{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:10:16Z","timestamp":1784211016677,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Sci-Tech Innovation Initiative by the Science and Technology Commission of Shanghai Municipality","award":["24ZR1419000"],"award-info":[{"award-number":["24ZR1419000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12471501"],"award-info":[{"award-number":["12471501"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/lra.2025.3544909","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T22:59:02Z","timestamp":1740437942000},"page":"3988-3995","source":"Crossref","is-referenced-by-count":70,"title":["TinyVLA: Toward Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1660-3268","authenticated-orcid":false,"given":"Junjie","family":"Wen","sequence":"first","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5126-838X","authenticated-orcid":false,"given":"Yichen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4777-9731","authenticated-orcid":false,"given":"Jinming","family":"Li","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3838-2210","authenticated-orcid":false,"given":"Minjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Tang","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2095-2140","authenticated-orcid":false,"given":"Kun","family":"Wu","sequence":"additional","affiliation":[{"name":"Syracuse University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2879-3244","authenticated-orcid":false,"given":"Zhiyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4943-6625","authenticated-orcid":false,"given":"Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Cheng","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9389-6472","authenticated-orcid":false,"given":"Chaomin","family":"Shen","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2983-555X","authenticated-orcid":false,"given":"Yaxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8612-5022","authenticated-orcid":false,"given":"Feifei","family":"Feng","sequence":"additional","affiliation":[{"name":"Midea Group, AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4418-0114","authenticated-orcid":false,"given":"Jian","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Innovation Center of Humanoid Robotics, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref5","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref7","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","volume":"205","author":"Ahn","year":"2022"},{"key":"ref8","first-page":"892","article-title":"Unleashing the power of pre-trained language models for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2024"},{"key":"ref9","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Brohan","year":"2023"},{"key":"ref10","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","volume":"270","author":"Kim","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref12","first-page":"800","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref13","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.284200"},{"key":"ref15","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref16","article-title":"MobileVLM v2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"},{"key":"ref18","first-page":"3157","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Proc. Conf. Robot Learn.","volume":"270","author":"Zawalski","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609992"},{"key":"ref20","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","volume-title":"Proc. Conf. Robot Learn.","volume":"270","author":"Fu","year":"2024"},{"key":"ref21","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023"},{"key":"ref22","first-page":"23","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable task planning","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Rana","year":"2023"},{"key":"ref23","article-title":"RT-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"ref24","first-page":"74394","article-title":"H-InDex: Visual reinforcement learning with hand-informed representations for dexterous manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ze","year":"2024"},{"key":"ref25","article-title":"ALOHA 2: An enhanced low-cost hardware for bimanual teleoperation","author":"Aldaco","year":"2024"},{"key":"ref26","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Jang","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref29","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref30","first-page":"2397","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Biderman","year":"2023"},{"key":"ref31","first-page":"1752","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lu","year":"2023"},{"key":"ref32","first-page":"31333","article-title":"A unified sequence interface for vision tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"ref34","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021"},{"key":"ref35","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref36","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref37","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Seo","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000346"},{"key":"ref42","first-page":"18284","article-title":"The magical benchmark for robust imitation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Toyer","year":"2020"},{"key":"ref43","first-page":"208","article-title":"Spatial generalization of visual imitation learning with position-invariant regularization","volume-title":"Proc. RSS 2023 Workshop Symmetries Robot Learn.","author":"Yin","year":"2023"},{"key":"ref44","first-page":"1210","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats","year":"2021"},{"key":"ref45","article-title":"PaliGemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024"},{"key":"ref46","first-page":"1910","article-title":"ALOHA unleashed: A simple recipe for robot dexterity","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Zhao","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10893718\/10900471-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10893718\/10900471.pdf?arnumber=10900471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:44:11Z","timestamp":1742319851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10900471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":46,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3544909","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}