{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:02:56Z","timestamp":1780639376204,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62403142"],"award-info":[{"award-number":["62403142"]}],"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":["24511103100"],"award-info":[{"award-number":["24511103100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/lra.2026.3693565","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:59:35Z","timestamp":1778788775000},"page":"8439-8446","source":"Crossref","is-referenced-by-count":0,"title":["Resolving State Ambiguity in Robot Manipulation via Adaptive Working Memory Recoding"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3975-4036","authenticated-orcid":false,"given":"Qingda","family":"Hu","sequence":"first","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4652-3861","authenticated-orcid":false,"given":"Ziheng","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3058-4154","authenticated-orcid":false,"given":"Zijun","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8586-2353","authenticated-orcid":false,"given":"Kaizhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8132-4599","authenticated-orcid":false,"given":"Xizhou","family":"Bu","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuolei","family":"Sun","sequence":"additional","affiliation":[{"name":"Westwell, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Westwell, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8211-2812","authenticated-orcid":false,"given":"Jieru","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1365-396X","authenticated-orcid":false,"given":"Zhongxue","family":"Gan","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4249-526X","authenticated-orcid":false,"given":"Wenchao","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref4","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref6","first-page":"2679","article-title":"Openvla: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Kim","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127739"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.158"},{"key":"ref9","article-title":"DreamVLA: A vision-language-action model dreamed with comprehensive world knowledge","volume-title":"Proc. 39th Annu. Conf. Neural Inform. Process. Syst.","author":"Zhang","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref11","first-page":"15 925","article-title":"SAM2Act: Integrating visual foundation model with a memory architecture for robotic manipulation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fang","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i5.37337"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3615520"},{"key":"ref14","first-page":"54 277","article-title":"TraceVLA: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Zheng","year":"2025"},{"key":"ref15","article-title":"ContextVLA: Vision-language-action model with amortized multi-frame context","author":"Jang","year":"2025"},{"key":"ref16","article-title":"Learning long-context diffusion policies via past-token prediction","author":"Torne","year":"2025"},{"key":"ref17","article-title":"History-aware visuomotor policy learning via point tracking","author":"Chen","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2022.03.016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_02298"},{"key":"ref20","article-title":"Flow matching for generative modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lipman","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801557"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.014"},{"key":"ref23","first-page":"33 914","article-title":"4D-VLA: Spatiotemporal vision-language-action pretraining with cross-scene calibration","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"38","author":"Zhang","year":"2026"},{"key":"ref24","article-title":"MemoryVLA: Perceptual-cognitive memory in vision-language-action models for robotic manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2026"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i22.38903"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s25041093"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01445"},{"key":"ref30","article-title":"GhostShell: Streaming LLM function calls for concurrent embodied programming","author":"Gong","year":"2025"},{"key":"ref31","article-title":"OmniNav: A unified framework for prospective exploration and visual-language navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue","year":"2026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01168-7"},{"key":"ref33","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref34","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Trans. Mach. Learn. Res. J.","author":"Oquab","year":"2024"},{"key":"ref35","first-page":"5776","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Proc. Adv. Neural. Inf. Process. Syst.","volume":"33","author":"Wang","year":"2020"},{"key":"ref36","first-page":"1898","article-title":"ControlVLA: Few-shot object-centric adaptation for pre-trained vision-language-action models","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Li","year":"2025"},{"key":"ref37","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref38","article-title":"RMBench: Memory-dependent robotic manipulation benchmark with insights into policy design","author":"Chen","year":"2026"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref40","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Intelligence","year":"2025"},{"key":"ref41","article-title":"X-VLA: Soft-prompted transformer as scalable cross-embodiment vision-language-action model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng","year":"2026"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11520249.pdf?arnumber=11520249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:22:07Z","timestamp":1780636927000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":41,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3693565","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}