{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:27:25Z","timestamp":1766068045632,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611597","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"6920-6927","source":"Crossref","is-referenced-by-count":6,"title":["SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention"],"prefix":"10.1109","author":[{"given":"Isabel","family":"Leal","sequence":"first","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Krzysztof","family":"Choromanski","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Deepali","family":"Jain","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Avinava","family":"Dubey","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Jake","family":"Varley","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Michael","family":"Ryoo","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Frederick","family":"Liu","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Vikas","family":"Sindhwani","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Quan","family":"Vuong","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Tamas","family":"Sarlos","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Ken","family":"Oslund","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Karol","family":"Hausman","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]},{"given":"Kanishka","family":"Rao","sequence":"additional","affiliation":[{"name":"Google,Mountain View,CA,94043"}]}],"member":"263","reference":[{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","article-title":"Palm: Scaling language modeling with pathways","volume-title":"CoRR","author":"Chowdhery","year":"2022"},{"article-title":"Language models are fewshot learners","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual","author":"Brown","key":"ref5"},{"key":"ref6","article-title":"Emergent abilities of large language models","volume-title":"Trans. Mach. Learn. Res","volume":"2022","author":"Wei","year":"2022"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, ser. Proceedings of Machine Learning Research","volume":"139","author":"Radford"},{"key":"ref8","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Pali: A jointly-scaled multilingual language-image model","volume-title":"CoRR","author":"Chen","year":"2022"},{"article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Zeng","key":"ref10"},{"key":"ref11","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand, ser. Proceedings of Machine Learning Research","volume":"205","author":"Ichter"},{"key":"ref12","article-title":"Demonstrating large language models on robots","volume-title":"Robotics: Science and Systems XIX, Daegu, Republic of Korea, July 10-14, 2023","author":"Zeng","year":"2023"},{"article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","year":"2023","author":"Ren","key":"ref13"},{"key":"ref14","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand, ser. Proceedings of Machine Learning Research","volume":"205","author":"Huang"},{"key":"ref15","article-title":"Code as policies: Language model programs for embodied control","volume-title":"CoRR","author":"Liang","year":"2022"},{"key":"ref16","article-title":"Palm-e: An embodied multimodal language model","volume-title":"ICML 2023","author":"Driess","year":"2023"},{"key":"ref17","article-title":"Transformers learn in-context by gradient descent","volume-title":"CoRR","author":"von Oswald","year":"2022"},{"key":"ref18","article-title":"Transformers as statisticians: Provable in-context learning with in-context algorithm selection","volume-title":"CoRR","author":"Bai","year":"2023"},{"article-title":"Large language models as general pattern machines","year":"2023","author":"Mirchandani","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref21","article-title":"Habitatmatterport 3d dataset (HM3D): 1000 large-scale 3d environments for embodied AI","volume-title":"CoRR","author":"Ramakrishnan","year":"2021"},{"article-title":"Rethinking attention with performers","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Choromanski","key":"ref22"},{"article-title":"Random feature attention","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Peng","key":"ref23"},{"key":"ref24","article-title":"Flurka: Fast fused low-rank & kernel attention","volume-title":"CoRR","author":"Gupta","year":"2023"},{"article-title":"Efficient attention via control variates","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Zheng","key":"ref25"},{"key":"ref26","first-page":"9355","article-title":"Linear transformers are secretly fast weight programmers","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, ser. Proceedings of Machine Learning Research","volume":"139","author":"Schlag"},{"key":"ref27","first-page":"7703","article-title":"Going beyond linear transformers with recurrent fast weight programmers","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual","author":"Irie"},{"key":"ref28","article-title":"Chefs\u2019 random tables: Non-trigonometric random features","volume-title":"NeurIPS","author":"Likhosherstov","year":"2022"},{"key":"ref29","article-title":"Favor#: Sharp attention kernel approximations via new classes of positive random features","volume-title":"CoRR","author":"Likhosherstov","year":"2023"},{"article-title":"cosformer: Rethinking softmax in attention","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Qin","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"article-title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","year":"2017","author":"Salimans","key":"ref32"},{"article-title":"Simple random search provides a competitive approach to reinforcement learning","year":"2018","author":"Mania","key":"ref33"},{"article-title":"i-Sim2Real: Reinforcement learning of robotic policies in tight human-robot interaction loops","volume-title":"Conference on Robot Learning (CoRL)","author":"Abeyruwan","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.006"},{"key":"ref36","article-title":"Pali-x: On scaling up a multilingual vision and language model","volume-title":"CoRR","author":"Chen","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611597.pdf?arnumber=10611597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:33:28Z","timestamp":1755545608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611597","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}