{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:31Z","timestamp":1777890151729,"version":"3.51.4"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01032","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11089-11099","source":"Crossref","is-referenced-by-count":0,"title":["VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers"],"prefix":"10.1109","author":[{"given":"Yating","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiange","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"SJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561232"},{"key":"ref5","volume-title":"Minivla: A better vla with a smaller footprint.","author":"Belkhale","year":"2024"},{"key":"ref6","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref8","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"1","article-title":"Anyvlm: Unified vision-language model for any robot morphology","volume-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Chen","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref12","article-title":"Igor: Image-goal representations are the atomic control units for foundation models in embodied ai","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref15","first-page":"8469","article-title":"Palm-e: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1319"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","article-title":"Rh20t: A comprehensive robotic dataset for learning diverse skills in one-shot","author":"Fang","year":"2023","journal-title":"arXiv preprint"},{"issue":"2","key":"ref19","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"The C Users Journal"},{"key":"ref20","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Gervet"},{"key":"ref21","article-title":"Relay policy learning: Solving longhorizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Deep reinforcement learning in parameterized action space","author":"Hausknecht","year":"2015","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref25","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.017"},{"key":"ref28","article-title":"Behavior generation with latent actions","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref31","article-title":"Language models are few-shot learners","volume":"1","author":"Mann","year":"2020","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"4062","article-title":"Quest: Self-supervised skill abstractions for learning continuous control","volume":"37","author":"Mete","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations","author":"Mu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.012"},{"issue":"8","key":"ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref37","article-title":"Taming scalable visual tokenizer for autoregressive image generation","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Llm pruning and distillation in practice: The minitron approach","author":"Turuvekere Sreenivas","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0638"},{"key":"ref41","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref44","article-title":"Any-point trajectory modeling for policy learning","author":"Wen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation","author":"Wen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Transferring foundation models for generalizable robotic manipulation","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Spatiotemporal predictive pre-training for robotic motor control","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Tra-moe: Learning trajectory prediction model from multiple domains for adaptive policy conditioning","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Como: Learning continuous latent motion from internet videos for scalable robot learning","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Latent action pretraining from videos","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Robotic control via embodied chain-of-thought reasoning","author":"Zawalski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref53","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Diception: A generalist diffusion model for visual perceptual tasks","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref56","article-title":"Vlas: Vision-language-action model with speech instructions for customized robot manipulation","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"3d-vla: A 3d vision-language-action generative world model","author":"Zhen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02096"},{"key":"ref59","author":"Zhou","year":"2020","journal-title":"Plas: Latent action space for offline reinforcement learning"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"},{"key":"ref61","article-title":"Spa: 3d spatial-awareness enables effective embodied representation","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445372.pdf?arnumber=11445372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:01Z","timestamp":1777613521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01032","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}