{"id":"https://openalex.org/W4388820116","doi":"https://doi.org/10.1109/access.2023.3334791","title":"Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments","display_name":"Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388820116","doi":"https://doi.org/10.1109/access.2023.3334791"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3334791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3334791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10323309.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10323309.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009170866","display_name":"Aleksei Staroverov","orcid":"https://orcid.org/0000-0002-4730-1543"},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksei Staroverov","raw_affiliation_strings":["Artificial Intelligence Research Institute (AIRI), Moscow, Russia","AIRI, Moscow, Russia","Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071362360","display_name":"Andrey Gorodetsky","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey S. Gorodetsky","raw_affiliation_strings":["Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0007-0763-9455","affiliations":[{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112506509","display_name":"A. S. Krishtopik","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrei S. Krishtopik","raw_affiliation_strings":["Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093293991","display_name":"Uliana A. Izmesteva","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Uliana A. Izmesteva","raw_affiliation_strings":["Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025655729","display_name":"Dmitry Yudin","orcid":"https://orcid.org/0000-0002-1407-2633"},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry A. Yudin","raw_affiliation_strings":["Artificial Intelligence Research Institute (AIRI), Moscow, Russia","AIRI, Moscow, Russia","Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia"],"raw_orcid":"https://orcid.org/0000-0002-1407-2633","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, 9, Institutskij per, Dolgoprudny, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054791318","display_name":"Alexey K. Kovalev","orcid":"https://orcid.org/0000-0003-2180-0990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey K. Kovalev","raw_affiliation_strings":["Artificial Intelligence Research Institute (AIRI), Moscow, Russia","AIRI, Moscow, Russia","Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080806360","display_name":"Aleksandr I. Panov","orcid":"https://orcid.org/0000-0002-9747-3837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr I. Panov","raw_affiliation_strings":["Artificial Intelligence Research Institute (AIRI), Moscow, Russia","AIRI, Moscow, Russia","Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-9747-3837","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\", 9, 60-letiya Oktyabrya pr, Moscow, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.7767,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69631895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"130548","last_page":"130559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.8648520708084106},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8144930601119995},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7572944164276123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5561926364898682},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5381442308425903},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5150370597839355},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4758074879646301},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4517943859100342},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4162992537021637},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.386652410030365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1925368309020996},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12762784957885742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648520708084106},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8144930601119995},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7572944164276123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561926364898682},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5381442308425903},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5150370597839355},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4758074879646301},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4517943859100342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4162992537021637},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.386652410030365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1925368309020996},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12762784957885742},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3334791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3334791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10323309.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a1dbf8dab5934c439c2f37832a1dd9bb","is_oa":true,"landing_page_url":"https://doaj.org/article/a1dbf8dab5934c439c2f37832a1dd9bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 130548-130559 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3334791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3334791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10323309.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2928192979","display_name":null,"funder_award_id":"000000D730321P5Q0002","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"},{"id":"https://openalex.org/G3736275146","display_name":null,"funder_award_id":"70-2021-00138","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"},{"id":"https://openalex.org/G5927019889","display_name":null,"funder_award_id":"70-2021-00138","funder_id":"https://openalex.org/F4320330091","funder_display_name":"Moscow Institute of Physics and Technology"},{"id":"https://openalex.org/G6723968916","display_name":null,"funder_award_id":"000000D730321P5Q0002","funder_id":"https://openalex.org/F4320324261","funder_display_name":"National Research University Higher School of Economics"}],"funders":[{"id":"https://openalex.org/F4320316464","display_name":"Kalashnikov Izhevsk State Technical University","ror":"https://ror.org/01pvdd334"},{"id":"https://openalex.org/F4320317497","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16"},{"id":"https://openalex.org/F4320319755","display_name":"Analytical Center for the Government of the Russian Federation","ror":null},{"id":"https://openalex.org/F4320324087","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375"},{"id":"https://openalex.org/F4320324261","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516"},{"id":"https://openalex.org/F4320330091","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322"},{"id":"https://openalex.org/F4320334801","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388820116.pdf","grobid_xml":"https://content.openalex.org/works/W4388820116.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2150468603","https://openalex.org/W2277195237","https://openalex.org/W2612690371","https://openalex.org/W2896457183","https://openalex.org/W2952122856","https://openalex.org/W2963150697","https://openalex.org/W2963323070","https://openalex.org/W2969876226","https://openalex.org/W3008492644","https://openalex.org/W3088310808","https://openalex.org/W3120778962","https://openalex.org/W3195577433","https://openalex.org/W3205388591","https://openalex.org/W3212580602","https://openalex.org/W4224912544","https://openalex.org/W4281608743","https://openalex.org/W4281663178","https://openalex.org/W4286987939","https://openalex.org/W4287026640","https://openalex.org/W4288089799","https://openalex.org/W4288376504","https://openalex.org/W4292947419","https://openalex.org/W4294435908","https://openalex.org/W4294936113","https://openalex.org/W4303648971","https://openalex.org/W4318142155","https://openalex.org/W4323572061","https://openalex.org/W4323650237","https://openalex.org/W4381245688","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4386071839","https://openalex.org/W4390873343","https://openalex.org/W4391759936","https://openalex.org/W6678262379","https://openalex.org/W6755207826","https://openalex.org/W6758604235","https://openalex.org/W6765779288","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6769627184","https://openalex.org/W6774583691","https://openalex.org/W6778883912","https://openalex.org/W6796289742","https://openalex.org/W6799634771","https://openalex.org/W6800751262","https://openalex.org/W6800875267","https://openalex.org/W6803376173","https://openalex.org/W6804244202","https://openalex.org/W6810640255","https://openalex.org/W6838557027","https://openalex.org/W6838865847","https://openalex.org/W6838931476","https://openalex.org/W6840199509","https://openalex.org/W6842475989","https://openalex.org/W6842654171","https://openalex.org/W6843759960","https://openalex.org/W6846242362","https://openalex.org/W6849543150","https://openalex.org/W6850503672","https://openalex.org/W6850591238","https://openalex.org/W6853289313","https://openalex.org/W6854738657"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556"],"abstract_inverted_index":{"In":[0,145],"this":[1],"work,":[2],"we":[3,35],"propose":[4],"and":[5,101,114,125,143],"investigate":[6],"an":[7,26],"original":[8],"approach":[9],"to":[10,37,111,135],"using":[11,155],"a":[12,17,22,45,92,107,136,152,165],"pre-trained":[13],"multimodal":[14],"transformer":[15,48],"of":[16,89,96,186],"specialized":[18],"architecture":[19,49],"for":[20,52,80,98],"controlling":[21,148],"robotic":[23,81],"agent":[24,150],"in":[25,91,123,151],"object":[27],"manipulation":[28,82],"task":[29],"based":[30,43],"on":[31,44,180],"language":[32,63],"instruction,":[33],"which":[34],"refer":[36],"as":[38,62],"RozumFormer.":[39],"Our":[40],"model":[41,77,108,131,163],"is":[42],"bimodal":[46],"(text-image)":[47],"originally":[50],"trained":[51],"solving":[53],"tasks":[54,83,113,175,187],"that":[55,105,160,168],"use":[56],"one":[57],"or":[58],"both":[59],"modalities,":[60],"such":[61,106],"modeling,":[64],"visual":[65,153],"question":[66],"answering,":[67],"image":[68],"captioning,":[69],"text":[70],"recognition,":[71],"text-to-image":[72],"generation,":[73],"etc.":[74],"The":[75],"discussed":[76],"was":[78],"adapted":[79],"by":[84],"organizing":[85],"the":[86,130,133,149,162,172,184],"input":[87],"sequence":[88],"tokens":[90,97],"particular":[93],"way,":[94],"consisting":[95],"text,":[99],"images,":[100],"actions.":[102],"We":[103],"demonstrated":[104],"adapts":[109],"well":[110],"new":[112,139],"shows":[115],"better":[116],"results":[117],"with":[118,164],"fine-tuning":[119,161],"than":[120],"complete":[121],"training":[122],"simulation":[124],"real":[126,137],"environments.":[127],"To":[128],"transfer":[129],"from":[132,171,188],"simulator":[134],"robot,":[138],"datasets":[140],"were":[141],"collected":[142],"annotated.":[144],"addition,":[146],"experiments":[147],"environment":[154],"reinforcement":[156],"learning":[157],"have":[158],"shown":[159],"mixed":[166],"dataset":[167],"includes":[169],"examples":[170],"initial":[173],"visual-linguistic":[174],"only":[176],"slightly":[177],"decreases":[178],"performance":[179],"these":[181],"tasks,":[182],"simplifying":[183],"addition":[185],"another":[189],"domain.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
