{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T07:05:20Z","timestamp":1790665520725,"version":"4.1.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":203,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["AI Open"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.aiopen.2026.07.002","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:57:32Z","timestamp":1786697852000},"page":"208-226","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["WorldArena: A unified benchmark for evaluating perception and functional utility of embodied world models"],"prefix":"10.1016","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9049-8483","authenticated-orcid":false,"given":"Yu","family":"Shang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5813-4537","authenticated-orcid":false,"given":"Zhuohang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiding","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1435-1604","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinzhou","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4228-7439","authenticated-orcid":false,"given":"Haisheng","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1831-9952","authenticated-orcid":false,"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-5066","authenticated-orcid":false,"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aiopen.2026.07.002_b1","series-title":"V-jepa 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b2","series-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b3","series-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b4","series-title":"V-jepa: Latent video prediction for visual representation learning","author":"Bardes","year":"2023"},{"key":"10.1016\/j.aiopen.2026.07.002_b5","series-title":"Sam 3: Segment anything with concepts","author":"Carion","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A., 2021. Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10.1016\/j.aiopen.2026.07.002_b7","series-title":"Robotwin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation","author":"Chen","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b8","series-title":"Wow: Towards a world omniscient world model through embodied interaction","author":"Chi","year":"2025"},{"issue":"3","key":"10.1016\/j.aiopen.2026.07.002_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3746449","article-title":"Understanding world or predicting future? a comprehensive survey of world models","volume":"58","author":"Ding","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.aiopen.2026.07.002_b10","series-title":"Worldscore: A unified evaluation benchmark for world generation","author":"Duan","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b11","series-title":"Wow, wo, val! A comprehensive embodied world model evaluation turing test","author":"Fan","year":"2026"},{"key":"10.1016\/j.aiopen.2026.07.002_b12","series-title":"Vidar: Embodied video diffusion model for generalist manipulation","author":"Feng","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b13","doi-asserted-by":"crossref","unstructured":"Gu, J., 2025. Cosmos World Foundation Models for Physical AI. In: Proceedings of the 3rd International Workshop on Rich Media with Generative AI. pp. 39\u201339.","DOI":"10.1145\/3746262.3761969"},{"key":"10.1016\/j.aiopen.2026.07.002_b14","series-title":"Ctrl-world: A controllable generative world model for robot manipulation","author":"Guo","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b15","first-page":"1","article-title":"Mastering diverse control tasks through world models","author":"Hafner","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.aiopen.2026.07.002_b16","series-title":"Video prediction policy: A generalist robot policy with predictive visual representations","author":"Hu","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b17","series-title":"Enerverse: Envisioning embodied future space for robotics manipulation","author":"Huang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b18","doi-asserted-by":"crossref","unstructured":"Huang, Z., He, Y., Yu, J., Zhang, F., Si, C., Jiang, Y., Zhang, Y., Wu, T., Jin, Q., Chanpaisit, N., et al., 2024. Vbench: Comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21807\u201321818.","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"10.1016\/j.aiopen.2026.07.002_b19","series-title":"\u03c00.5: A vision-language-action model with open-world generalization","author":"Intelligence","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b20","series-title":"DreamGen: Unlocking generalization in robot learning through video world models","author":"Jang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b21","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F., 2021. Musiq: Multi-scale image quality transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 5148\u20135157.","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"10.1016\/j.aiopen.2026.07.002_b22","series-title":"3D and 4d world modeling: A survey","author":"Kong","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b23","series-title":"Aesthetic predictor","author":"LAION-AI","year":"2022"},{"key":"10.1016\/j.aiopen.2026.07.002_b24","series-title":"Worldmodelbench: Judging video generation models as world models","author":"Li","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b25","series-title":"WorldEval: World model as real-world robot policies evaluator","author":"Li","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b26","series-title":"WorldLens: Full-spectrum evaluations of driving world models in real world","author":"Liang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b27","series-title":"Genie envisioner: A unified world foundation platform for robotic manipulation","author":"Liao","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b28","series-title":"JEPA-reasoner: Decoupling latent reasoning from token generation","author":"Liu","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b29","series-title":"Evalcrafter: Benchmarking and evaluating large video generation models","author":"Liu","year":"2023"},{"key":"10.1016\/j.aiopen.2026.07.002_b30","doi-asserted-by":"crossref","first-page":"44776","DOI":"10.52202\/075280-1939","article-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aiopen.2026.07.002_b31","series-title":"A survey: Learning embodied intelligence from physical simulators and world models","author":"Long","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b32","series-title":"4DWorldBench: A comprehensive evaluation framework for 3D\/4D world generation models","author":"Lu","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b33","series-title":"Beyond FVD: Enhanced evaluation metrics for video generation quality","author":"Luo","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b34","series-title":"Information retrieval for music and motion","author":"M\u00fcller","year":"2007"},{"key":"10.1016\/j.aiopen.2026.07.002_b35","series-title":"Wristworld: Generating wrist-views via 4d world models for robotic manipulation","author":"Qian","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b36","series-title":"Worldsimbench: Towards video generation models as world simulators","author":"Qin","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b37","series-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.aiopen.2026.07.002_b38","series-title":"A survey of embodied world models","author":"Shang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b39","series-title":"RoboScape: Physics-informed embodied world model","author":"Shang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b40","series-title":"Gigaworld-0: World models as data engine to empower embodied ai","author":"Team","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b41","series-title":"European Conference on Computer Vision","first-page":"402","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.aiopen.2026.07.002_b42","series-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b43","series-title":"Depth anything V2","author":"Yang","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b44","series-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b45","series-title":"Ewmbench: Evaluating scene, motion, and semantic quality in embodied world models","author":"Yue","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b46","series-title":"World-in-world: World models in a closed-loop world","author":"Zhang","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b47","series-title":"VFIMamba: Video frame interpolation with state space models","author":"Zhang","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b48","series-title":"TesserAct: learning 4D embodied world models","author":"Zhen","year":"2025"},{"key":"10.1016\/j.aiopen.2026.07.002_b49","series-title":"Is sora a world simulator? A comprehensive survey on general world models and beyond","author":"Zhu","year":"2024"},{"key":"10.1016\/j.aiopen.2026.07.002_b50","doi-asserted-by":"crossref","unstructured":"Zhu, F., Wu, H., Guo, S., Liu, Y., Cheang, C., Kong, T., 2025. Irasim: A fine-grained world model for robot manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9834\u20139844.","DOI":"10.1109\/ICCV51701.2025.00917"}],"container-title":["AI Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666651026000136?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666651026000136?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T11:58:08Z","timestamp":1786708688000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666651026000136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"alternative-id":["S2666651026000136"],"URL":"https:\/\/doi.org\/10.1016\/j.aiopen.2026.07.002","relation":{},"ISSN":["2666-6510"],"issn-type":[{"value":"2666-6510","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"WorldArena: A unified benchmark for evaluating perception and functional utility of embodied world models","name":"articletitle","label":"Article Title"},{"value":"AI Open","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aiopen.2026.07.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd.","name":"copyright","label":"Copyright"}]}}