{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:33:44Z","timestamp":1773376424763,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"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"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794510","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"823-827","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evolution 6.0: Robot Evolution through Generative Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1112-0280","authenticated-orcid":false,"given":"Muhammad Haris","family":"Khan","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7449-7114","authenticated-orcid":false,"given":"Artyom","family":"Myshlyaev","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-2366","authenticated-orcid":false,"given":"Artem","family":"Lykov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_2_1","unstructured":"Suneel Belkhale and Dorsa Sadigh. 2024. MiniVLA: A Better VLA with a Smaller Footprint. https:\/\/github.com\/Stanford-ILIAD\/openvla-mini"},{"key":"e_1_3_2_1_3_1","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Xi Chen Krzysztof Choromanski Tianli Ding Danny Driess Avinava Dubey Chelsea Finn et al. 2023. Rt-2: Vision-language-action models transfer web knowledge to robotic control. arxiv:arXiv:2307.15818.. Retrieved from https:\/\/arxiv.org\/abs\/2307.15818"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Joseph Dabis Chelsea Finn Keerthana Gopalakrishnan Karol Hausman Alex Herzog Jasmine Hsu et al. 2022. Rt-1: Robotics transformer for real-world control at scale. arxiv:arXiv:2212.06817.. Retrieved from https:\/\/arxiv.org\/abs\/2212.06817","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"e_1_3_2_1_6_1","volume-title":"Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al.","author":"Deitke Matt","year":"2024","unstructured":"Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al. 2024. Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models. arxiv:arXiv:2409.17146.. Retrieved from https:\/\/arxiv.org\/abs\/2409.17146"},{"key":"e_1_3_2_1_7_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. 2023. Palm-e: An embodied multimodal language model. arxiv:arXiv:2303.03378.. Retrieved from https:\/\/arxiv.org\/abs\/2303.03378."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of the 36th Int. Conf. on Neural Information Processing Systems (NIPS \u201922)","author":"Fu Rao","year":"2022","unstructured":"Rao Fu, Xiao Zhan, Yiwen Chen, Daniel Ritchie, and Srinath Sridhar. 2022. ShapeCrafter: a recursive text-conditioned 3D shape generation model. In Proc. of the 36th Int. Conf. on Neural Information Processing Systems (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA. Article 646, 14 pages. isbn:9781713871088"},{"key":"e_1_3_2_1_9_1","volume-title":"Ali Alabbas, Oussama Alyunes, Artem Lykov, and Dzmitry Tsetserukou.","author":"Gbagbe Koffivi Fid\u00e8le","year":"2024","unstructured":"Koffivi Fid\u00e8le Gbagbe, Miguel Altamirano Cabrera, Ali Alabbas, Oussama Alyunes, Artem Lykov, and Dzmitry Tsetserukou. 2024. Bi-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Dexterous Manipulations. arxiv:arXiv:2405.06039.. Retrieved from https:\/\/arxiv.org\/abs\/2405.06039"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_1_11_1","volume-title":"Luis Moreno, Issatay Tokmurziyev, and Dzmitry Tsetserukou.","author":"Khan Muhamamd Haris","year":"2025","unstructured":"Muhamamd Haris Khan, Selamawit Asfaw, Dmitrii Iarchuk, Miguel Altamirano Cabrera, Luis Moreno, Issatay Tokmurziyev, and Dzmitry Tsetserukou. 2025. Shake-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Manipulations and Liquid Mixing. arxiv:arXiv:2501.06919.. Retrieved from https:\/\/arxiv.org\/abs\/2501.06919"},{"key":"e_1_3_2_1_12_1","unstructured":"Moo Jin Kim Karl Pertsch Siddharth Karamcheti Ted Xiao Ashwin Balakrishna Suraj Nair Rafael Rafailov Ethan Foster Grace Lam Pannag Sanketi et al. 2024. OpenVLA: An Open-Source Vision-Language-Action Model. arxiv:2406.09246.. Retrieved from https:\/\/arxiv.org\/abs\/2406.09246"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. of the 40th Int. Conf. on Machine Learning (ICML\u201923)","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In Proc. of the 40th Int. Conf. on Machine Learning (ICML\u201923). JMLR.org, Article 814, 13 pages."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"e_1_3_2_1_16_1","volume-title":"Mikhail Konenkov, Valerii Serpiva, Koffivi Fid\u2018ele Gbagbe, Ali Alabbas, Aleksey Fedoseev, Luis Moreno, Muhammad Haris Khan, Ziang Guo, and Dzmitry Tsetserukou.","author":"Lykov Artem","year":"2024","unstructured":"Artem Lykov, Miguel Altamirano Cabrera, Mikhail Konenkov, Valerii Serpiva, Koffivi Fid\u2018ele Gbagbe, Ali Alabbas, Aleksey Fedoseev, Luis Moreno, Muhammad Haris Khan, Ziang Guo, and Dzmitry Tsetserukou. 2024. Industry 6.0: New Generation of Industry driven by Generative AI and Swarm of Heterogeneous Robots. arxiv:arXiv:2409.10106.. Retrieved from https:\/\/arxiv.org\/abs\/2409.10106"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128224"},{"key":"e_1_3_2_1_18_1","unstructured":"Abby O\u2019Neill Abdul Rehman Abhinav Gupta Abhiram Maddukuri Abhishek Gupta Abhishek Padalkar Abraham Lee Acorn Pooley Agrim Gupta Ajay Mandlekar et al. 2023. Open x-embodiment: Robotic learning datasets and rt-x models. arxiv:2310.08864.. Retrieved from https:\/\/arxiv.org\/abs\/2310.08864"},{"key":"e_1_3_2_1_19_1","unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arxiv:arXiv:2303.08774.. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.1760520"},{"key":"e_1_3_2_1_21_1","unstructured":"Zhiliang Peng Wenhui Wang Li Dong Yaru Hao Shaohan Huang Shuming Ma and Furu Wei. 2023. Kosmos-2: Grounding multimodal large language models to the world. arxiv:2306.14824.. Retrieved from arxiv:2306.14824"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"e_1_3_2_1_23_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Yang Fan Kai Dang Mengfei Du Xuancheng Ren Rui Men Dayiheng Liu Chang Zhou Jingren Zhou and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution. arxiv:2409.12191.. Retrieved from https:\/\/arxiv.org\/abs\/2409.12191"},{"key":"e_1_3_2_1_24_1","unstructured":"Zhengyi Wang Jonathan Lorraine Yikai Wang Hang Su Jun Zhu Sanja Fidler and Xiaohui Zeng. 2024. LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models. arxiv:2411.09595.. Retrieved from https:\/\/arxiv.org\/abs\/2411.0959"},{"key":"e_1_3_2_1_25_1","unstructured":"Zhiyuan Xu Kun Wu Junjie Wen Jinming Li Ning Liu Zhengping Che and Jian Tang. 2024. A Survey on Robotics with Foundation Models: toward Embodied AI. arxiv:2402.02385.. Retrieved from https:\/\/arxiv.org\/abs\/2402.02385."},{"key":"e_1_3_2_1_26_1","unstructured":"Xin Yu Yuan-Chen Guo Yangguang Li Ding Liang Song-Hai Zhang and Xiaojuan Qi. 2023. Text-to-3D with Classifier Score Distillation. arxiv:2310.19415.. Retrieved from https:\/\/arxiv.org\/abs\/2310.19415"}],"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":"2026-03-12T20:14:10Z","timestamp":1773346450000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":26,"alternative-id":["10.1145\/3776734.3794510","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794510","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"}}]}}