{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:04Z","timestamp":1777889704420,"version":"3.51.4"},"reference-count":43,"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 Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322117,62371365,U24B20136"],"award-info":[{"award-number":["62322117,62371365,U24B20136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005320","name":"Xidian University","doi-asserted-by":"publisher","award":["YJSJ25007"],"award-info":[{"award-number":["YJSJ25007"]}],"id":[{"id":"10.13039\/501100005320","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\/iccv51701.2025.00643","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6839-6848","source":"Crossref","is-referenced-by-count":0,"title":["Towards Long-Horizon Vision-Language-Action System: Reasoning, Acting and Memory"],"prefix":"10.1109","author":[{"given":"Daixun","family":"Li","sequence":"first","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxiang","family":"Cao","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglai","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiying","family":"Xie","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlin","family":"Hui","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lunkai","family":"Lin","sequence":"additional","affiliation":[{"name":"AgileX Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Xie","sequence":"additional","affiliation":[{"name":"AgileX Robotics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00207"},{"key":"ref2","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01709"},{"key":"ref7","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Achieving human level competitive robot table tennis","author":"D\u2019Ambrosio","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref11","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref14","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00029"},{"key":"ref18","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02040"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref22","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"18081","article-title":"Hierarchical diffusion policy for kinematics-aware multitask robotic manipulation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ma","year":"2024"},{"key":"ref24","article-title":"Robomatrix: A skill-centric hierarchical framework for scalable robot task planning and execution in open-world","author":"Mao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adp6419"},{"key":"ref27","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01470"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00894-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref33","article-title":"Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation","author":"Wen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref37","article-title":"Robotic control via embodied chain-of-thought reasoning","author":"Zawalski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Generalizable humanoid manipulation with improved 3d diffusion policies","author":"Ze","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref40","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Multimodal chain-ofthought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-47788-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01717"}],"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\/11444034.pdf?arnumber=11444034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:53Z","timestamp":1777612793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00643","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}