{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:15:21Z","timestamp":1784146521651,"version":"3.55.0"},"reference-count":45,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NUS Artificial Intelligence Institute","award":["H1FY2025"],"award-info":[{"award-number":["H1FY2025"]}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","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.2026.3692345","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:18Z","timestamp":1778528898000},"page":"8487-8494","source":"Crossref","is-referenced-by-count":2,"title":["<b>VLA-Touch: Enhancing Vision-Language-Action Model With Dual-Level Tactile Feedback<\/b>"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3886-5054","authenticated-orcid":false,"given":"Jianxin","family":"Bi","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5952-1604","authenticated-orcid":false,"given":"Kevin Yuchen","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7653-9713","authenticated-orcid":false,"given":"Ce","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike Shou","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3278-0035","authenticated-orcid":false,"given":"Harold","family":"Soh","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref2","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn., Proc. Mach. Learn. Res.","volume":"270","author":"Kim","year":"2025"},{"key":"ref3","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Zitkovich","year":"2023"},{"key":"ref4","first-page":"6892","article-title":"Open X-Embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"O\u2019Neill","year":"2024"},{"key":"ref5","article-title":"RDT-1b: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref6","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","author":"Intelligence","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3677716"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3560871"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.052"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.24.1.167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.22719"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2006.03.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref15","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot.: Sci. Syst.","author":"Model","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref17","first-page":"8469","article-title":"PaLM-e: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Driess","year":"2023"},{"key":"ref18","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref19","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024"},{"key":"ref20","article-title":"Gr00t n1: An open foundation model for generalist humanoid robots","year":"2025"},{"key":"ref21","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref23","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Trans. Mach. Learn. Res.","author":"Oquab","year":"2024"},{"issue":"70","key":"ref24","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume-title":"J. Mach. Learn. Res.","volume":"25","author":"Chung","year":"2024"},{"key":"ref25","article-title":"Rh20t: A robotic dataset for learning diverse skills in one-shot","volume-title":"Proc. RSS Workshop Learn. Task Motion Plan.","author":"Fang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127987"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.55092\/rl20260001"},{"key":"ref28","article-title":"ForceVLA: Enhancing VLA models with a force-aware moe for contact-rich manipulation","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Proc. Syst.","author":"Yu","year":"2025"},{"key":"ref29","article-title":"Tactile-VLA: Unlocking vision-language-action models physical knowledge for tactile generalization","author":"Huang","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2026.100333"},{"key":"ref31","first-page":"3766","article-title":"Transferable tactile transformers for representation learning across diverse sensors and tasks","volume-title":"Proc. 8th Annu. Conf. Robot Learn, Proc. Mach. Learn. Res.","volume":"270","author":"Zhao","year":"2025"},{"key":"ref32","first-page":"885","article-title":"Sparsh: Self-supervised touch representations for vision-based tactile sensing","volume-title":"Proc. 8th Annu. Conf. Robot Learn, Proc. Mach. Learn. Res.","volume":"270","author":"Higuera","year":"2025"},{"key":"ref33","article-title":"Learning unified static-dynamic representation across multiple visuo-tactile sensors","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Feng","year":"2025"},{"key":"ref34","article-title":"GelSight Mini Tactile Sensor","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977257"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3376574"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161150"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.066"},{"key":"ref39","first-page":"14080","article-title":"A touch, vision, and language dataset for multimodal alignment","volume-title":"Proc. 41st Int. Conf. Mach. Learn, Proc. Mach. Learn. Res.","volume":"235","author":"Fu","year":"2024"},{"key":"ref40","first-page":"2557","article-title":"3D ViTac: Learning fine-grained manipulation with visuo-tactile sensing","volume-title":"Proc. Robot.: Conf. Robot Learn, in Proc. Mach. Learn. Res.","volume":"270","author":"Huang","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.052"},{"key":"ref42","article-title":"uskin patch - tactile sensor","author":"Robotics","year":"2024"},{"key":"ref43","article-title":"TAC-02 Robotic Finger Development Kit","year":"2024"},{"key":"ref44","article-title":"Rdt-1b: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.122"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11515075.pdf?arnumber=11515075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:44:26Z","timestamp":1781293466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":45,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3692345","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}