{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:32Z","timestamp":1777888472868,"version":"3.51.4"},"reference-count":56,"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\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["16KISK036K"],"award-info":[{"award-number":["16KISK036K"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"publisher","award":["rwth1825"],"award-info":[{"award-number":["rwth1825"]}],"id":[{"id":"10.13039\/501100007210","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\/iccv51701.2025.02684","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28903-28912","source":"Crossref","is-referenced-by-count":0,"title":["DONUT: A Decoder-Only Model for Trajectory Prediction"],"prefix":"10.1109","author":[{"given":"Markus","family":"Knoche","sequence":"first","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daan","family":"de Geus","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref3","article-title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","volume-title":"CoRL","author":"Chai","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00797"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00783"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160984"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793868"},{"key":"ref9","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL","author":"Devlin","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3311351"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3262150"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564944"},{"key":"ref14","article-title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","author":"Gilles","year":"2022","journal-title":"ICLR"},{"key":"ref15","article-title":"Better & Faster Large Language Models via Multi-token Prediction","author":"Gloeckle","year":"2024","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00865"},{"key":"ref18","article-title":"SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout","author":"Jiang","year":"2024","journal-title":"NeurIPS"},{"key":"ref19","article-title":"SEPT: Towards Efficient Scene Representation Learning for Motion Prediction","author":"Lan","year":"2024","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28130"},{"key":"ref23","article-title":"DeepSeek-V3 Technical Report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"ref27","article-title":"The Waymo Open Sim Agents Challenge","author":"Montali","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"ref29","article-title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","author":"Ngiam","year":"2022","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01408"},{"key":"ref31","article-title":"Trajeglish: Traffic Modeling as Next-Token Prediction","author":"Philion","year":"2024","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_19"},{"key":"ref33","article-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01321"},{"key":"ref35","article-title":"Learning Cooperative Trajectory Representations for Motion Forecasting","author":"Ruan","year":"2024","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref38","article-title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","author":"Shi","year":"2022","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","author":"Tancik","year":"2020","journal-title":"NeurIPS"},{"key":"ref40","article-title":"Multiple Futures Prediction","author":"Tang","year":"2019","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01445"},{"key":"ref42","article-title":"Gemini: A Family of Highly Capable Multimodal Models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Attention is All you Need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160468"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02106"},{"key":"ref47","article-title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","author":"Wilson","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref48","article-title":"SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_30"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636035"},{"key":"ref51","article-title":"DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","article-title":"TNT: Target-driveN Trajectory Prediction","author":"Zhao","year":"2021","journal-title":"CoRL"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01447"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"ref56","article-title":"BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction","author":"Zhou","year":"2024","journal-title":"NeurIPS"}],"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\/11443584.pdf?arnumber=11443584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:45:33Z","timestamp":1777610733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02684","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}