{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T20:59:49Z","timestamp":1789073989523,"version":"build-2803163510"},"reference-count":35,"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\/icra57147.2024.10610356","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"4781-4787","source":"Crossref","is-referenced-by-count":16,"title":["SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Network"],"prefix":"10.1109","author":[{"given":"Xingyu","family":"Lin","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"So","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sashwat","family":"Mahalingam","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangchen","family":"Liu","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep vit features as dense visual descriptors","author":"Amir","year":"2022","journal-title":"ECCV Workshop on What is Motion For?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref5","article-title":"Vision transformer adapter for dense predictions","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref6","article-title":"Genaug: Retargeting behaviors to unseen situations via generative augmentation","author":"Chen","year":"2023","journal-title":"Robotics: Science and Systems (RSS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-0826-5_3"},{"key":"ref8","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"European Conference on Computer Vision (ECCV)","author":"Damen"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","first-page":"21271","article-title":"Boot-strap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"One-shot transfer of affordance regions? affcorrs!","volume-title":"Conference on Robot Learning (CoRL)","author":"Hadjivelichkov"},{"key":"ref14","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","author":"Hansen","year":"2023","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning (ICML)","author":"Houlsby"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref21","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ma"},{"key":"ref22","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref23","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Nair"},{"key":"ref24","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref25","article-title":"The unsurprising effectiveness of pretrained vision models for control","volume-title":"International Conference on Machine Learning (ICML)","author":"Parisi"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref27","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning (CoRL)","author":"Radosavovic"},{"key":"ref28","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref29","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref30","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref32","article-title":"Rrl: Resnet as representation for reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Shah"},{"key":"ref33","article-title":"Lossless adaptation of pre-trained vision models for robotic manipulation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Sharma"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref35","article-title":"What makes representation learning from videos hard for control?","volume-title":"RSS 2022 Workshop on Scaling Robot Learning","author":"Zhao"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"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\/10610356.pdf?arnumber=10610356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:48:03Z","timestamp":1723268883000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610356","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}