{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:44:10Z","timestamp":1780634650268,"version":"3.54.1"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128272","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"5937-5944","source":"Crossref","is-referenced-by-count":6,"title":["ICRT: In-Context Imitation Learning via Next-Token Prediction"],"prefix":"10.1109","author":[{"given":"Max","family":"Fu","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huang","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Datta","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence Yunliang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Will","family":"Panitch","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangchen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Autodesk Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295255"},{"key":"ref4","author":"Reed","year":"2022","journal-title":"A generalist agent"},{"key":"ref5","article-title":"ViNT: A Foundation Model for Visual Navigation","volume-title":"7th Annual Conference on Robot Learning (CoRL)","author":"Shah","year":"2023"},{"key":"ref6","article-title":"RoboAgent: Towards sample efficient robot manipulation with semantic augmentations and action chunking","author":"Bharadhwaj","year":"2023","journal-title":"arxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref8","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref10","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model"},{"key":"ref11","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02157"},{"key":"ref14","author":"Kim","year":"2024","journal-title":"Openvla: An open-source vision-language-action model"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.090"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref17","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018","journal-title":"CoRL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560844"},{"key":"ref20","author":"Shafiullah","year":"2023","journal-title":"On bringing robots home"},{"key":"ref21","article-title":"RH20T: A robotic dataset for learning diverse skills in one-shot","author":"Fang","year":"2023","journal-title":"RSS 2023 Workshop on Learning for Task and Motion Planning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref23","author":"Walke","year":"2023","journal-title":"Bridgedata v2: A dataset for robot learning at scale"},{"key":"ref24","author":"Nair","year":"2022","journal-title":"R3m: A universal visual representation for robot manipulation"},{"key":"ref25","author":"Xiao","year":"2022","journal-title":"Masked visual pre-training for motor control"},{"key":"ref26","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","author":"Radosavovic","year":"2022","journal-title":"Real-world robot learning with masked visual pre-training"},{"key":"ref28","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"NeurIPS","volume":"1","author":"Pomerleau","year":"1988"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref30","article-title":"End-to-end training of deep visuomotor policies","author":"Levine","year":"2016","journal-title":"JMLR"},{"key":"ref31","article-title":"Implicit behavioral cloning","author":"Florence","year":"2021","journal-title":"CoRL"},{"key":"ref32","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Conference on Robot Learning","author":"Ha","year":"2023"},{"key":"ref33","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref35","author":"Radosavovic","year":"2023","journal-title":"Robot learning with sensorimotor pre-training"},{"key":"ref36","author":"Radosavovic","year":"2024","journal-title":"Humanoid locomotion as next token prediction"},{"key":"ref37","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref38","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"International Conference on Machine Learning (ICML)","author":"Jiang","year":"2023"},{"key":"ref39","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","author":"Collaboration","year":"2024","journal-title":"Open x-embodiment: Robotic learning datasets and rt-x models"},{"key":"ref41","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn","year":"2017"},{"key":"ref42","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","author":"Finn","year":"2017","journal-title":"Conference on robot learning, PMLR"},{"key":"ref43","article-title":"Hyper-decision transformer for efficient online policy adaptation","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.096"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812450"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981982"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.062"},{"key":"ref49","article-title":"One-shot imitation learning","volume":"30","author":"Duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref50","first-page":"24631","article-title":"Prompting decision transformer for few-shot policy generalization","volume-title":"international conference on machine learning","author":"Xu","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref52","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01709"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","article-title":"Rethinking patch dependence for masked autoencoders","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"International conference on machine learning","author":"Lee","year":"2019"},{"key":"ref58","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref59","author":"Han","year":"2023","journal-title":"Imagebind-llm: Multi-modality instruction tuning"},{"key":"ref60","article-title":"A touch, vision, and language dataset for multimodal alignment","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","author":"Mirchandani","year":"2023","journal-title":"Large language models as general pattern machines"},{"key":"ref62","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"issue":"3","key":"ref63","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref65","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128272.pdf?arnumber=11128272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:28Z","timestamp":1756879948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128272","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}