{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:31:32Z","timestamp":1773376292010,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["24-41-02039"],"award-info":[{"award-number":["24-41-02039"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["24-41-02039"],"award-info":[{"award-number":["24-41-02039"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794528","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"918-922","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HumanoidVLM: Vision-Language-Guided Impedance Control for Contact-Rich Humanoid Manipulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5104-682X","authenticated-orcid":false,"given":"Yara","family":"Mahmoud","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3610-2452","authenticated-orcid":false,"given":"Yasheerah","family":"Yaqoot","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-9257","authenticated-orcid":false,"given":"Miguel","family":"Altamirano Cabrera","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8055-5345","authenticated-orcid":false,"given":"Dzmitry","family":"Tsetserukou","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2025. Molmo-7B-O BnB 4bit quantized 7GB. https:\/\/huggingface.co\/cyan2k\/molmo-7B-O-bnb-4bit"},{"key":"e_1_3_2_2_2_1","unstructured":"2025. Sentence Transformer: all-MiniLM-L6-v2. https:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L6-v2"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.590681"},{"key":"e_1_3_2_2_4_1","first-page":"205","volume-title":"Proc. of the Conf. on Robot Learning","author":"Ahn Michael","year":"2023","unstructured":"Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Chuyuan Fu, Keerthana Gopalakrishnan, Karol Hausman, et al. 2023. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. Proc. of the Conf. on Robot Learning, 205 (2023)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9677-2"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In Advances in Neural Information Processing Systems S. Koyejo S. Mohamed A. Agarwal D. Belgrave K. Cho and A. Oh (Eds.). 35 Curran Associates Inc. 23716\u201323736.","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247031"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Joseph Dabis Chelsea Finn et al. 2023. RT-1: Robotics Transformer for Real-World Control at Scale. arxiv:2212.06817. Retrieved from https:\/\/arxiv.org\/abs\/2212.06817","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/smc54092.2024.10831380"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140702"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14198868"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-75715-4"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251390579"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ichr.2008.4755981"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO66223.2025.11377956"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Heng Zhang Wei-Hsing Huang Gokhan Solak and Arash Ajoudani. 2025. OmniVIC: A Self-Improving Variable Impedance Controller with Vision\u2013Language In-Context Learning for Safe Robotic Manipulation. https:\/\/doi.org\/10.48550\/arXiv.2510.17150 Retrieved from https:\/\/arxiv.org\/abs\/2510.17150 10.48550\/arXiv.2510.17150","DOI":"10.48550\/arXiv.2510.17150"},{"key":"e_1_3_2_2_19_1","first-page":"229","volume-title":"Proc. of the 7th Conf.on Robot Learning","author":"Zitkovich Brianna","year":"2023","unstructured":"Brianna Zitkovich, Tianhe Yu, Sichun Xu, Peng Xu, Ted Xiao, Fei Xia, Jialin Wu, Paul Wohlhart, Stefan Welker, Ayzaan Wahid, et al. 2023. RT-2: Vision\u2013Language\u2013Action Models Transfer Web Knowledge to Robotic Control. Proc. of the 7th Conf.on Robot Learning, 229 (2023), 2165\u20132183."}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Companion Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:08:01Z","timestamp":1773346081000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":19,"alternative-id":["10.1145\/3776734.3794528","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794528","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}