{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:07:33Z","timestamp":1775596053320,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFC3308500"],"award-info":[{"award-number":["2024YFC3308500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92570206"],"award-info":[{"award-number":["92570206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473356"],"award-info":[{"award-number":["62473356"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L232028"],"award-info":[{"award-number":["L232028"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242060"],"award-info":[{"award-number":["L242060"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Key R&D Program of Chongqing","award":["CSTB2024TIAD-STX0028"],"award-info":[{"award-number":["CSTB2024TIAD-STX0028"]}]},{"name":"Chongqing Economy and Information Technology R&D Program","award":["YJX-2025001001003"],"award-info":[{"award-number":["YJX-2025001001003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3673974","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:55:25Z","timestamp":1773431725000},"page":"6002-6009","source":"Crossref","is-referenced-by-count":0,"title":["BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3725-2686","authenticated-orcid":false,"given":"Haosheng","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0444-1079","authenticated-orcid":false,"given":"Weixin","family":"Mao","sequence":"additional","affiliation":[{"name":"LimX Dynamic, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5757-9581","authenticated-orcid":false,"given":"Zihan","family":"Lan","sequence":"additional","affiliation":[{"name":"LimX Dynamic, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Xiong","sequence":"additional","affiliation":[{"name":"LimX Dynamic, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9320-4920","authenticated-orcid":false,"given":"Hongan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3354-1968","authenticated-orcid":false,"given":"Chenyang","family":"Si","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-1201","authenticated-orcid":false,"given":"Xiaoming","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4252-8693","authenticated-orcid":false,"given":"Hua","family":"Chen","sequence":"additional","affiliation":[{"name":"LimX Dynamic, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","volume":"270","author":"Kim","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544909"},{"key":"ref5","first-page":"61229","article-title":"3D-VLA: A 3D vision-language-action generative world model","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhen","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3653303"},{"key":"ref7","article-title":"EfficientVLA: Training-free acceleration and compression for vision-language-action models","author":"Yang","year":"2025"},{"key":"ref8","first-page":"3866","article-title":"Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs","volume-title":"Proc. Conf. Robot Learn.","author":"Xu","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref10","article-title":"RoboMatrix: A skill-centric hierarchical framework for scalable robot task planning and execution in open-world","author":"Mao","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831380"},{"key":"ref12","article-title":"HybridVLA: Collaborative diffusion and autoregression in a unified vision-language-action model","author":"Liu","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3550849"},{"key":"ref14","article-title":"RDT-1B: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3589149"},{"key":"ref16","article-title":"SP-VLA: A joint model scheduling and token pruning approach for VLA model acceleration","author":"Li","year":"2025"},{"key":"ref17","article-title":"Simplevla-RL: Scaling VLA training via reinforcement learning","author":"Li","year":"2025"},{"key":"ref18","article-title":"Inspire: Vision-language-action models with intrinsic spatial reasoning","author":"Zhang","year":"2025"},{"key":"ref19","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.505"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01501.x"},{"key":"ref22","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref24","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"ref27","article-title":"$\\pi$0.5: A vision-language-action model with open-world generalization","author":"Intelligence","year":"2025"},{"key":"ref28","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Bolya","year":"2023"},{"key":"ref29","article-title":"3D CAVLA: Leveraging depth and 3D context to generalize vision language action models for unseen tasks","author":"Bhat","year":"2025"},{"key":"ref30","article-title":"Grounding DINO 1.5: Advance theEdge of open-set object detection","author":"Ren","year":"2024"},{"key":"ref31","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref32","article-title":"RoboTwin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation","author":"Chen","year":"2025"},{"issue":"11","key":"ref33","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref35","article-title":"DECO: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11433770.pdf?arnumber=11433770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:02:12Z","timestamp":1775592132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":35,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3673974","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}