{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:29:16Z","timestamp":1791912556681,"version":"4.3.4"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC No.62276108"],"award-info":[{"award-number":["NSFC No.62276108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11263-026-03002-y","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:41:35Z","timestamp":1787672495000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving"],"prefix":"10.1007","volume":"134","author":[{"given":"Bo","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bencheng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"3002_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., and others.(2023). Gpt-4 technical report. Preprint retrieved from arXiv:2303.08774"},{"key":"3002_CR2","unstructured":"Anil, R., Dai, A.M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., and others.(2023). Palm 2 technical report. Preprint retrieved from arXiv:2305.10403"},{"issue":"5","key":"3002_CR3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.tics.2008.02.004","volume":"12","author":"D Badre","year":"2008","unstructured":"Badre, D. (2008). Cognitive control, hierarchy, and the rostro-caudal organization of the frontal lobes. Trends in cognitive sciences, 12(5), 193\u2013200.","journal-title":"Trends in cognitive sciences"},{"key":"3002_CR4","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., & Zhou, J.(2023). Qwen-vl: A frontier large vision-language model with versatile abilities. Preprint retrieved from arXiv:2308.12966"},{"key":"3002_CR5","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., and others.(2025). Qwen2. 5-vl technical report. Preprint retrieved from arXiv:2502.13923"},{"key":"3002_CR6","unstructured":"Banerjee, S., & Lavie, A. (2005). Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization"},{"issue":"5","key":"3002_CR7","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.tics.2008.02.009","volume":"12","author":"MM Botvinick","year":"2008","unstructured":"Botvinick, M. M. (2008). Hierarchical models of behavior and prefrontal function. Trends in cognitive sciences, 12(5), 201\u2013208.","journal-title":"Trends in cognitive sciences"},{"key":"3002_CR8","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., and others.(2020). Language models are few-shot learners. In: NeurIPS"},{"key":"3002_CR9","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuscenes: A multimodal dataset for autonomous driving. In: CVPR.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"3002_CR10","unstructured":"Chai, Y., Sapp, B., Bansal, M., & Anguelov, D. (2019). Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction. Preprint retrieved from arXiv:1910.05449."},{"key":"3002_CR11","unstructured":"Chen, S., Jiang, B., Gao, H., Liao, B., Xu, Q., Zhang, Q., Huang, C., Liu, W., & Wang, X. (2024). Vadv2: End-to-end vectorized autonomous driving via probabilistic planning. Preprint retrieved from arXiv:2402.13243."},{"key":"3002_CR12","doi-asserted-by":"crossref","unstructured":"Chen, L., Sinavski, O., H\u00fcnermann, J., Karnsund, A., Willmott, A. J., Birch, D., Maund, D., & Shotton, J. (2023). Driving with llms: Fusing object-level vector modality for explainable autonomous driving. Preprint retrieved from arXiv:2310.01957.","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"3002_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wu, J., Wang, W., Su, W., Chen, G., Xing, S., Zhong, M., Zhang, Q., Zhu, X., Lu, L., and others.(2024). Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"3002_CR14","doi-asserted-by":"crossref","unstructured":"Dauner, D., Hallgarten, M., Li, T., Weng, X., Huang, Z., Yang, Z., Li, H., Gilitschenski, I., Ivanovic, B., Pavone, M., and others.(2024). Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking. In: NeurIPS","DOI":"10.52202\/079017-0902"},{"key":"3002_CR15","doi-asserted-by":"crossref","unstructured":"Deruyttere, T., Vandenhende, S., Grujicic, D., Van Gool, L., & Moens, M.-F. (2019). Talk2car: Taking control of your self-driving car. Preprint retrieved from arXiv:1909.10838.","DOI":"10.18653\/v1\/D19-1215"},{"key":"3002_CR16","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V.(2017). Carla: An open urban driving simulator. In: CoRL"},{"key":"3002_CR17","doi-asserted-by":"crossref","unstructured":"Frieder, S., Pinchetti, L., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P., & Berner, J. (2024). Mathematical capabilities of chatgpt. NeurIPS,","DOI":"10.52202\/075280-1205"},{"key":"3002_CR18","doi-asserted-by":"crossref","unstructured":"Fu, H., Zhang, D., Zhao, Z., Cui, J., Liang, D., Zhang, C., Zhang, D., Xie, H., Wang, B., & Bai, X.(2025). Orion: A holistic end-to-end autonomous driving framework by vision-language instructed action generation. Preprint retrieved from arXiv:2503.19755","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"3002_CR19","doi-asserted-by":"crossref","unstructured":"Gu, J., Hu, C., Zhang, T., Chen, X., Wang, Y., Wang, Y., & Zhao, H.(2022). Vip3d: End-to-end visual trajectory prediction via 3d agent queries. Preprint retrieved from arXiv:2208.01582","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"3002_CR20","doi-asserted-by":"crossref","unstructured":"Hamdan, S., Sima, C., Yang, Z., Li, H., & Guney, F. (2025). Eta: Efficiency through thinking ahead, a dual approach to self-driving with large models.In: ICCV","DOI":"10.1109\/ICCV51701.2025.02462"},{"key":"3002_CR21","unstructured":"Hendrycks, D., & Gimpel, K. (2016). Gaussian error linear units (gelus). Preprint retrieved from arXiv:1606.08415."},{"key":"3002_CR22","unstructured":"Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., & Steinhardt, J. (2021). Measuring mathematical problem solving with the math dataset. Preprint retrieved from arXiv:2103.03874."},{"key":"3002_CR23","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, J., Chen, L., Li, K., Sima, C., Zhu, X., Chai, S., Du, S., Lin, T., Wang, W., Wang, W., and others.(2023). Planning-oriented autonomous driving. In: CVPR","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"3002_CR24","doi-asserted-by":"crossref","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., & Tao, D. (2022). St-p3: End-to-end vision-based autonomous driving via spatial-temporal feature learning. ECCV.","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"3002_CR25","doi-asserted-by":"crossref","unstructured":"Jia, X., Yang, Z., Li, Q., Zhang, Z., & Yan, J. (2024). Bench2drive: Towards multi-ability benchmarking of closed-loop end-to-end autonomous driving. In: NeurIPS.","DOI":"10.52202\/079017-0025"},{"key":"3002_CR26","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q., Sung, Y.-H., Li, Z., & Duerig, T. (2021). Scaling up visual and vision-language representation learning with noisy text supervision. In:ICML"},{"key":"3002_CR27","unstructured":"Jiang, B., Chen, S., Wang, X., Liao, B., Cheng, T., Chen, J., Zhou, H., Zhang, Q., Liu, W., & Huang, C.(2022). Perceive, interact, predict: Learning dynamic and static clues for end-to-end motion prediction. Preprint retrieved from arXiv:2212.02181"},{"key":"3002_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, B., Chen, S., Xu, Q., Liao, B., Chen, J., Zhou, H., Zhang, Q., Liu, W., Huang, C., & Wang, X.(2023). Vad: Vectorized scene representation for efficient autonomous driving. In: ICCV","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"3002_CR29","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., & Akata, Z. (2018). Textual explanations for self-driving vehicles. In: ECCV.","DOI":"10.1007\/978-3-030-01216-8_35"},{"issue":"5648","key":"3002_CR30","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1126\/science.1088545","volume":"302","author":"E Koechlin","year":"2003","unstructured":"Koechlin, E., Ody, C., & Kouneiher, F. (2003). The architecture of cognitive control in the human prefrontal cortex. Science, 302(5648), 1181\u20131185.","journal-title":"Science"},{"key":"3002_CR31","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S.(2023). Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML"},{"key":"3002_CR32","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S.(2022). Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML"},{"key":"3002_CR33","unstructured":"Li, Y., Shang, S., Liu, W., Zhan, B., Wang, H., Wang, Y., Chen, Y., Wang, X., An, Y., Tang, C., Hou, L., Fan, L., & Zhang, Z.(2026). DriveVLA-W0: World models amplify data scaling law in autonomous driving. In: ICLR"},{"key":"3002_CR34","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Yu, Q., & Dai, J.(2022). Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. Preprint retrieved from arXiv:2203.17270","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"3002_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Liu, Y., He, J., Fan, L., & Zhang, Z.(2025). End-to-end driving with online trajectory evaluation via bev world model. In: ICCV","DOI":"10.1109\/ICCV51701.2025.02519"},{"key":"3002_CR36","unstructured":"Li, Y., Xiong, K., Guo, X., Li, F., Yan, S., Xu, G., Zhou, L., Chen, L., Sun, H., Wang, B., Ma, K., Chen, G., Ye, H., Liu, W., & Wang, X.(2026). ReCogDrive: A reinforced cognitive framework for end-to-end autonomous driving. In: ICLR"},{"key":"3002_CR37","unstructured":"Liao, B., Chen, S., Wang, X., Cheng, T., Zhang, Q., Liu, W.,& Huang, C.(2022). Maptr: Structured modeling and learning for online vectorized hd map construction. Preprint retrieved from arXiv:2208.14437"},{"key":"3002_CR38","doi-asserted-by":"crossref","unstructured":"Liao, B., Chen, S., Yin, H., Jiang, B., Wang, C., Yan, S., Zhang, X., Li, X., Zhang, Y., Zhang, Q., and others.(2025). Diffusiondrive: Truncated diffusion model for end-to-end autonomous driving. In: CVPR","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"3002_CR39","doi-asserted-by":"crossref","unstructured":"Liao, B., Chen, S., Zhang, Y., Jiang, B., Zhang, Q., Liu, W., Huang, C., & Wang, X.(2023). Maptrv2: An end-to-end framework for online vectorized hd map construction. Preprint retrieved from arXiv:2308.05736","DOI":"10.1007\/s11263-024-02235-z"},{"key":"3002_CR40","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., & Han, S. (2024). Vila: On pre-training for visual language models. CVPR.","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"3002_CR41","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., & Lee, Y.J.(2024). Improved baselines with visual instruction tuning. In: CVPR","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"3002_CR42","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y.J.(2024). Visual instruction tuning. In: NeurIPS","DOI":"10.52202\/075280-1516"},{"key":"3002_CR43","unstructured":"Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS"},{"issue":"1","key":"3002_CR44","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/TIV.2016.2578706","volume":"1","author":"B Paden","year":"2016","unstructured":"Paden, B., \u010c\u00e1p, M., Yong, S. Z., Yershov, D., & Frazzoli, E. (2016). A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Transactions on intelligent vehicles, 1(1), 33\u201355.","journal-title":"IEEE Transactions on intelligent vehicles"},{"key":"3002_CR45","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). Bleu: a method for automatic evaluation of machine translation. In: ACL","DOI":"10.3115\/1073083.1073135"},{"key":"3002_CR46","doi-asserted-by":"crossref","unstructured":"Philion, J., & Fidler, S. (2020). Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In: ECCV.","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"3002_CR47","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., & Geiger, A. (2021). Multi-modal fusion transformer for end-to-end autonomous driving. In: CVPR.","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"3002_CR48","doi-asserted-by":"crossref","unstructured":"Qian, T., Chen, J., Zhuo, L., Jiao, Y., & Jiang, Y.-G. (2024). Nuscenes-qa: A multi-modal visual question answering benchmark for autonomous driving scenario. In: AAAI.","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"3002_CR49","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., and others.(2021). Learning transferable visual models from natural language supervision. In: ICML"},{"key":"3002_CR50","unstructured":"Sha, H., Mu, Y., Jiang, Y., Chen, L., Xu, C., Luo, P., Li, S. E., Tomizuka, M., Zhan, W., & Ding, M. (2023). Languagempc: Large language models as decision makers for autonomous driving. Preprint retrieved from arXiv:2310.03026."},{"key":"3002_CR51","doi-asserted-by":"crossref","unstructured":"Sheng, Z., Ye, X., Luo, J., Chen, S., & Ren, L. (2026). ExploreVLA: Dense world modeling and exploration for end-to-end autonomous driving. In: ECCV.","DOI":"10.1007\/978-3-032-37261-1_16"},{"key":"3002_CR52","doi-asserted-by":"crossref","unstructured":"Sima, C., Renz, K., Chitta, K., Chen, L., Zhang, H., Xie, C., Luo, P., Geiger, A., & Li, H. (2023). Drivelm: Driving with graph visual question answering. Preprint retrieved from arXiv:2312.14150.","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"3002_CR53","doi-asserted-by":"crossref","unstructured":"Song, Z., Jia, C., Liu, L., Pan, H., Zhang, Y., Wang, J., Zhang, X., Xu, S., Yang, L.,& Luo, Y.(2025). Don\u2019t shake the wheel: Momentum-aware planning in end-to-end autonomous driving. In: CVPR","DOI":"10.32388\/2VUIDZ"},{"key":"3002_CR54","doi-asserted-by":"crossref","unstructured":"Sun, W., Lin, X., Shi, Y., Zhang, C., Wu, H., & Zheng, S. (2025). Sparsedrive: End-to-end autonomous driving via sparse scene representation. In: ICRA","DOI":"10.1109\/ICRA55743.2025.11128800"},{"issue":"9","key":"3002_CR55","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1002\/rob.20147","volume":"23","author":"S Thrun","year":"2006","unstructured":"Thrun, S., Montemerlo, M., Dahlkamp, H., Stavens, D., Aron, A., Diebel, J., Fong, P., Gale, J., Halpenny, M., Hoffmann, G., et al. (2006). Stanley: The robot that won the darpa grand challenge. Journal of field Robotics, 23(9), 661\u2013692.","journal-title":"Journal of field Robotics"},{"key":"3002_CR56","unstructured":"Tian, X., Gu, J., Li, B., Liu, Y., Wang, Y., Zhao, Z., Zhan, K., Jia, P., Lang, X., & Zhao, H.(2025). Drivevlm: The convergence of autonomous driving and large vision-language models. In: CoRL"},{"key":"3002_CR57","doi-asserted-by":"crossref","unstructured":"Toromanoff, M., Wirbel, E., & Moutarde, F. (2020). End-to-end model-free reinforcement learning for urban driving using implicit affordances. In: CVPR.","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"3002_CR58","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., and others.(2023). Llama: Open and efficient foundation language models. Preprint retrieved from arXiv:2302.13971"},{"issue":"8","key":"3002_CR59","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1002\/rob.20255","volume":"25","author":"C Urmson","year":"2008","unstructured":"Urmson, C., Anhalt, J., Bagnell, D., Baker, C., Bittner, R., Clark, M., Dolan, J., Duggins, D., Galatali, T., Geyer, C., et al. (2008). Autonomous driving in urban environments: Boss and the urban challenge. Journal of field Robotics, 25(8), 425\u2013466.","journal-title":"Journal of field Robotics"},{"key":"3002_CR60","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I.(2017). Attention is all you need. In: NeurIPS"},{"key":"3002_CR61","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. In: CVPR.","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"3002_CR62","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., and others.(2024). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. Preprint retrieved from arXiv:2409.12191"},{"key":"3002_CR63","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., & Solomon, J.(2022). Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In: CoRL"},{"key":"3002_CR64","unstructured":"Wang, W., Xie, J., Hu, C., Zou, H., Fan, J., Tong, W., Wen, Y., Wu, S., Deng, H., Li, Z.,and others.(2023). Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving. Preprint retrieved from arXiv:2312.09245"},{"key":"3002_CR65","unstructured":"Wang, S., Yu, Z., Jiang, X., Lan, S., Shi, M., Chang, N., Kautz, J., Li, Y., & Alvarez, J. M. (2024). Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning. Preprint retrieved from arXiv:2405.01533."},{"key":"3002_CR66","doi-asserted-by":"crossref","unstructured":"Weng, X., Ivanovic, B., Wang, Y., Wang, Y., & Pavone, M.(2024). Para-drive: Parallelized architecture for real-time autonomous driving. In: CVPR","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"3002_CR67","unstructured":"Wu, D., Han, W., Wang, T., Liu, Y., Zhang, X., & Shen, J. (2023). Language prompt for autonomous driving. Preprint retrieved from arXiv:2309.04379."},{"key":"3002_CR68","doi-asserted-by":"crossref","unstructured":"Wu, D., Han, W., Wang, T., Dong, X., Zhang, X., & Shen, J. (2023). Referring multi-object tracking. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"3002_CR69","doi-asserted-by":"crossref","unstructured":"Xing, Z., Zhang, X., Hu, Y., Jiang, B., He, T., Zhang, Q., Long, X.,& Yin, W. (2025). Goalflow: Goal-driven flow matching for multimodal trajectories generation in end-to-end autonomous driving. In: CVPR","DOI":"10.1109\/CVPR52734.2025.00157"},{"key":"3002_CR70","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, Y., Xie, E., Zhao, Z., Guo, Y., Wong, K.K., Li, Z., & Zhao, H.(2023). Drivegpt4: Interpretable end-to-end autonomous driving via large language model. Preprint retrieved from arXiv:2310.01412","DOI":"10.1109\/LRA.2024.3440097"},{"key":"3002_CR71","unstructured":"Yang, A., Yang, B., Hui, B., Zheng, B., Yu, B., Zhou, C., Li, C., Li, C., Liu, D., Huang, F., and others.(2024). Qwen2 technical report. Preprint retrieved from arXiv:2407.10671"},{"key":"3002_CR72","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., and others.(2023). Judging llm-as-a-judge with mt-bench and chatbot arena. In: NeurIPS","DOI":"10.52202\/075280-2020"},{"key":"3002_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Cai, T., Zhao, S.Z., Zhang, Y., Huang, Z., Zhou, B., & Ma, J. (2025). Autovla: A vision-language-action model for end-to-end autonomous driving with adaptive reasoning and reinforcement fine-tuning. In: NeurIPS","DOI":"10.52202\/085713-0942"},{"key":"3002_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Huang, L., Bu, Q., Zeng, J., Li, T., Qiu, H., Zhu, H., Guo, M., Qiao, Y., & Li, H.(2024). Embodied understanding of driving scenarios. Preprint retrieved from arXiv:2403.04593","DOI":"10.1007\/978-3-031-73033-7_8"},{"key":"3002_CR75","unstructured":"Zhou, Z., Yang, R., Qi, X., Guo, Y., Chen, S. X., Feng, T., Pistunova, K., Shen, Y., Su, L., & Ma, J. (2026). SpanVLA: Efficient action bridging and learning from negative-recovery samples for Vision-Language-Action model. Preprint retrieved from arXiv:2604.19710."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03002-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-03002-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03002-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:13:15Z","timestamp":1790151195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-03002-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":75,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["3002"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-03002-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"9 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All authors declare no conflicts of interest.","order":1,"name":"Ethics","label":"Conflicts of Interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The full suite of code, including the model architecture, training, and inference procedures, is publicly available at\n                      \n                      .","order":2,"name":"Ethics","label":"Code availability","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"407"}}