modality":[10],"Alignment":[11,70],"enables":[12],"the":[13,32,65,93,98,144],"robot":[14,66,141],"to":[15,31,57,90],"holistically":[16],"understand":[17],"complex":[18],"instructions.":[20],"Directly":[21],"annotating":[22],"multimodal":[23,36,59,76,100,122],"instructions":[24,47],"model":[26],"training":[27],"proves":[28],"impractical,":[29],"due":[30],"sparsity":[33],"of":[34,107,147],"paired":[35],"data.":[37,81],"In":[38],"this":[39],"study,":[40],"we":[41,52,63,83],"demonstrate":[42],"that":[43],"by":[44,72],"leveraging":[45],"unimodal":[46],"abundant":[48],"in":[49,97,154,158],"real":[50,140],"data,":[51],"can":[53],"effectively":[54],"teach":[55],"robots":[56],"learn":[58],"specifications.":[61],"First,":[62],"endow":[64],"with":[67],"strong":[68],"Crossmodality":[69],"capabilities,":[71],"pretraining":[73],"a":[74,120],"encoder":[77],"using":[78],"extensive":[79],"out-of-domain":[80],"Then,":[82],"employ":[84],"two":[85],"Collapse":[86],"and":[87,131,139],"Corrupt":[88],"operations":[89,118],"further":[91],"bridge":[92],"remaining":[94],"modality":[95],"gap":[96],"learned":[99],"representation.":[101],"This":[102],"approach":[103],"projects":[104],"different":[105],"modalities":[106],"identical":[108],"goal":[110],"as":[111],"interchangeable":[112],"representations,":[113],"thus":[114],"enabling":[115],"accurate":[116],"within":[119],"well-aligned":[121],"latent":[123],"space.":[124],"Evaluation":[125],"across":[126],"more":[127],"than":[128],"130":[129],"tasks":[130],"4000":[132],"evaluations":[133],"on":[134],"both":[135],"simulated":[136],"LIBERO":[137],"benchmark":[138],"platforms":[142],"showcases":[143],"superior":[145],"capabilities":[146],"our":[148],"proposed":[149],"framework,":[150],"demonstrating":[151],"significant":[152],"potential":[153],"overcoming":[155],"data":[156],"constraints":[157],"learning.":[160],"Website:":[161],"zh1hao.wang/Robo_MUTUAL":[162]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}