{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:21Z","timestamp":1777890141562,"version":"3.51.4"},"reference-count":63,"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\/iccv51701.2025.01322","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14248-14258","source":"Crossref","is-referenced-by-count":0,"title":["DexVLG: Dexterous Vision-Language-Grasp Model at Scale"],"prefix":"10.1109","author":[{"given":"Jiawei","family":"He","sequence":"first","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danshi","family":"Li","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinqiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zekun","family":"Qi","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Chen","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yi","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"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":"Dexterous functional grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Agarwal"},{"key":"ref3","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Task-oriented dexterous grasp synthesis via differentiable grasp wrench boundary estimator","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Bodex: Scalable and efficient robotic dexterous grasp synthesis using bilevel optimization","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Springgrasp: An optimization pipeline for robust and compliant dexterous pre-grasp synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref8","article-title":"Learning robust real-world dexterous grasping policies via implicit shape augmentation","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802733"},{"key":"ref11","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Dong"},{"key":"ref12","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref13","author":"Grathwohl","year":"2018","journal-title":"Ffjord: Free-form continuous dynamics for scalable reversible generative models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28897"},{"key":"ref15","article-title":"Manifoldplus: A robust and scalable watertight manifold surface generation method for triangle soups","author":"Huang","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3561573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"ref18","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341806"},{"key":"ref20","article-title":"Multi-graspllm: A multimodal 11 m for multi-hand semantic guided grasp generation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392425"},{"key":"ref23","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Liu","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129138"},{"key":"ref26","article-title":"Dextrack: Towards generalizable neural tracking control for dexterous manipulation from human references","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14909"},{"key":"ref28","article-title":"Find any part in 3d","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Isaac gym: High performance GPU based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"NeurIPS"},{"key":"ref30","year":"2024","journal-title":"OpenAI. Introducing gpt-4o and more tools to chatgpt free users"},{"key":"ref31","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","volume-title":"In International Conference on Machine Learning","author":"Qi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref34","article-title":"Sofar: Language-grounded orientation bridges spatial reasoning and object manipulation","author":"Qi","year":"2025","journal-title":"CoRR, abs\/2502.13143"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.015"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160765"},{"key":"ref38","article-title":"Segment any mesh: Zero-shot mesh part segmentation via lifting segment anything 2 to 3d","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_12"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160314"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref44","article-title":"Vlm see, robot do: Human demo video to robot action plan via vision language model","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530103"},{"key":"ref48","article-title":"Grasp as you say: Language-guided dexterous grasp generation","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3472349"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01698"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref53","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref55","article-title":"Sampart3d: Segment any part in 3d objects","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_22"},{"key":"ref57","article-title":"Dexgraspnet 2.0: Learning generative dexterous grasping in largescale synthetic cluttered scenes","volume-title":"8th Annual Conference on Robot Learning","author":"Zhang"},{"key":"ref58","article-title":"Dreamvla: A vision-languageaction model dreamed with comprehensive world knowledge","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Dexgrasp-diffusion: Diffusionbased unified functional grasp synthesis method for multidexterous robotic hands","volume-title":"arXiv preprint","author":"Zhang","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref61","article-title":"Transfusion: Predict the next token and diffuse images with one multimodal model","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhou"},{"key":"ref62","article-title":"Uni3d: Exploring unified 3d representation at scale","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhou"},{"key":"ref63","article-title":"Partslip++: Enhancing low-shot 3d part segmentation via multi-view instance segmentation and maximum likelihood estimation","author":"Zhou","year":"2023","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\/11444467.pdf?arnumber=11444467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:39Z","timestamp":1777613379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01322","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}