{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:50Z","timestamp":1777889150204,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62302246,62250062"],"award-info":[{"award-number":["62302246,62250062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00250","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2599-2608","source":"Crossref","is-referenced-by-count":0,"title":["Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qi","family":"Wang","sequence":"first","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baao","family":"Xie","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbo","family":"Wang","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liaomo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01447"},{"key":"ref5","author":"Clevert","year":"2015","journal-title":"Fast and accurate deep network learning by exponential linear units (elus)"},{"key":"ref6","article-title":"Conditional mutual information for disentangled representations in reinforcement learning","author":"Dunion","year":"2023","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Temporal disentanglement of representations for improved generalisation in reinforcement learning","author":"Dunion","year":"2023","journal-title":"ICLR"},{"key":"ref8","article-title":"Learning latent dynamics for planning from pixels","author":"Hafner","year":"2019","journal-title":"ICML"},{"key":"ref9","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2020","journal-title":"ICLR"},{"key":"ref10","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2021","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08744-2"},{"key":"ref13","article-title":"Td-mpc2: Scalable, robust world models for continuous control","author":"Hansen","year":"2024","journal-title":"ICLR"},{"key":"ref14","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2017","journal-title":"ICLR"},{"key":"ref15","article-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"Higgins","year":"2017","journal-title":"ICML"},{"key":"ref16","article-title":"Leveraging separated world model for exploration in visually distracted environments","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Reinforcement learning with augmented data","author":"Laskin","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref19","article-title":"Generalizing consistency policy to visual rl with prioritized proximal experience regularization","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Open-world reinforcement learning over long short-term imagination","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref21","article-title":"Learning to model the world with language","author":"Lin","year":"2024","journal-title":"ICML"},{"key":"ref22","article-title":"Structured state space models for in-context reinforcement learning","author":"Lu","year":"2023","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Harmonydream: Task harmonization inside world models","author":"Ma","year":"2024","journal-title":"ICML"},{"key":"ref24","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2023","journal-title":"ICLR"},{"key":"ref25","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref26","article-title":"Choreographer: Learning and adapting skills in imagination","author":"Mazzaglia","year":"2023","journal-title":"ICLR"},{"key":"ref27","article-title":"Genrl: Multimodalfoundation world models for generalization in embodied agents","author":"Mazzaglia","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1684"},{"key":"ref29","article-title":"Reinforcement learning with action-free pretraining from videos","author":"Seo","year":"2022","journal-title":"ICML"},{"key":"ref30","article-title":"Multi-view masked world models for visual robotic manipulation","author":"Seo","year":"2023","journal-title":"ICML"},{"key":"ref31","first-page":"121790","article-title":"A simple framework for generalization in visual rl under dynamic scene perturbations","volume":"37","author":"Song","year":"2024","journal-title":"NeurIPS"},{"key":"ref32","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","author":"Stooke","year":"2021","journal-title":"ICML"},{"key":"ref33","article-title":"Transfer rl across observation feature spaces via model-based regularization","author":"Sun","year":"2022","journal-title":"ICLR"},{"key":"ref34","author":"Tassa","year":"2018","journal-title":"Deepmind control suite"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","article-title":"Making offline rl online: Collaborative world models for offline visual reinforcement learning","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00661"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"ref39","article-title":"Pre-training contextualized world models with in-the-wild videos for reinforcement learning","author":"Wu","year":"2023","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01649"},{"key":"ref41","article-title":"Graph-based unsupervised disentangled representation learning via multimodal large language models","author":"Xie","year":"2024","journal-title":"NeurIPS"},{"key":"ref42","article-title":"Mastering visual continuous control: Improved dataaugmented reinforcement learning","author":"Yarats","year":"2022","journal-title":"ICLR"},{"key":"ref43","article-title":"Metaworld: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2019","journal-title":"CoRL"},{"key":"ref44","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"Zhang","year":"2021","journal-title":"ICLR"},{"key":"ref45","article-title":"Prelar: World model pre-training with learnable action representation","author":"Zhang","year":"2024","journal-title":"ECCV"},{"key":"ref46","article-title":"Storm: Efficient stochastic transformer based world models for reinforcement learning","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref47","article-title":"Taco: Temporal latent action-driven contrastive loss for visual reinforcement learning","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443598.pdf?arnumber=11443598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:47Z","timestamp":1777612127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00250","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}