{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:30:41Z","timestamp":1784399441122,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557394","type":"print"},{"value":"9789819557400","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5740-0_18","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:22:17Z","timestamp":1768220537000},"page":"255-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MiniDrive: More Efficient Vision-Language Models with\u00a0Multi-level 2D Features as\u00a0Text Tokens for\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Enming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyuan","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghai","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"18_CR1","unstructured":"Abdin, M., et al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)"},{"key":"18_CR2","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"18_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Driving with LLMs: fusing object-level vector modality for explainable autonomous driving. arXiv preprint arXiv:2310.01957 (2023)","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Chen, L., et al.: Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving. arXiv e-prints arXiv:2310.01957 (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.01957","DOI":"10.48550\/arXiv.2310.01957"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Unireplknet: a universal perception large-kernel convnet for audio video point cloud time-series and image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5513\u20135524 (2024)","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"18_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Gopalkrishnan, A., Greer, R., Trivedi, M.: Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving. arXiv e-prints arXiv:2403.19838 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.19838","DOI":"10.48550\/arXiv.2403.19838"},{"key":"18_CR10","unstructured":"Greer, R., Trivedi, M.: Towards explainable, safe autonomous driving with language embeddings for novelty identification and active learning: framework and experimental analysis with real-world data sets. arXiv preprint arXiv:2402.07320 (2024)"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Hu, E.J., et al.: LoRA: Low-Rank Adaptation of Large Language Models. arXiv e-prints arXiv:2106.09685 (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.09685","DOI":"10.48550\/arXiv.2106.09685"},{"key":"18_CR12","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"18_CR13","unstructured":"Li, Y., et al.: Automated evaluation of large vision-language models on self-driving corner cases. arXiv preprint arXiv:2404.10595 (2024)"},{"key":"18_CR14","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR16","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Mao, J., Qian, Y., Ye, J., Zhao, H., Wang, Y.: GPT-Driver: Learning to Drive with GPT. arXiv e-prints arXiv:2310.01415 (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.01415","DOI":"10.48550\/arXiv.2310.01415"},{"key":"18_CR18","unstructured":"Mao, J., Qian, Y., Zhao, H., Wang, Y.: GPT-driver: learning to drive with GPT. arXiv preprint arXiv:2310.01415 (2023)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Panagopoulou, A., et al.: X-instructblip: a framework for aligning x-modal instruction-aware representations to LLMs and emergent cross-modal reasoning. arXiv preprint arXiv:2311.18799 (2023)","DOI":"10.1007\/978-3-031-72995-9_11"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"18_CR21","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Sha, H., et al.: LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving. arXiv e-prints arXiv:2310.03026 (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.03026","DOI":"10.48550\/arXiv.2310.03026"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Sima, C., et al.: DriveLM: Driving with Graph Visual Question Answering. arXiv e-prints arXiv:2312.14150 (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.14150","DOI":"10.48550\/arXiv.2312.14150"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Sima, C., et al.: Drivelm: driving with graph visual question answering. arXiv preprint arXiv:2312.14150 (2023)","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"18_CR25","doi-asserted-by":"publisher","unstructured":"Touvron, H., et al.: LLaMA: Open and Efficient Foundation Language Models. arXiv e-prints arXiv:2302.13971 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"18_CR26","unstructured":"Vaswani, A.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving. arXiv e-prints arXiv:2312.09245 (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.09245","DOI":"10.48550\/arXiv.2312.09245"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Wei, J., et al.: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv e-prints arXiv:2201.11903 (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.11903","DOI":"10.48550\/arXiv.2201.11903"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Drivegpt4: interpretable end-to-end autonomous driving via large language model. arXiv preprint arXiv:2310.01412 (2023)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Drivegpt4: interpretable end-to-end autonomous driving via large language model. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"18_CR32","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5740-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:22:42Z","timestamp":1768220562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5740-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557394","9789819557400"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5740-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}