{"id":"https://openalex.org/W4402726973","doi":"https://doi.org/10.1109/cvpr52733.2024.02482","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","display_name":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402726973","doi":"https://doi.org/10.1109/cvpr52733.2024.02482"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5054969834","display_name":"Yijun Yang","orcid":"https://orcid.org/0000-0002-9243-6228"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Yang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039076312","display_name":"Tianyi Zhou","orcid":"https://orcid.org/0000-0001-5348-0632"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhou","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104205442","display_name":"Kanxue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kanxue Li","raw_affiliation_strings":["Yunnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["Yunnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000112545","display_name":"Lusong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lusong Li","raw_affiliation_strings":["JD Explore Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333320","display_name":"Li Shen","orcid":"https://orcid.org/0000-0002-5443-0503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["JD Explore Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115430452","display_name":"Xiaodong He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD Explore Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589441","display_name":"Jing Jiang","orcid":"https://orcid.org/0009-0008-0489-2217"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["University of Technology Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008058155","display_name":"Yuhui Shi","orcid":"https://orcid.org/0009-0008-0457-2475"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Shi","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26265","last_page":"26275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.88521808385849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6762571334838867},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6550947427749634},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5072800517082214},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39729130268096924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27791619300842285},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.061634361743927}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.88521808385849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762571334838867},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6550947427749634},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5072800517082214},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39729130268096924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27791619300842285},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.061634361743927},{"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/cvpr52733.2024.02482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G131974302","display_name":null,"funder_award_id":"2023YFE0106300,2017YFC0804002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":112,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1850531616","https://openalex.org/W1931877416","https://openalex.org/W2124344619","https://openalex.org/W2142641780","https://openalex.org/W2158349948","https://openalex.org/W2161414194","https://openalex.org/W2174803659","https://openalex.org/W2194775991","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2805805280","https://openalex.org/W2810346659","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2962944953","https://openalex.org/W2963150697","https://openalex.org/W2963277051","https://openalex.org/W2970393539","https://openalex.org/W3022566517","https://openalex.org/W3034758614","https://openalex.org/W3126325318","https://openalex.org/W3166396011","https://openalex.org/W3213931323","https://openalex.org/W4205181707","https://openalex.org/W4221143046","https://openalex.org/W4221152848","https://openalex.org/W4224912544","https://openalex.org/W4293566037","https://openalex.org/W4297664295","https://openalex.org/W4300799055","https://openalex.org/W4300973271","https://openalex.org/W4304195432","https://openalex.org/W4318718936","https://openalex.org/W4318751977","https://openalex.org/W4319323461","https://openalex.org/W4323572061","https://openalex.org/W4323651349","https://openalex.org/W4353112996","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4367628410","https://openalex.org/W4376312115","https://openalex.org/W4377130677","https://openalex.org/W4378465306","https://openalex.org/W4378505261","https://openalex.org/W4378771755","https://openalex.org/W4378942419","https://openalex.org/W4379548460","https://openalex.org/W4380353763","https://openalex.org/W4383097638","https://openalex.org/W4384264726","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4385565405","https://openalex.org/W4386721983","https://openalex.org/W4386794445","https://openalex.org/W4387559151","https://openalex.org/W4387636027","https://openalex.org/W4387764390","https://openalex.org/W4387839203","https://openalex.org/W4391801200","https://openalex.org/W4394862732","https://openalex.org/W4396681775","https://openalex.org/W4401386967","https://openalex.org/W4401417048","https://openalex.org/W4402667011","https://openalex.org/W6604566608","https://openalex.org/W6638018090","https://openalex.org/W6639056794","https://openalex.org/W6640174482","https://openalex.org/W6680724558","https://openalex.org/W6718092244","https://openalex.org/W6741002519","https://openalex.org/W6747106673","https://openalex.org/W6751275834","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6767047803","https://openalex.org/W6776438516","https://openalex.org/W6784429693","https://openalex.org/W6791353385","https://openalex.org/W6809509765","https://openalex.org/W6809646742","https://openalex.org/W6844617645","https://openalex.org/W6846254642","https://openalex.org/W6849177959","https://openalex.org/W6849470435","https://openalex.org/W6850327944","https://openalex.org/W6850370512","https://openalex.org/W6850503672","https://openalex.org/W6850886341","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852418670","https://openalex.org/W6852489829","https://openalex.org/W6852669507","https://openalex.org/W6852874933","https://openalex.org/W6852884379","https://openalex.org/W6853116092","https://openalex.org/W6853229423","https://openalex.org/W6853313673","https://openalex.org/W6853465110","https://openalex.org/W6854454755","https://openalex.org/W6854929498","https://openalex.org/W6855873836","https://openalex.org/W6855890912","https://openalex.org/W6856965252","https://openalex.org/W6857017073","https://openalex.org/W6857478865","https://openalex.org/W6860926904","https://openalex.org/W6862027763"],"related_works":["https://openalex.org/W1487956045","https://openalex.org/W1601503673","https://openalex.org/W1592154258","https://openalex.org/W1527882169","https://openalex.org/W1596535966","https://openalex.org/W4388039923","https://openalex.org/W2096246921","https://openalex.org/W2145935766","https://openalex.org/W2136562935","https://openalex.org/W26087330"],"abstract_inverted_index":{"While":[0],"large":[1],"language":[2],"models":[3,34],"(LLMs)":[4],"excel":[5],"in":[6,56,65,85,107,116,132,150,217],"a":[7,86,103,108,117,133,175,184],"simulated":[8],"world":[9,20,52,69,89,110,161],"of":[10,23,51,145,187],"texts,":[11],"they":[12,60],"struggle":[13],"to":[14,137,158,181,183,210],"interact":[15],"with":[16,41,74],"the":[17,57,78,139,142,146,159,168,195,201,218],"more":[18],"realistic":[19],"without":[21,90,190],"perceptions":[22],"other":[24,79],"modalities":[25],"such":[26],"as":[27],"visual":[28,68,88,109,147,160],"or":[29],"audio":[30],"signals.":[31],"Although":[32],"vision-language":[33],"(VLMs)":[35],"integrate":[36],"LLM":[37,113,196],"modules":[38],"(1)":[39],"aligned":[40],"static":[42],"image":[43],"features,":[44],"and":[45,70,96],"(2)":[46],"may":[47],"possess":[48],"prior":[49],"knowledge":[50],"dynamics":[53],"(as":[54],"demonstrated":[55],"text":[58,119,134],"world),":[59],"have":[61],"not":[62],"been":[63],"trained":[64],"an":[66,82,112,151],"embodied":[67,83],"thus":[71],"cannot":[72],"align":[73],"its":[75],"dynamics.":[76],"On":[77],"hand,":[80],"training":[81],"agent":[84,105,114],"noisy":[87],"expert":[91],"guidance":[92,193],"is":[93,172],"often":[94],"chal-lenging":[95],"inefficient.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101,122],"train":[102],"VLM":[104,140],"living":[106],"using":[111],"excelling":[115],"parallel":[118,170],"world.":[120],"Specifically,":[121],"distill":[123],"LLM's":[124],"reflection":[125],"outcomes":[126],"(improved":[127],"actions":[128],"by":[129,174],"analyzing":[130],"mistakes)":[131],"world's":[135],"tasks":[136,144,189,205],"finetune":[138],"on":[141,200],"same":[143],"world,":[148],"resulting":[149],"Embodied":[152],"Multi-Modal":[153],"Agent":[154],"(EMMA)":[155],"quickly":[156],"adapting":[157],"dy-namics.":[162],"Such":[163],"cross-modality":[164],"imitation":[165],"learning":[166],"between":[167],"two":[169],"worlds":[171],"achieved":[173],"novel":[176],"DAgger-DPO":[177],"algorithm,":[178],"enabling":[179],"EMMA":[180],"generalize":[182],"broad":[185],"scope":[186],"new":[188],"any":[191],"further":[192],"from":[194],"expert.":[197],"Extensive":[198],"evaluations":[199],"ALFWorld":[202],"benchmark's":[203],"diverse":[204],"highlight":[206],"EMMA's":[207],"superior":[208],"performance":[209],"SOTA":[211],"VLM-based":[212],"agents,":[213],"e.g.,":[214],"20%-70%":[215],"improvement":[216],"success":[219],"rate.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}