{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:41Z","timestamp":1777888841729,"version":"3.51.4"},"reference-count":46,"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\/iccv51701.2025.02347","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25305-25314","source":"Crossref","is-referenced-by-count":0,"title":["Long-Term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation"],"prefix":"10.1109","author":[{"given":"Xiuyu","family":"Yang","sequence":"first","affiliation":[{"name":"UT Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhan","family":"Tan","sequence":"additional","affiliation":[{"name":"UT Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Kr\u00e4henb\u00fchl","sequence":"additional","affiliation":[{"name":"UT Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"nuplan: A closed-loop mlbased planning benchmark for autonomous vehicles","author":"Caesar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_37"},{"key":"ref3","article-title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_14"},{"key":"ref5","volume-title":"Rift: Closed-loop rl fine-tuning for realistic and controllable traffic simulation","author":"Chen","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_4"},{"key":"ref7","article-title":"Robust autonomy emerges from self-play","author":"Cusumano-Towner","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_22"},{"key":"ref12","article-title":"Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads","author":"Kou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2582"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"ref16","article-title":"Trajeglish: Traffic modeling as next-token prediction","author":"Philion","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01679"},{"key":"ref18","article-title":"Ctrl-sim: Reactive and controllable driving agents with offline reinforcement learning","author":"Rowe","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00095"},{"key":"ref24","article-title":"Language conditioned traffic generation","volume-title":"7th Annual Conference on Robot Learning (CoRL)","author":"Tan"},{"key":"ref25","article-title":"Promptable closed-loop traffic simulation","volume-title":"8th Annual Conference on Robot Learning (CoRL)","author":"Tan"},{"key":"ref26","article-title":"Interactive post-training for vision-language-action models","author":"Tan","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00154"},{"key":"ref28","article-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3622"},{"key":"ref32","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802408"},{"key":"ref34","volume-title":"Gpd1: Generative pre-training for driving","author":"Xie","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32951"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161167"},{"key":"ref37","article-title":"Modalityspecialized synergizers for interleaved vision-language generalists","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xu"},{"key":"ref38","article-title":"Rmmdet: Road-side multitype and multigroup sensor detection system for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Learning realistic traffic agents in closed-loop","volume-title":"7th Annual Conference on Robot Learning","author":"Zhang"},{"key":"ref40","article-title":"Trafficbots v1. 5: Traffic simulation via conditional vaes and transformers with relative pose encoding","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00510"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3518308"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01240"},{"key":"ref44","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Conference on Robot Learning","author":"Zhong"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref46","article-title":"Behaviorgpt: Smart agent simulation for autonomous driving with next-patch prediction","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11443647.pdf?arnumber=11443647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:34Z","timestamp":1777611574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02347","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}