{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:35Z","timestamp":1777865495971,"version":"3.51.4"},"reference-count":84,"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\/iccv51701.2025.00847","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9058-9069","source":"Crossref","is-referenced-by-count":0,"title":["SITE: Towards Spatial Intelligence Thorough Evaluation"],"prefix":"10.1109","author":[{"given":"Wenqi","family":"Wang","sequence":"first","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reuben","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyue","family":"Zhu","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Kolobov","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Microsoft Research,Redmond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref6","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511571312"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2466\/pms.2002.94.2.479"},{"key":"ref15","volume-title":"An International Directory of Spatial Tests","author":"Eliot","year":"1983"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2013.01.010"},{"key":"ref18","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref21","volume-title":"Frames of mind: The theory of multiple intelligences","author":"Gardner","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.intell.2003.12.001"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511610448.005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.intell.2005.09.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/9780470996287.part2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.02.018"},{"key":"ref35","first-page":"2679","article-title":"Openvla: An open source vision-language-action model","volume-title":"Conference on Robot Learning (CoRL)","author":"Kim","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref38","article-title":"Seed-bench: Benchmarking multimodal llms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Lmms-eval: Accelerating the development of large multimoal models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref47","first-page":"181","article-title":"Spatial abilities as traits, processes, and knowledge","volume-title":"Advances in the Psychology of Human Intelligence","author":"Lohman","year":"1988"},{"key":"ref48","article-title":"Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning","volume-title":"The 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks","author":"Lu","year":"2021"},{"key":"ref49","article-title":"3dsrbench: A comprehensive 3d spatial reasoning benchmark","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01811"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.86.5.889"},{"key":"ref55","article-title":"Mmiu: Multimodal multi-image understanding for evaluating large vision-language models","author":"Meng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/001316445701700202"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-57207-4_21"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01261"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref60","article-title":"Sat: Spatial aptitude training for multimodal language models","author":"Ray","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","first-page":"492","article-title":"Lm nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning (CoRL)","author":"Shah","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511610448"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103557"},{"key":"ref64","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Georgiev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2771"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1037\/a0028446"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1037\/a0028446"},{"key":"ref70","article-title":"Muirbench: A comprehensive benchmark for robust multi-image understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2400"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01243"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_10"},{"key":"ref74","article-title":"Logicvista: Multimodal llm logical reasoning benchmark in visual contexts","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref77","article-title":"Mmt bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi","author":"Ying","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref80","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","volume-title":"International Conference on M achine Learning (ICML)","author":"Yu","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref82","article-title":"Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenarios that are difficult for humans?","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning (CoRL)","author":"Zitkovich","year":"2023"}],"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\/11445630.pdf?arnumber=11445630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:41:55Z","timestamp":1777531315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00847","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}