{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:08:58Z","timestamp":1780355338299,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4505800"],"award-info":[{"award-number":["2024YFB4505800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["Z241100004224015"],"award-info":[{"award-number":["Z241100004224015"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731099","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"327-343","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Dadu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5095-418X","authenticated-orcid":false,"given":"Yiyang","family":"Huang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-5271","authenticated-orcid":false,"given":"Yuhui","family":"Hao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0139-3622","authenticated-orcid":false,"given":"Bo","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6267-9423","authenticated-orcid":false,"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3007-3705","authenticated-orcid":false,"given":"Yuxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0107-0196","authenticated-orcid":false,"given":"Feng","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5113-8067","authenticated-orcid":false,"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8172-5788","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5132-8351","authenticated-orcid":false,"given":"Shaoshan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-0508","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2532-6259","authenticated-orcid":false,"given":"Yiming","family":"Gan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.01691","author":"Ahn Michael","year":"2022","unstructured":"Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Chuyuan Fu, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario\u00a0Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Kuang-Huei Lee, Sergey Levine, Yao Lu, Linda Luu, Carolina Parada, Peter Pastor, Jornell Quiambao, Kanishka Rao, Jarek Rettinghouse, Diego Reyes, Pierre Sermanet, Nicolas Sievers, Clayton Tan, Alexander Toshev, Vincent Vanhoucke, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Mengyuan Yan, and Andy Zeng. 2022. Do As I Can and Not As I Say: Grounding Language in Robotic Affordances. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.01691."},{"key":"e_1_3_3_2_3_2","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds Roman Ring Eliza Rutherford Serkan Cabi Tengda Han Zhitao Gong Sina Samangooei Marianne Monteiro Jacob Menick Sebastian Borgeaud Andrew Brock Aida Nematzadeh Sahand Sharifzadeh Barreira Binkowski Mikolaj\u00a0Ricardo Oriol Vinyals and Andrew Zisserman. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems 35 (2022) 23716\u201323736."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"EPL Aude and JS Aude. 1991. A hardware accelerator for a robot arm multivariable self-tuning control. IFAC Proceedings Volumes 24 7 (1991) 73\u201380.","DOI":"10.1016\/B978-0-08-041699-1.50017-3"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527383"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00047"},{"key":"e_1_3_3_2_7_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.15818","author":"Brohan Anthony","year":"2023","unstructured":"Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, Pete Florence, Chuyuan Fu, Montse\u00a0Gonzalez Arenas, Keerthana Gopalakrishnan, Kehang Han, Karol Hausman, Alex Herzog, Jasmine Hsu, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Isabel Leal, Lisa Lee, Tsang-Wei\u00a0Edward Lee, Sergey Levine, Yao Lu, Henryk Michalewski, Igor Mordatch, Karl Pertsch, Kanishka Rao, Krista Reymann, Michael Ryoo, Grecia Salazar, Pannag Sanketi, Pierre Sermanet, Jaspiar Singh, Anikait Singh, Radu Soricut, Huong Tran, Vincent Vanhoucke, Quan Vuong, Ayzaan Wahid, Stefan Welker, Paul Wohlhart, Jialin Wu, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Tianhe Yu, and Brianna Zitkovich. 2023. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.15818."},{"key":"e_1_3_3_2_8_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.06817","author":"Brohan Anthony","year":"2022","unstructured":"Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Tomas Jackson, Sally Jesmonth, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Isabel Leal, Kuang-Huei Lee, Sergey Levine, Yao Lu, Utsav Malla, Deeksha Manjunath, Igor Mordatch, Ofir Nachum, Carolina Parada, Jodilyn Peralta, Emily Perez, Karl Pertsch, Jornell Quiambao, Kanishka Rao, Michael Ryoo, Grecia Salazar, Pannag Sanketi, Kevin Sayed, Jaspiar Singh, Sumedh Sontakke, Austin Stone, Clayton Tan, Huong Tran, Vincent Vanhoucke, Steve Vega, Quan Vuong, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Tianhe Yu, and Brianna Zitkovich. 2022. RT-1: Robotics Transformer for Real-World Control at Scale. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.06817."},{"key":"e_1_3_3_2_9_2","unstructured":"Chi-Lam Cheang Guangzeng Chen Ya Jing Tao Kong Hang Li Yifeng Li Yuxiao Liu Hongtao Wu Jiafeng Xu Yichu Yang Hanbo Zhang and Minzhao Zhu. 2024. GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.06158 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Ron Chrisley. 2003. Embodied artificial intelligence. Artificial intelligence 149 1 (2003) 131\u2013150.","DOI":"10.1016\/S0004-3702(03)00055-9"},{"key":"e_1_3_3_2_11_2","unstructured":"Open X-Embodiment Collaboration Abby O\u2019Neill Abdul Rehman Abhinav Gupta Abhiram Maddukuri Abhishek Gupta Abhishek Padalkar Abraham Lee Acorn Pooley Agrim Gupta Ajay Mandlekar Ajinkya Jain Albert Tung Alex Bewley Alex Herzog Alex Irpan Alexander Khazatsky Anant Rai Anchit Gupta Andrew Wang Andrey Kolobov Anikait Singh Animesh Garg Aniruddha Kembhavi Annie Xie Anthony Brohan Antonin Raffin Archit Sharma Arefeh Yavary Arhan Jain Ashwin Balakrishna Ayzaan Wahid Ben Burgess-Limerick Beomjoon Kim Bernhard Sch\u00f6lkopf Blake Wulfe Brian Ichter Cewu Lu Charles Xu Charlotte Le Chelsea Finn Chen Wang Chenfeng Xu Cheng Chi Chenguang Huang Christine Chan Christopher Agia Chuer Pan Chuyuan Fu Coline Devin Danfei Xu Daniel Morton Danny Driess Daphne Chen Deepak Pathak Dhruv Shah Dieter B\u00fcchler Dinesh Jayaraman Dmitry Kalashnikov Dorsa Sadigh Edward Johns Ethan Foster Fangchen Liu Federico Ceola Fei Xia Feiyu Zhao Felipe\u00a0Vieira Frujeri Freek Stulp Gaoyue Zhou Gaurav\u00a0S. Sukhatme Gautam Salhotra Ge Yan Gilbert Feng Giulio Schiavi Glen Berseth Gregory Kahn Guangwen Yang Guanzhi Wang Hao Su Hao-Shu Fang Haochen Shi Henghui Bao Heni\u00a0Ben Amor Henrik\u00a0I Christensen Hiroki Furuta Homanga Bharadhwaj Homer Walke Hongjie Fang Huy Ha Igor Mordatch Ilija Radosavovic Isabel Leal Jacky Liang Jad Abou-Chakra Jaehyung Kim Jaimyn Drake Jan Peters Jan Schneider Jasmine Hsu Jay Vakil Jeannette Bohg Jeffrey Bingham Jeffrey Wu Jensen Gao Jiaheng Hu Jiajun Wu Jialin Wu Jiankai Sun Jianlan Luo Jiayuan Gu Jie Tan Jihoon Oh Jimmy Wu Jingpei Lu Jingyun Yang Jitendra Malik Jo\u00e3o Silv\u00e9rio Joey Hejna Jonathan Booher Jonathan Tompson Jonathan Yang Jordi Salvador Joseph\u00a0J. Lim Junhyek Han Kaiyuan Wang Kanishka Rao Karl Pertsch Karol Hausman Keegan Go Keerthana Gopalakrishnan Ken Goldberg Kendra Byrne Kenneth Oslund Kento Kawaharazuka Kevin Black Kevin Lin Kevin Zhang Kiana Ehsani Kiran Lekkala Kirsty Ellis Krishan Rana Krishnan Srinivasan Kuan Fang Kunal\u00a0Pratap Singh Kuo-Hao Zeng Kyle Hatch Kyle Hsu Laurent Itti Lawrence\u00a0Yunliang Chen Lerrel Pinto Li Fei-Fei Liam Tan Linxi\u00a0\"Jim\" Fan Lionel Ott Lisa Lee Luca Weihs Magnum Chen Marion Lepert Marius Memmel Masayoshi Tomizuka Masha Itkina Mateo\u00a0Guaman Castro Max Spero Maximilian Du Michael Ahn Michael\u00a0C. Yip Mingtong Zhang Mingyu Ding Minho Heo Mohan\u00a0Kumar Srirama Mohit Sharma Moo\u00a0Jin Kim Naoaki Kanazawa Nicklas Hansen Nicolas Heess Nikhil\u00a0J Joshi Niko Suenderhauf Ning Liu Norman\u00a0Di Palo Nur Muhammad\u00a0Mahi Shafiullah Oier Mees Oliver Kroemer Osbert Bastani Pannag\u00a0R Sanketi Patrick\u00a0\"Tree\" Miller Patrick Yin Paul Wohlhart Peng Xu Peter\u00a0David Fagan Peter Mitrano Pierre Sermanet Pieter Abbeel Priya Sundaresan Qiuyu Chen Quan Vuong Rafael Rafailov Ran Tian Ria Doshi Roberto Mart\u2019in-Mart\u2019in Rohan Baijal Rosario Scalise Rose Hendrix Roy Lin Runjia Qian Ruohan Zhang Russell Mendonca Rutav Shah Ryan Hoque Ryan Julian Samuel Bustamante Sean Kirmani Sergey Levine Shan Lin Sherry Moore Shikhar Bahl Shivin Dass Shubham Sonawani Shubham Tulsiani Shuran Song Sichun Xu Siddhant Haldar Siddharth Karamcheti Simeon Adebola Simon Guist Soroush Nasiriany Stefan Schaal Stefan Welker Stephen Tian Subramanian Ramamoorthy Sudeep Dasari Suneel Belkhale Sungjae Park Suraj Nair Suvir Mirchandani Takayuki Osa Tanmay Gupta Tatsuya Harada Tatsuya Matsushima Ted Xiao Thomas Kollar Tianhe Yu Tianli Ding Todor Davchev Tony\u00a0Z. Zhao Travis Armstrong Trevor Darrell Trinity Chung Vidhi Jain Vikash Kumar Vincent Vanhoucke Wei Zhan Wenxuan Zhou Wolfram Burgard Xi Chen Xiangyu Chen Xiaolong Wang Xinghao Zhu Xinyang Geng Xiyuan Liu Xu Liangwei Xuanlin Li Yansong Pang Yao Lu Yecheng\u00a0Jason Ma Yejin Kim Yevgen Chebotar Yifan Zhou Yifeng Zhu Yilin Wu Ying Xu Yixuan Wang Yonatan Bisk Yongqiang Dou Yoonyoung Cho Youngwoon Lee Yuchen Cui Yue Cao Yueh-Hua Wu Yujin Tang Yuke Zhu Yunchu Zhang Yunfan Jiang Yunshuang Li Yunzhu Li Yusuke Iwasawa Yutaka Matsuo Zehan Ma Zhuo Xu Zichen\u00a0Jeff Cui Zichen Zhang Zipeng Fu and Zipeng Lin. 2023. Open X-Embodiment: Robotic Learning Datasets and RT-X Models. https:\/\/arxiv.org\/abs\/2310.08864."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560742"},{"key":"e_1_3_3_2_13_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ArXiv abs\/2010.11929 (2020). https:\/\/api.semanticscholar.org\/CorpusID:225039882"},{"key":"e_1_3_3_2_14_2","first-page":"8469","volume-title":"International Conference on Machine Learning","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi S.\u00a0M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, and Pete Florence. 2023. PaLM-E: An Embodied Multimodal Language Model. In International Conference on Machine Learning. PMLR, 8469\u20138488."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Jiafei Duan Samson Yu Hui\u00a0Li Tan Hongyuan Zhu and Cheston Tan. 2022. A survey of embodied ai: From simulators to research tasks. IEEE Transactions on Emerging Topics in Computational Intelligence 6 2 (2022) 230\u2013244.","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/210139"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Reza Eyvazpour Maryam Shoaran and Ghader Karimian. 2023. Hardware implementation of SLAM algorithms: a survey on implementation approaches and platforms. Artificial Intelligence Review 56 7 (2023) 6187\u20136239.","DOI":"10.1007\/s10462-022-10310-5"},{"key":"e_1_3_3_2_18_2","unstructured":"Roya Firoozi Johnathan Tucker Stephen Tian Anirudha Majumdar Jiankai Sun Weiyu Liu Yuke Zhu Shuran Song Ashish Kapoor Karol Hausman Brian Ichter Danny Driess Jiajun Wu Cewu Lu and Mac Schwager. [n. d.]. Foundation models in robotics: Applications challenges and the future. The International Journal of Robotics Research ([n. d.]) 02783649241281508."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Stan Franklin. 1997. Autonomous agents as embodied AI. Cybernetics & Systems 28 6 (1997) 499\u2013520.","DOI":"10.1080\/019697297126029"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2012.6489717"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00074"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Claudio Gaz Marco Cognetti Alexander Oliva Paolo\u00a0Robuffo Giordano and Alessandro De\u00a0Luca. 2019. Dynamic identification of the franka emika panda robot with retrieval of feasible parameters using penalty-based optimization. IEEE Robotics and Automation Letters 4 4 (2019) 4147\u20134154.","DOI":"10.1109\/LRA.2019.2931248"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640379"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247780"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3561112"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9 8 (1997) 1735\u20131780.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342109"},{"key":"e_1_3_3_2_28_2","unstructured":"Yafei Hu Quanting Xie Vidhi Jain Jonathan Francis Jay Patrikar Nikhil Keetha Seungchan Kim Yaqi Xie Tianyi Zhang Hao-Shu Fang Shibo Zhao Shayegan Omidshafiei Dong-Ki Kim Ali akbar Agha-mohammadi Katia Sycara Matthew Johnson-Roberson Dhruv Batra Xiaolong Wang Sebastian Scherer Chen Wang Zsolt Kira Fei Xia and Yonatan Bisk. 2023. Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis. (2023)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Hanyao Huang Ou Zheng Dongdong Wang Jiayi Yin Zijin Wang Shengxuan Ding Heng Yin Chuan Xu Renjie Yang Qian Zheng and Bing Shi. 2023. ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model. International Journal of Oral Science 15 1 (2023) 29.","DOI":"10.1038\/s41368-023-00239-y"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00043"},{"key":"e_1_3_3_2_31_2","first-page":"540","volume-title":"Conference on Robot Learning","author":"Huang Wenlong","year":"2023","unstructured":"Wenlong Huang, Chen Wang, Ruohan Zhang, Yunzhu Li, Jiajun Wu, and Li Fei-Fei. 2023. VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models. In Conference on Robot Learning. PMLR, 540\u2013562."},{"key":"e_1_3_3_2_32_2","first-page":"4171","volume-title":"Proceedings of NAACL-HLT","author":"Kenton Jacob Devlin Ming-Wei\u00a0Chang","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Oussama Khatib. 1986. Real-time obstacle avoidance for manipulators and mobile robots. The international journal of robotics research 5 1 (1986) 90\u201398.","DOI":"10.1177\/027836498600500106"},{"key":"e_1_3_3_2_34_2","unstructured":"Moo Jin Kim Karl Pertsch Siddharth Karamcheti Ted Xiao Ashwin Balakrishna Suraj Nair Rafael Rafailov Ethan Foster Grace Lam Pannag Sanketi Quan Vuong Thomas Kollar Benjamin Burchfiel Russ Tedrake Dorsa Sadigh Sergey Levine Percy Liang and Chelsea Finn. 2024. OpenVLA: An Open-Source Vision-Language-Action Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09246 (2024)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560990"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00033"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00041"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1267\/1\/012036"},{"key":"e_1_3_3_2_39_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li Xinghang","year":"2024","unstructured":"Xinghang Li, Minghuan Liu, Hanbo Zhang, Cunjun Yu, Jie Xu, Hongtao Wu, Chilam Cheang, Ya Jing, Weinan Zhang, Huaping Liu, Hang Li, and Tao Kong. 2024. Vision-Language Foundation Models as Effective Robot Imitators. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196020"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062223"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT51103.2020.00046"},{"key":"e_1_3_3_2_44_2","unstructured":"Fanfan Liu Feng Yan Liming Zheng Chengjian Feng Yiyang Huang and Lin Ma. 2024. RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulaiton. arxiv:https:\/\/arXiv.org\/abs\/2406.18977\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2406.18977"},{"key":"e_1_3_3_2_45_2","volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Liu Peiqi","unstructured":"Peiqi Liu, Yaswanth Orru, Jay Vakil, Chris Paxton, Nur Muhammad\u00a0Mahi Shafiullah, and Lerrel Pinto. [n. d.]. OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics. In First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024."},{"key":"e_1_3_3_2_46_2","unstructured":"Qiang Liu Yuhui Hao Weizhuang Liu Bo Yu Yiming Gan Jie Tang Shao-Shan Liu and Yuhao Zhu. 2022. An energy efficient and runtime reconfigurable accelerator for robotic localization. IEEE Trans. Comput. 72 7 (2022) 1943\u20131957."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317820"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480077"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Ye Liu Jingyuan Li Kun Huang Xiangting Li Xiuyuan Qi Liang Chang Yu Long and Jun Zhou. 2022. MobileSP: An FPGA-based real-time keypoint extraction hardware accelerator for mobile VSLAM. IEEE Transactions on Circuits and Systems I: Regular Papers 69 12 (2022) 4919\u20134929.","DOI":"10.1109\/TCSI.2022.3190300"},{"key":"e_1_3_3_2_50_2","unstructured":"Chenyang Lyu Minghao Wu Longyue Wang Xinting Huang Bingshuai Liu Zefeng Du Shuming Shi and Zhaopeng Tu. 2023. Macaw-LLM: Multi-Modal Language Modeling with Image Audio Video and Text Integration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.09093 (2023)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982082"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Oier Mees Lukas Hermann Erick Rosete-Beas and Wolfram Burgard. 2022. CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks. IEEE Robotics and Automation Letters (RA-L) 7 3 (2022) 7327\u20137334.","DOI":"10.1109\/LRA.2022.3180108"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Yongguo Mei Yung-Hsiang Lu Yu\u00a0Charlie Hu and CS\u00a0George Lee. 2006. Deployment of mobile robots with energy and timing constraints. IEEE Transactions on robotics 22 3 (2006) 507\u2013522.","DOI":"10.1109\/TRO.2006.875494"},{"key":"e_1_3_3_2_54_2","unstructured":"Yao Mu Qinglong Zhang Mengkang Hu Wenhai Wang Mingyu Ding Jun Jin Bin Wang Jifeng Dai Yu Qiao and Ping Luo. 2024. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781315136370"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.000-4"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783748"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589104"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446746"},{"key":"e_1_3_3_2_60_2","volume-title":"Proceedings of Robotics: Science and Systems","author":"Team Octo Model","year":"2024","unstructured":"Octo Model Team, Dibya Ghosh, Homer Walke, Karl Pertsch, Kevin Black, Oier Mees, Sudeep Dasari, Joey Hejna, Charles Xu, Jianlan Luo, Tobias Kreiman, You Liang Tan, Lawrence\u00a0Yunliang Chen, Pannag Sanketi, Quan Vuong, Ted Xiao, Dorsa Sadigh, Chelsea Finn, and Sergey Levine. 2024. Octo: An Open-Source Generalist Robot Policy. In Proceedings of Robotics: Science and Systems. Delft, Netherlands."},{"key":"e_1_3_3_2_61_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga Alban Desmaison Andreas K\u00f6pf Edward Yang Zach DeVito Martin Raison Alykhan Tejani Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai and Soumith Chintala. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. ArXiv abs\/1912.01703 (2019). https:\/\/api.semanticscholar.org\/CorpusID:202786778"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00047"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139569"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589092"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445099"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT52863.2021.9609886"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Keisuke Sugiura and Hiroki Matsutani. 2022. A universal LiDAR SLAM accelerator system on low-cost FPGA. IEEE Access 10 (2022) 26931\u201326947.","DOI":"10.1109\/ACCESS.2022.3157822"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Amr Suleiman Zhengdong Zhang Luca Carlone Sertac Karaman and Vivienne Sze. 2019. Navion: A 2-mw fully integrated real-time visual-inertial odometry accelerator for autonomous navigation of nano drones. IEEE Journal of Solid-State Circuits 54 4 (2019) 1106\u20131119.","DOI":"10.1109\/JSSC.2018.2886342"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Sai\u00a0H Vemprala Rogerio Bonatti Arthur Bucker and Ashish Kapoor. 2024. Chatgpt for robotics: Design principles and model abilities. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"e_1_3_3_2_71_2","unstructured":"Paul von Behren. [n. d.]. NVML: Implementing Persistent Memory Applications. ([n. d.])."},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Naoki Wake Atsushi Kanehira Kazuhiro Sasabuchi Jun Takamatsu and Katsushi Ikeuchi. 2024. Gpt-4v (ision) for robotics: Multimodal task planning from human demonstration. IEEE Robotics and Automation Letters (2024).","DOI":"10.1109\/LRA.2024.3477090"},{"key":"e_1_3_3_2_73_2","volume-title":"International Conference on Learning Representations","author":"Wu Hongtao","year":"2024","unstructured":"Hongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, and Tao Kong. 2024. Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_74_2","unstructured":"Xilinx. [n. d.]. Xilinx Zynq-7000 SoC ZC706 Evaluation Kit. https:\/\/www.xilinx.com\/products\/boards-and-kits\/ek-z7-zc706-g.html. Accessed: 2024-06-1."},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614298"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00089"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Andrea\u00a0Maria Zanchettin Nicola\u00a0Maria Ceriani Paolo Rocco Hao Ding and Bj\u00f6rn Matthias. 2015. Safety in human-robot collaborative manufacturing environments: Metrics and control. IEEE Transactions on Automation Science and Engineering 13 2 (2015) 882\u2013893.","DOI":"10.1109\/TASE.2015.2412256"},{"key":"e_1_3_3_2_78_2","volume-title":"ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems","author":"Zhao Tony\u00a0Z","unstructured":"Tony\u00a0Z Zhao, Vikash Kumar, Sergey Levine, and Chelsea Finn. [n. d.]. Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware. In ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems."},{"key":"e_1_3_3_2_79_2","unstructured":"Yang Zhao Zhijie Lin Daquan Zhou Zilong Huang Jiashi Feng and Bingyi Kang. 2023. Bubogpt: Enabling visual grounding in multi-modal llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.08581 (2023)."}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:04:07Z","timestamp":1750503847000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":78,"alternative-id":["10.1145\/3695053.3731099","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731099","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}