{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:31:24Z","timestamp":1780086684770,"version":"3.54.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127286","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"3445-3451","source":"Crossref","is-referenced-by-count":8,"title":["Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Zhiyu","family":"Huang","sequence":"first","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinshuo","family":"Weng","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Igl","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiao","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulong","family":"Cao","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Ivanovic","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[{"name":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref2","article-title":"Categorical traffic transformer: Interpretable and diverse behavior prediction with tokenized latent","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3416771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3332474"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3283542"},{"key":"ref6","first-page":"2170","article-title":"Diffstack: A differentiable and modular control stack for autonomous vehicles","volume-title":"Conference on robot learning. PMLR","author":"Karkus","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3254579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610550"},{"key":"ref9","article-title":"MATS: An interpretable trajectory forecasting representation for planning and control","author":"Ivanovic","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Versatile scene-consistent traffic scenario generation as optimization with diffusion","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref12","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Conference on Robot Learning. PMLR","author":"Zhong","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32951"},{"key":"ref15","article-title":"Understanding reinforcement learning-based fine-tuning of diffusion models: A tutorial and review","author":"Uehara","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"ref17","article-title":"Reinforcement learning with human feedback for realistic traffic simulation","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3352811"},{"key":"ref22","article-title":"What truly matters in trajectory prediction for autonomous driving?","author":"Tran","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Rethinking integration of prediction and planning in deep learning-based automated driving systems: a review","author":"Hagedorn","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking","author":"Dauner","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref26","article-title":"A survey of reinforcement learning from human feedback","author":"Kaufmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Behaviorgpt: Smart agent simulation for autonomous driving with next-patch prediction","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Smart: Scalable multiagent real-time simulation via next-token prediction","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_22"},{"key":"ref30","article-title":"Trajeglish: Learning the language of driving scenarios","author":"Philion","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Scenedm: Scene-level multi-agent trajectory generation with consistent diffusion models","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"A diffusion-model of joint interactive navigation","volume":"36","author":"Niedoba","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01453"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_1"},{"key":"ref35","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning. PMLR","author":"Nichol","year":"2021"},{"key":"ref38","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Improving multimodal interactive agents with reinforcement learning from human feedback","author":"Abramson","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"1268","article-title":"Parting with misconceptions about learning-based vehicle motion planning","volume-title":"Conference on Robot Learning. PMLR","author":"Dauner","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611364"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127286.pdf?arnumber=11127286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:37Z","timestamp":1756880077000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127286","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}