{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:09:24Z","timestamp":1774872564339,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020409","name":"Analytical Center for the Government of the Russian Federation","doi-asserted-by":"publisher","award":["000000D730321P5Q0002"],"award-info":[{"award-number":["000000D730321P5Q0002"]}],"id":[{"id":"10.13039\/100020409","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020409","name":"Analytical Center for the Government of the Russian Federation","doi-asserted-by":"publisher","award":["70-2021-00138"],"award-info":[{"award-number":["70-2021-00138"]}],"id":[{"id":"10.13039\/100020409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3334791","type":"journal-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:29:10Z","timestamp":1700508550000},"page":"130548-130559","source":"Crossref","is-referenced-by-count":8,"title":["Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments"],"prefix":"10.1109","volume":"11","author":[{"given":"Aleksei","family":"Staroverov","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0763-9455","authenticated-orcid":false,"given":"Andrey S.","family":"Gorodetsky","sequence":"additional","affiliation":[{"name":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei S.","family":"Krishtopik","sequence":"additional","affiliation":[{"name":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uliana A.","family":"Izmesteva","sequence":"additional","affiliation":[{"name":"Center of Cognitive Modeling, Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1407-2633","authenticated-orcid":false,"given":"Dmitry A.","family":"Yudin","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey K.","family":"Kovalev","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute (AIRI), Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref3","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref4","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref5","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref6","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref7","article-title":"Embodied BERT: A transformer model for embodied, language-guided visual task completion","author":"Suglia","year":"2021","journal-title":"arXiv:2108.04927"},{"key":"ref8","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref9","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref10","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv:2303.03378"},{"key":"ref11","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv:2204.01691"},{"key":"ref12","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv:2307.15818"},{"key":"ref13","article-title":"VIMA: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022","journal-title":"arXiv:2210.03094"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref16","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3295255"},{"key":"ref18","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner"},{"key":"ref19","article-title":"Multi-game decision transformers","author":"Lee","year":"2022","journal-title":"arXiv:2205.15241"},{"key":"ref20","article-title":"Efficient planning in a compact latent action space","author":"Jiang","year":"2022","journal-title":"arXiv:2208.10291"},{"key":"ref21","article-title":"Recurrent memory decision transformer","author":"Bessonov","year":"2023","journal-title":"arXiv:2306.09459"},{"key":"ref22","article-title":"SMART: Self-supervised multi-task pretrAining with contRol transformers","author":"Sun","year":"2023","journal-title":"arXiv:2301.09816"},{"key":"ref23","article-title":"Decision transformer under random frame dropping","author":"Hu","year":"2023","journal-title":"arXiv:2303.03391"},{"key":"ref24","article-title":"Transformers are sample-efficient world models","author":"Micheli","year":"2022","journal-title":"arXiv:2209.00588"},{"key":"ref25","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021","journal-title":"arXiv:2109.01652"},{"key":"ref26","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref27","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126658"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102365"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app10051555"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722001230"},{"key":"ref33","first-page":"212","article-title":"i-Sim2Real: Reinforcement learning of robotic policies in tight human\u2013robot interaction loops","volume-title":"Proc. Conf. Robot Learn.","author":"Abeyruwan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561858"},{"key":"ref36","article-title":"A comprehensive review of YOLO: From YOLOv1 and beyond","author":"Terven","year":"2023","journal-title":"arXiv:2304.00501"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"issue":"11","key":"ref39","first-page":"120","article-title":"The OpenCV library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s J. Softw. Tools"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"1","key":"ref41","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-2124"},{"key":"ref44","article-title":"Analysing mathematical reasoning abilities of neural models","author":"Saxton","year":"2019","journal-title":"arXiv:1904.01557"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1405.0312"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref47","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref48","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel","year":"2017"},{"key":"ref49","volume-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"ref50","volume-title":"AIRI.","year":"2022"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10323309.pdf?arnumber=10323309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T21:54:58Z","timestamp":1709416498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10323309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3334791","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}