{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:04Z","timestamp":1777889044335,"version":"3.51.4"},"reference-count":58,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01253","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13491-13501","source":"Crossref","is-referenced-by-count":0,"title":["$A_{0}$: An Affordance-Aware Hierarchical Model for General Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Rongtao","family":"Xu","sequence":"first","affiliation":[{"name":"Spatialtemporal AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Guo","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youpeng","family":"Wen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoting","family":"Yang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Kuang","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Spatialtemporal AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref2","volume-title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","author":"Awadalla","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref7","volume-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref8","volume-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","author":"Brohan","year":"2023"},{"key":"ref9","volume-title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","author":"Cheang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00657"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref12","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref14","volume-title":"Figure AI Team. Helix: Our first humanoid robot, 2025","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161571"},{"key":"ref16","volume-title":"Diffusion Transformer Policy: Scaling Diffusion Transformer for Generalist Vision-Language-Action Learning","author":"Hou","year":"2025"},{"key":"ref17","volume-title":"A3VLM: Actionable Articulation-Aware Vision Language Model","author":"Huang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref19","volume-title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","author":"Huang"},{"key":"ref20","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref22","article-title":"Openvla: An open-source vision-language-action model","volume-title":"8th Annual Conference on Robot Learning","author":"Jin Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","article-title":"Ram: Retrieval-based affordance transfer for generalizable zero-shot robotic manipulation","author":"Kuang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","volume-title":"CogACT: A Foundational Vision-LanguageAction Model for Synergizing Cognition and Action in Robotic Manipulation","author":"Li","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610593"},{"key":"ref28","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"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/4933270371"},{"key":"ref30","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41714-6_180595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref34","article-title":"kpam: Keypoint affordances for category-level robotic manipulation","volume":"abs\/1903.06684","author":"Manuelli","year":"2019","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref36","volume-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref41","volume-title":"Goal-conditioned imitation learning using scorebased diffusion policies","author":"Reuss","year":"2023"},{"key":"ref42","article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","volume-title":"Octo: An Open-Source Generalist Robot Policy","author":"Model Team","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160982"},{"key":"ref46","volume-title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","author":"Wang","year":"2023"},{"key":"ref47","article-title":"Any-point trajectory modeling for policy learning","author":"Wen","year":"2024","journal-title":"Robotics: Science and Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1298"},{"key":"ref49","volume-title":"Unleashing Large-Scale Video Generative Pretraining for Visual Robot Manipulation","author":"Wu","year":"2023"},{"key":"ref50","volume-title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","author":"Wu","year":"2022"},{"key":"ref51","article-title":"Flow as the cross-domain manipulation interface","volume-title":"8th Annual Conference on Robot Learning","author":"Xu"},{"key":"ref52","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","volume-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01325"},{"key":"ref55","article-title":"General flow as foundation affordance for scalable robot learning","volume-title":"8th Annual Conference on Robot Learning","author":"Yuan"},{"key":"ref56","article-title":"Robopoint: A vision-language model for spatial affordance prediction in robotics","volume-title":"8th Annual Conference on Robot Learning","author":"Yuan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref58","volume-title":"3DVLA: A 3D Vision-Language-Action Generative World Model","author":"Zhen","year":"2024"}],"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\/11444045.pdf?arnumber=11444045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:45Z","timestamp":1777611945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01253","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}