{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:28Z","timestamp":1777888768756,"version":"3.51.4"},"reference-count":52,"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":["62306046"],"award-info":[{"award-number":["62306046"]}],"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\/iccv51701.2025.00533","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5622-5632","source":"Crossref","is-referenced-by-count":0,"title":["STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?"],"prefix":"10.1109","author":[{"given":"Yun","family":"Li","sequence":"first","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Lin","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XiangRui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiao","family":"Cai","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"BAAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","year":"2025","journal-title":"Claude 3.7 Sonnet and Claude Code. Anthropic News Announcement, 2025. Announcement on Anthropic blog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref6","article-title":"Worldsense: A synthetic benchmark for grounded reasoning in large language models","author":"Benchekroun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Spatialbot: Precise spatial understanding with vision language models","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref13","author":"Chen","year":"2025","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref15","article-title":"Embodiedeval: Evaluate multimodal 11 ms as embodied agents","author":"Cheng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.33"},{"key":"ref18","article-title":"Mmbench-video: A long-form multi-shot benchmark for holistic video understanding","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","year":"2025","journal-title":"Gemini 2.5 pro preview model card"},{"key":"ref21","article-title":"Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Behavior-1k: A human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","article-title":"Embodied agent interface: Benchmarking $l l m s$ for embodied decision making","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Videochatflash: Hierarchical compression for long-context video modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Videochat-r1: Enhancing spatio-temporal perception via reinforcement fine-tuning","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref33","year":"2024","journal-title":"GPT-4o system card"},{"key":"ref34","article-title":"Sat: Spatial aptitude training for multimodal language models","author":"Ray","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02436"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref37","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Lvbench: An extreme long video understanding benchmark","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","first-page":"28828","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Vlm-ad: End-to-end autonomous driving through vision-language model supervision","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref44","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Thinking in space: How multimodal large language models see, remember, and recall spaces","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Rag-driver: Generalisable driving explanations with retrieval-augmented incontext learning in multi-modal large language model","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_12"},{"key":"ref52","article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"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\/11446029.pdf?arnumber=11446029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:41Z","timestamp":1777611461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00533","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}