{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:14:39Z","timestamp":1792786479948,"version":"4.5.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"funder":[{"name":"National Eye Institute","award":["R01EY037193"],"award-info":[{"award-number":["R01EY037193"]}],"id":[{"id":"https:\/\/ror.org\/03wkg3b53","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/cvprf71909.2026.00930","type":"proceedings-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:19:30Z","timestamp":1791487170000},"page":"9717-9726","source":"Crossref","is-referenced-by-count":0,"title":["UnrealSpace: Analyzing Spatial Understanding and Reasoning in Controllable Simulation"],"prefix":"10.1109","author":[{"given":"Wufei","family":"Ma","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sky","family":"Cen","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianzhi","family":"Shen","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rex","family":"Lee","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le\u00f3n","family":"Begiristain","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Peng","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifei","family":"Yu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianao","family":"Song","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Qi","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianmin","family":"Shu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Kortylewski","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gemini robotics 1.5: Pushing the frontier of generalist robots with advanced embodied reasoning, thinking, and motion transfer","author":"Abdolmaleki","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","article-title":"Pursuing minimal sufficiency in spatial reasoning","volume-title":"Submitted to The Fourteenth International Conference on Learning Representations","year":"2025"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","article-title":"4dnex: Feed-forward 4d generative modeling made easy","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref12","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","article-title":"Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","author":"Ma","year":"2025","journal-title":"LychSim: Analyzing vision systems in controllable and interactive simulation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_29"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3046"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00651"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4703"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01608"},{"key":"ref22","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Indoor segmentation and support inference from rgbd images","volume-title":"ECCV","author":"Kohli","year":"2012"},{"key":"ref24","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Spacer: Reinforcing mllms in video spatial reasoning","author":"Ouyang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2565"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129396"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref30","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Sat: Dynamic spatial aptitude training for multimodal language models","author":"Ray","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","author":"Ren","year":"2024","journal-title":"Dino-x: A unified vision model for open-world object detection and understanding"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2771"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2560"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02297"},{"key":"ref40","author":"Wang","year":"2024","journal-title":"Orient anything: Learning robust object orientation estimation from rendering 3d models"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4797"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836101"},{"key":"ref43","article-title":"Multi-spatialmllm: Multi-frame spatial understanding with multi-modal large language models","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref47","article-title":"Mmsi-bench: A benchmark for multi-image spatial intelligence","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","author":"Yi","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref49","article-title":"Spatial mental modeling from limited views","volume-title":"Structural Priors for Vision Workshop at ICCV\u201925","author":"Yin","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.acl-long.1910"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01153"}],"event":{"name":"2026 IEEE\/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","location":"Denver, CO, USA","start":{"date-parts":[[2026,6,3]]},"end":{"date-parts":[[2026,6,7]]}},"container-title":["2026 IEEE\/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11697600\/11697601\/11697800.pdf?arnumber=11697800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T19:07:40Z","timestamp":1792696060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11697800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cvprf71909.2026.00930","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}