{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:28:27Z","timestamp":1768404507143,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342381","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"3621-3627","source":"Crossref","is-referenced-by-count":12,"title":["PACT: Perception-Action Causal Transformer for Autoregressive Robotics Pre-Training"],"prefix":"10.1109","author":[{"given":"Rogerio","family":"Bonatti","sequence":"first","affiliation":[{"name":"Microsoft"}]},{"given":"Sai","family":"Vemprala","sequence":"additional","affiliation":[{"name":"Scaled Foundations"}]},{"given":"Shuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Felipe","family":"Frujeri","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Shuhang","family":"Chen","sequence":"additional","affiliation":[{"name":"Scaled Foundations"}]},{"given":"Ashish","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Scaled Foundations"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","volume-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"ref10","first-page":"133","article-title":"Deep drone racing: Learning agile flight in dynamic environments","volume-title":"Conference on Robot Learning","author":"Kaufmann"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00867"},{"key":"ref12","article-title":"Learning to localize using a lidar intensity map","author":"Barsan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Generalization in dexterous manipulation via geometry-aware multi-task learning","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982241"},{"key":"ref17","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref20","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume":"34","author":"Szot","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref24","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref27","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref29","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981810"},{"key":"ref32","first-page":"1484","article-title":"Differentiable spatial planning using transformers","volume-title":"International Conference on Machine Learning","author":"Chaplot"},{"key":"ref33","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref37","article-title":"MuSHR: A low-cost, open-source robotic racecar for education and research","volume":"abs\/1908.08031","author":"Srinivasa","year":"2019","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560733"},{"key":"ref41","article-title":"Daydreamer: World models for physical robot learning","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"11784","article-title":"Representation matters: Offline pretraining for sequential decision making","volume-title":"International Conference on Machine Learning","author":"Yang"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342381.pdf?arnumber=10342381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:53:24Z","timestamp":1752774804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342381","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}