{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T15:38:35Z","timestamp":1793288315224,"version":"4.5.0"},"reference-count":102,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00865","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9263-9274","source":"Crossref","is-referenced-by-count":8,"title":["GWM: Towards Scalable Gaussian World Models for Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Guanxing","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxiong","family":"Jia","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Puhao","family":"Li","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"BIGAI,State Key Laboratory of General Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref3","author":"Authors","year":"2024","journal-title":"Genesis: A universal and generative physics engine for robotics and beyond"},{"key":"ref4","article-title":"Videophy: Evaluating physical commonsense for video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint arXiv:2406.03520"},{"key":"ref5","article-title":"A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint arXiv:2410.24164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01840"},{"key":"ref7","article-title":"Polarnet: 3d point clouds for language-guided robotic manipulation","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2309.15596"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref10","article-title":"Acdc: Automated creation of digital cousins for robust policy learning","volume-title":"8th Annual Conference on Robot Learning","author":"Dai","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00148991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3400227"},{"key":"ref15","first-page":"3949","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Gervet","year":"2023"},{"key":"ref16","article-title":"Rvt: Robotic view transformer for 3d object manipulation","author":"Goyal","year":"2023","journal-title":"arXiv preprint arXiv:2306.14896"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref18","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Ha","year":"2018"},{"key":"ref19","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv preprint arXiv:1912.01603"},{"key":"ref20","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020","journal-title":"arXiv preprint arXiv:2010.02193"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1892"},{"key":"ref22","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv preprint arXiv:2301.04104"},{"key":"ref23","article-title":"Td-mpc2: Scalable, robust world models for continuous control","author":"Hansen","year":"2023","journal-title":"arXiv preprint arXiv:2310.16828"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1505"},{"key":"ref27","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv:2309.17080"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"issue":"4","key":"ref30","article-title":"Estimation of nonnormalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref31","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Janner","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref36","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv:2406.09246"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801835"},{"key":"ref39","article-title":"Controlvla: Few-shot object-centric adaptation for pre-trained vision-languageaction models","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv:2506.16211"},{"key":"ref40","article-title":"Evaluating real-world robot manipulation policies in simulation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2405.05941"},{"key":"ref41","first-page":"112","article-title":"3d neural scene representations for visuomotor control","volume-title":"Conference on Robot Learning (CoRL)","author":"Li","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811651"},{"key":"ref43","first-page":"1916","article-title":"Mira: Mental imagery for robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Lin","year":"2023"},{"key":"ref44","article-title":"Voxact-b: Voxel-based acting and stabilizing policy for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2407.04152"},{"key":"ref45","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2410.07864"},{"key":"ref46","article-title":"Endogaussian: Gaussian splatting for deformable surgical scene reconstruction","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2401.12561"},{"key":"ref47","article-title":"Building interactable replicas of complex articulated objects via gaussian splatting","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Liu","year":"2025"},{"key":"ref48","article-title":"Robo-gs: A physics consistent spatialtemporal model for robotic arm with hybrid representation","author":"Lou","year":"2024","journal-title":"arXiv preprint arXiv:2408.14873"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01266"},{"key":"ref51","article-title":"Dreamart: Generating interactable articulated objects from a single image","author":"Lu","year":"2025","journal-title":"arXiv preprint arXiv:2507.05763"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"key":"ref54","article-title":"Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv:2410.21845"},{"key":"ref55","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","author":"Mandlekar","year":"2023","journal-title":"arXiv preprint arXiv:2310.17596"},{"key":"ref56","article-title":"Transformers are sample-efficient world models","volume-title":"International Conference on Learning Representations","author":"Micheli","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02575"},{"key":"ref59","article-title":"Robocasa: Large-scale simulation of everyday tasks for generalist robots","author":"Nasiriany","year":"2024","journal-title":"arXiv preprint arXiv:2406.02523"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610710"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128339"},{"key":"ref64","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref65","article-title":"Transformer-based world models are happy with 100k interactions","volume-title":"International Conference on Learning Representations","author":"Robine","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref67","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Conference on Robot Learning (CoRL)","author":"Seo","year":"2023"},{"key":"ref68","article-title":"Snerl: Semantic-aware neural radiance fields for reinforcement learning","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Shim","year":"2023"},{"key":"ref69","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Shridhar","year":"2023"},{"key":"ref70","article-title":"Splatt3r: Zero-shot gaussian splatting from uncalibarated image pairs","author":"Smart","year":"2024","journal-title":"arXiv preprint arXiv:2408.13912"},{"key":"ref71","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref72","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref74","article-title":"Splatter image: Ultra-fast single-view 3d reconstruction","author":"Szymanowicz","year":"2023","journal-title":"arXiv preprint arXiv:2312.13150"},{"key":"ref75","article-title":"Octo: An open-source generalist robot policy","author":"Model Team","year":"2024","journal-title":"arXiv preprint arXiv:2405.12213"},{"key":"ref76","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint arXiv:1812.01717"},{"key":"ref77","article-title":"Attention is all you need","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref78","article-title":"Gensim: Generating robotic simulation tasks via large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2310.01361"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref82","first-page":"68082","article-title":"ivideogpt: Interactive videogpts are scalable world models","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","volume":"37","author":"Wu","year":"2025"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"ref85","article-title":"Agg: Amortized generative 3d gaussians for single image to 3d","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv:2401.04099"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref87","article-title":"Learning interactive real-world simulators","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2310.06114"},{"key":"ref88","article-title":"Mastering visual continuous control: Improved dataaugmented reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Yarats","year":"2022"},{"key":"ref89","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","volume":"34","author":"Ye","year":"2021"},{"key":"ref90","first-page":"1094","article-title":"Metaworld: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu","year":"2020"},{"key":"ref91","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning (CoRL)","author":"Ze","year":"2023"},{"key":"ref92","article-title":"Root mean square layer normalization","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","volume":"32","author":"Zhang","year":"2019"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref94","article-title":"Gaussiancube: Structuring gaussian splatting using optimal transport for 3d generative modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2403.19655"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1182"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01861"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref100","article-title":"Point cloud matters: Rethinking the impact of different observation spaces on robot learning","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhu","year":"2025"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00983"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00635"}],"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\/11448986.pdf?arnumber=11448986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:19Z","timestamp":1777612879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11448986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00865","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}