{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:12:39Z","timestamp":1783437159683,"version":"3.54.6"},"reference-count":56,"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\/501100001809","name":"National 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"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24ZR1419000"],"award-info":[{"award-number":["24ZR1419000"]}],"id":[{"id":"10.13039\/501100003399","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\/iccv51701.2025.00910","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9759-9769","source":"Crossref","is-referenced-by-count":3,"title":["CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Midea Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Wen","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengmeng","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Cheng","sequence":"additional","affiliation":[{"name":"Midea Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feifei","family":"Feng","sequence":"additional","affiliation":[{"name":"Midea Group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"TraceVLA: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","volume-title":"Submitted to The Thirteenth International Conference on Learning Representations","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref5","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Zero-shot robotic manipulation with pretrained imageediting diffusion models","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","volume-title":"\u03c0_0: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref11","article-title":"Manipulateanything: Automating real-world robots using vision-language models","author":"Duan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref15","article-title":"A3vlm: Actionable articulation-aware vision language model","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref20","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref22","article-title":"OpenVLA: An opensource vision-language-action model","author":"Kim","journal-title":"2, 3, 6, 7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","article-title":"Chain of code: Reasoning with a language model-augmented code emulator","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","volume-title":"Cogact: A foundational vision-languageaction model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024"},{"key":"ref26","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref28","volume-title":"Data scaling laws in imitation learning for robotic manipulation","author":"Lin","year":"2024"},{"key":"ref29","article-title":"Cot-vla visual chain-of-thought reasoning for vision-language-action models","author":"Qingqing","year":"2024","journal-title":"Cot-vla visual chain-of-thought reasoning for vision-language-action models."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811931"},{"key":"ref34","first-page":"1540","article-title":"Same object, different grasps: Data and semantic knowledge for task-oriented grasping","volume-title":"Conference on robot learning","author":"Murali","year":"2021"},{"key":"ref35","volume-title":"Rtaffordance: Affordances are versatile intermediate representations for robot manipulation","author":"Nasiriany","year":"2024"},{"key":"ref36","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proceedings of Robotics: Science and Systems","author":"Team"},{"key":"ref37","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","volume-title":"Chatgpt"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"ref40","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref44","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref46","article-title":"DiffusionVLA: Scaling robot foundation models via unified diffusion and autoregression","author":"Wen","journal-title":"2024. 2, 3, 6"},{"key":"ref47","article-title":"Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation","author":"Wen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623635"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref50","article-title":"M2t2: Multi-task masked transformer for object-centric pick and place","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Robotic control via embodied chain-of-thought reasoning","author":"Zawalski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Zeng","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00166"},{"key":"ref55","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Scaling diffusion policy in transformer to 1 billion parameters for robotic manipulation","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\/11445407.pdf?arnumber=11445407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:38:07Z","timestamp":1777531087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00910","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}