{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:24Z","timestamp":1778048364331,"version":"3.51.4"},"reference-count":68,"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\/wacv61042.2026.00266","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2710-2720","source":"Crossref","is-referenced-by-count":0,"title":["iMotion-LLM: Instruction-Conditioned Trajectory Generation"],"prefix":"10.1109","author":[{"given":"Abdulwahab","family":"Felemban","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nussair","family":"Hroub","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Ding","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eslam","family":"Abdelrahman","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqian","family":"Shen","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abduallah","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"issue":"2","key":"ref4","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02471"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref9","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01659"},{"key":"ref12","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793868"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref17","article-title":"Talk2bev: Language-enhanced bird\u2019s-eye view maps for autonomous driving","author":"Dewangan","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564944"},{"key":"ref22","author":"Grattafiori","year":"2024","journal-title":"The LLama 3 herd of models"},{"key":"ref23","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref26","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref28","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812060"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref32","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref33","article-title":"Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on large language model","author":"Jin","year":"2023"},{"key":"ref34","article-title":"Fast and efficient 2-bit llm inference on gpu","author":"Kim","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref38","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Q-sparse: All large language models can be fully sparsely-activated","author":"Liu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref41","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023"},{"key":"ref42","author":"Mirza","year":"2014","journal-title":"Conditional generative adversarial nets"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3146300"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2582"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"ref47","article-title":"Scene transformer: A unified architecture for predicting future trajectories of multiple agents","volume-title":"International Conference on Learning Representations","author":"Ngiam"},{"issue":"8","key":"ref48","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103705"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0473"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0473"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3352811"},{"key":"ref55","article-title":"Language conditioned traffic generation","volume-title":"7th Annual Conference on Robot Learning","author":"Tan"},{"key":"ref56","article-title":"Promptable closed-loop traffic simulation","volume-title":"8th Annual Conference on Robot Learning","author":"Tan"},{"key":"ref57","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref58","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref59","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","article-title":"Flightllm: Efficient large language model inference with a complete mapping flow on fpgas","author":"Wu","year":"2024"},{"key":"ref61","article-title":"Language-driven interactive traffic trajectory generation","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Xia"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3590784\/mm1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref64","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"7th Annual Conference on Robot Learning","author":"Zhong"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref66","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref67","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu"},{"key":"ref68","article-title":"Star attention: Efficient llm inference over long sequences","author":"Zhu","year":"2024"}],"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\/11492414.pdf?arnumber=11492414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:30Z","timestamp":1778046990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00266","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}