{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:14Z","timestamp":1778048474871,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00502","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5174-5183","source":"Crossref","is-referenced-by-count":0,"title":["ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos"],"prefix":"10.1109","author":[{"given":"Peiran","family":"Wu","sequence":"first","affiliation":[{"name":"University of Bristol"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunze","family":"Liu","sequence":"additional","affiliation":[{"name":"Memories.ai Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxiao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Bristol"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref5","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref7","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Damen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.397"},{"key":"ref11","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref12","volume-title":"open-r1-mutimodal","author":"Li","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01761"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref15","article-title":"Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.428"},{"key":"ref17","article-title":"Aria everyday activities dataset","author":"Lv","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01811"},{"key":"ref21","volume-title":"Technical report","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477708"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02826-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00253"},{"key":"ref27","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref29","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":"ref30","article-title":"Fmbench: Benchmarking fairness in multimodal large language models on medical tasks","author":"Wu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref33","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.822"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491952.pdf?arnumber=11491952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:04:26Z","timestamp":1778047466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00502","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}