{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:30:13Z","timestamp":1778347813222,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097672","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"1689-1696","source":"Crossref","is-referenced-by-count":1,"title":["PrefDrive: Enhancing Autonomous Driving Through Preference-Guided Large Language Models"],"prefix":"10.1109","author":[{"given":"Yun","family":"Li","sequence":"first","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Javanmardi","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Thompson","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Katsumata","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Orsholits","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manabu","family":"Tsukada","sequence":"additional","affiliation":[{"name":"Graduate School of Information and Science Technology, The University of Tokyo,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1117\/12.3026671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIBMS60103.2023.10347754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422308"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3711118"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranpol.2024.03.006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01434"},{"key":"ref11","article-title":"Evaluation of Large Language Models for Decision Making in Autonomous Driving","volume-title":"2023 Symposium on Machine Learning for Autonomous Driving collocated with NeurIPS","author":"Tanahashi"},{"key":"ref12","article-title":"For Perception Tasks: The Cost of LLM Pretraining by Next-Token Prediction Outweigh its Benefits","volume-title":"NeurIPS 2024 Workshop: Self-Supervised Learning - Theory and Practice","author":"Balestriero","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"ref14","first-page":"24466","article-title":"Preference-grounded token-level guidance for language model fine-tuning","volume":"abs\/2306.00398","author":"Yang","year":"2023","journal-title":"Neural Inf Process Syst"},{"key":"ref15","article-title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Rafailov"},{"key":"ref16","article-title":"Are we done with ImageNet?","author":"Beyer","year":"2020","journal-title":"arXiv [cs.CV]"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00252"},{"key":"ref19","article-title":"Reinforcement learning with Human Feedback: Learning Dynamic Choices via Pessimism","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref20","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref21","article-title":"QLoRA: Efficient Finetuning of Quantized LLMs","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Dettmers","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3273547"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3402136"},{"key":"ref24","article-title":"Don\u2019t stop pretraining? Make prompt-based fine-tuning powerful learner","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"abs\/2305.01711","author":"Shi"},{"key":"ref25","first-page":"3773","article-title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Chen","year":"2022"},{"key":"ref26","first-page":"1","article-title":"CARLA: An Open Urban Driving Simulator","volume-title":"Proceedings of the 1 st Annual Conference on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref27","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref29","article-title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","volume-title":"First Conference on Language Modeling","author":"Huang"},{"key":"ref30","article-title":"RRHF: Rank responses to align language models with Human Feedback without tears","volume-title":"37th Conference on Neural Information Processing Systems (NeurIPS 2023).","volume":"11","author":"Yuan"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097672.pdf?arnumber=11097672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:59:31Z","timestamp":1754542771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097672","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}