{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T21:55:45Z","timestamp":1786658145276,"version":"build-2736575974"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JC STEM Lab of Autonomous Intelligent Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tro.2026.3686184","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:52:04Z","timestamp":1776801124000},"page":"1872-1883","source":"Crossref","is-referenced-by-count":1,"title":["Is Diversity All You Need for Scalable Robotic Manipulation?"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8465-0559","authenticated-orcid":false,"given":"Modi","family":"Shi","sequence":"first","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9500-5722","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6344-3880","authenticated-orcid":false,"given":"Yuxiang","family":"Lu","sequence":"additional","affiliation":[{"name":"AgiBot, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3278-2983","authenticated-orcid":false,"given":"Chiming","family":"Liu","sequence":"additional","affiliation":[{"name":"AgiBot, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2743-8278","authenticated-orcid":false,"given":"Guanghui","family":"Ren","sequence":"additional","affiliation":[{"name":"AgiBot, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2412-9330","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maoqing","family":"Yao","sequence":"additional","affiliation":[{"name":"AgiBot, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9110-5534","authenticated-orcid":false,"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247088"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref4","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref7","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref10","first-page":"23123","article-title":"Prismatic VLMs: Investigating the design space of visually-conditioned language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karamcheti","year":"2024"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref14","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. CoRL","author":"Brohan","year":"2023"},{"key":"ref15","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. CoRL","author":"Kim","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref17","article-title":"RDT-1B: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.014"},{"key":"ref19","article-title":"GR00 T N1: An open foundation model for generalist humanoid robots","author":"Bjorck","year":"2025"},{"key":"ref20","article-title":"Intelligent robot manipulation requires self-directed learning","author":"Chen","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref22","first-page":"1723","article-title":"BridgeData v2: A dataset for robot learning at scale","volume-title":"Proc. CoRL","author":"Walke","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref24","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. Int. Conf. Robot. Automat.","author":"Padalkar","year":"2024"},{"key":"ref25","article-title":"Data scaling laws in imitation learning for robotic manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2025"},{"key":"ref26","article-title":"ManiBox: Enhancing spatial grasping generalization via scalable simulation data generation","author":"Tan","year":"2024"},{"key":"ref27","first-page":"124420","article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","volume-title":"Proc. NeurIPS","author":"Wang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02096"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.093"},{"key":"ref30","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"Proc. CoRL","author":"Doshi","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128520"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref35","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown","year":"2020"},{"key":"ref36","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref37","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref38","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544909"},{"key":"ref40","article-title":"DexVLA: Vision-language model with plug-in diffusion expert for general robot control","volume-title":"Proc. CoRL","author":"Wen","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref45","first-page":"4603","article-title":"Genie: Generative interactive environments","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bruce","year":"2024"},{"key":"ref46","article-title":"Latent action pretraining from videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye","year":"2025"},{"key":"ref47","article-title":"IGOR: Image-goal representations are the atomic control units for foundation models in embodied AI","author":"Chen","year":"2024"},{"key":"ref48","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2024"},{"key":"ref49","article-title":"GR-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024"},{"key":"ref50","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. NeurIPS","author":"Du","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.123"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4411"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611615"},{"key":"ref55","article-title":"All robots in one: A new standard and unified dataset for versatile, general-purpose embodied agents","author":"Wang","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.152"},{"key":"ref57","article-title":"FreeTacMan: Robot-free visuo-tactile data collection system for contact-rich manipulation","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"Wu","year":"2026"},{"key":"ref58","article-title":"Agility Meets Stability: Versatile humanoid control with heterogeneous data","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"Pan","year":"2026"},{"key":"ref59","article-title":"Gemini Robotics 1.5: Pushing the frontier of generalist robots with advanced embodied reasoning, thinking, and motion transfer","author":"Team","year":"2025"},{"key":"ref60","article-title":"Emergence of human to robot transfer in vision-language-action models","author":"Kareer","year":"2025"},{"key":"ref61","article-title":"What matters in learning from large-scale datasets for robot manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Saxena","year":"2025"},{"key":"ref62","first-page":"145","article-title":"ReMix: Optimizing data mixtures for large scale imitation learning","volume-title":"Proc. CoRL","author":"Hejna","year":"2024"},{"key":"ref63","article-title":"Preliminary investigation into data scaling laws for imitation learning-based end-to-end autonomous driving","author":"Zheng","year":"2024"},{"key":"ref64","article-title":"ManiSkill: Generalizable manipulation skill benchmark with large-scale demonstrations","volume-title":"Proc. NeurIPS Datasets Benchmarks","author":"Mu","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICM62621.2025.10934874"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref68","first-page":"599","article-title":"DemoSpeedup: Accelerating visuomotor policies via entropy-guided demonstration acceleration","volume-title":"Proc. CoRL","author":"Guo","year":"2025"},{"key":"ref69","first-page":"721","article-title":"SAIL: Faster-than-demonstration execution of imitation learning policies","volume-title":"Proc. CoRL","author":"Arachchige","year":"2025"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/11297026\/11488937.pdf?arnumber=11488937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:52:25Z","timestamp":1779220345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tro.2026.3686184","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}