{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:08:45Z","timestamp":1788988125316,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:15Z","timestamp":1788985575000},"page":"317-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Teaching Vision-Language-Action Models What to\u00a0See and\u00a0Where to\u00a0Look"],"prefix":"10.1007","author":[{"given":"Yuguang","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhewen","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kehua","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianbin","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","unstructured":"Ang, S., et al.: ASSCG: just-right gating over chattering for fast-slow LLM planning in autonomous driving (2026). https:\/\/arxiv.org\/abs\/2606.25509"},{"key":"18_CR2","unstructured":"Bai, S., et al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"18_CR3","unstructured":"Broekman, N.: Toward safe and scalable autonomy: a comprehensive review of technologies, deployments, and challenges in autonomous driving. Trans. Comput. Sci. Methods 5(4) (2025)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"18_CR5","unstructured":"Chen, C., et al.: Devil is in narrow policy: unleashing exploration in driving VLA models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1062\u20131072 (2026)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Ding, Z.H., Wang, Z., Wang, Y., Zhang, L., Liu, S.: Asynchronous large language model enhanced planner for autonomous driving. In: European Conference on Computer Vision, pp. 22\u201338. Springer (2024)","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chi, H., et al.: Impromptu VLA: open weights and open data for driving vision-language-action models. arXiv preprint arXiv:2505.23757 (2025)","DOI":"10.52202\/085713-2557"},{"issue":"11","key":"18_CR9","doi-asserted-by":"publisher","first-page":"12878","DOI":"10.1109\/TPAMI.2022.3200245","volume":"45","author":"K Chitta","year":"2022","unstructured":"Chitta, K., Prakash, A., Jaeger, B., Yu, Z., Renz, K., Geiger, A.: Transfuser: imitation with transformer-based sensor fusion for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 12878\u201312895 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR10","doi-asserted-by":"publisher","first-page":"28706","DOI":"10.52202\/079017-0902","volume":"37","author":"D Dauner","year":"2024","unstructured":"Dauner, D., et al.: Navsim: data-driven non-reactive autonomous vehicle simulation and benchmarking. Adv. Neural. Inf. Process. Syst. 37, 28706\u201328719 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR11","unstructured":"Feng, R., et al.: Artemis: autoregressive end-to-end trajectory planning with mixture of experts for autonomous driving. arXiv preprint arXiv:2504.19580 (2025)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: Orion: a holistic end-to-end autonomous driving framework by vision-language instructed action generation. arXiv preprint arXiv:2503.19755 (2025)","DOI":"10.1109\/ICCV51701.2025.02302"},{"issue":"8081","key":"18_CR13","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D., et al.: Deepseek-r1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081), 633\u2013638 (2025)","journal-title":"Nature"},{"key":"18_CR14","first-page":"45","volume":"3","author":"A Heyden","year":"2005","unstructured":"Heyden, A., Pollefeys, M.: Multiple view geometry. Emerg. Top. Comput. Vis. 3, 45\u2013108 (2005)","journal-title":"Emerg. Top. Comput. Vis."},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., Tao, D.: ST-P3: end-to-end vision-based autonomous driving via spatial-temporal feature learning. In: European Conference on Computer Vision, pp. 533\u2013549. Springer (2022)","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liu, H., Lv, C.: Gameformer: game-theoretic modeling and learning of transformer-based interactive prediction and planning for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3903\u20133913 (2023)","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liu, H., Wu, J., Lv, C.: Differentiable integrated motion prediction and planning with learnable cost function for autonomous driving. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3283542"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Gen-drive: enhancing diffusion generative driving policies with reward modeling and reinforcement learning fine-tuning. arXiv preprint arXiv:2410.05582 (2024)","DOI":"10.1109\/ICRA55743.2025.11127286"},{"key":"18_CR20","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"18_CR21","unstructured":"Hwang, J.J., et al.: Emma: end-to-end multimodal model for autonomous driving. arXiv preprint arXiv:2410.23262 (2024)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: VAD: vectorized scene representation for efficient autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138350 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"18_CR23","unstructured":"Jiao, S., et al.: Evadrive: evolutionary adversarial policy optimization for end-to-end autonomous driving. arXiv preprint arXiv:2508.09158 (2025)"},{"key":"18_CR24","unstructured":"Kirby, E., et al.: Driving on registers. arXiv preprint arXiv:2601.05083 (2026)"},{"key":"18_CR25","unstructured":"Li, J., Zhang, B., Jin, X., Deng, J., Zhu, X., Zhang, L.: Imagidrive: a unified imagination-and-planning framework for autonomous driving. arXiv preprint arXiv:2508.11428 (2025)"},{"key":"18_CR26","unstructured":"Li, K., et al.: Hydra-MDP++: advancing end-to-end driving via expert-guided hydra-distillation. arXiv preprint arXiv:2503.12820 (2025)"},{"key":"18_CR27","unstructured":"Li, Y., et al.: Drivevla-w0: world models amplify data scaling law in autonomous driving. arXiv preprint arXiv:2510.12796 (2025)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Liu, Y., He, J., Fan, L., Zhang, Z.: End-to-end driving with online trajectory evaluation via BEV world model. arXiv preprint arXiv:2504.01941 (2025)","DOI":"10.1109\/ICCV51701.2025.02519"},{"key":"18_CR29","unstructured":"Li, Y., et al.: Recogdrive: a reinforced cognitive framework for end-to-end autonomous driving. arXiv preprint arXiv:2506.08052 (2025)"},{"key":"18_CR30","unstructured":"Li, Z., et al.: Hydra-MDP: end-to-end multimodal planning with multi-target hydra-distillation. arXiv preprint arXiv:2406.06978 (2024)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from lidar-camera via spatiotemporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3515454"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Is ego status all you need for open-loop end-to-end autonomous driving? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14864\u201314873 (2024)","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"18_CR33","doi-asserted-by":"publisher","first-page":"10421","DOI":"10.52202\/068431-0757","volume":"35","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: Bevfusion: a simple and robust lidar-camera fusion framework. Adv. Neural. Inf. Process. Syst. 35, 10421\u201310434 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Liao, B., et al.: Diffusiondrive: truncated diffusion model for end-to-end autonomous driving. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12037\u201312047 (2025)","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Adaptive smooth L1 loss: a better way to regress scene texts with extreme aspect ratios. In: 2021 IEEE Symposium on Computers and Communications (ISCC), pp.\u00a01\u20137. IEEE (2021)","DOI":"10.1109\/ISCC53001.2021.9631466"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Liu, H., Huang, Z., Huang, W., Yang, H., Mo, X., Lv, C.: Hybrid-prediction integrated planning for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3526936"},{"key":"18_CR37","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR38","unstructured":"Liu, R., Kong, L., Li, D., Zhao, H.: Occvla: vision-language-action model with implicit 3D occupancy supervision. arXiv preprint arXiv:2509.05578 (2025)"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR40","unstructured":"Luo, Y., et al.: Adathinkdrive: adaptive thinking via reinforcement learning for autonomous driving. arXiv preprint arXiv:2509.13769 (2025)"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Qian, T., Chen, J., Zhuo, L., Jiao, Y., Jiang, Y.G.: Nuscenes-qa: a multi-modal visual question answering benchmark for autonomous driving scenario. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4542\u20134550 (2024)","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"18_CR42","unstructured":"Qiao, Z., Li, H., Cao, Z., Liu, H.X.: Lightemma: lightweight end-to-end multimodal model for autonomous driving. arXiv preprint arXiv:2505.00284 (2025)"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Renz, K., Chen, L., Arani, E., Sinavski, O.: Simlingo: vision-only closed-loop autonomous driving with language-action alignment. arXiv preprint arXiv:2503.09594 (2025)","DOI":"10.1109\/CVPR52734.2025.01120"},{"key":"18_CR44","unstructured":"Renz, K., et al.: Carllava: vision language models for camera-only closed-loop driving. arXiv preprint arXiv:2406.10165 (2024)"},{"key":"18_CR45","unstructured":"Rowe, L., de\u00a0Schaetzen, R., Girgis, R., Pal, C., Paull, L.: Poutine: vision-language-trajectory pre-training and reinforcement learning post-training enable robust end-to-end autonomous driving. arXiv preprint arXiv:2506.11234 (2025)"},{"issue":"5","key":"18_CR46","doi-asserted-by":"publisher","first-page":"3955","DOI":"10.1109\/TPAMI.2024.3352811","volume":"46","author":"S Shi","year":"2024","unstructured":"Shi, S., Jiang, L., Dai, D., Schiele, B.: MTR++: multi-agent motion prediction with symmetric scene modeling and guided intention querying. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 3955\u20133971 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Sima, C., et al.: Drivelm: driving with graph visual question answering. In: European Conference on Computer Vision, pp. 256\u2013274. Springer (2024)","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"18_CR48","unstructured":"Tian, X., et al.: Drivevlm: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"18_CR49","unstructured":"Wang, S., et al.: Omnidrive: a holistic LLM-agent framework for autonomous driving with 3D perception, reasoning and planning. arXiv preprint arXiv:2405.01533 (2024)"},{"key":"18_CR50","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: Detr3d: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"18_CR51","unstructured":"Wu, Z., et al.: Deepseek-vl2: mixture-of-experts vision-language models for advanced multimodal understanding (2024). https:\/\/arxiv.org\/abs\/2412.10302. Accessed 16 May 2025"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Xing, S., et al.: Openemma: open-source multimodal model for end-to-end autonomous driving. In: Proceedings of the Winter Conference on Applications of Computer Vision, pp. 1001\u20131009 (2025)","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"18_CR53","unstructured":"Yang, Z., et al.: Drivemoe: mixture-of-experts for vision-language-action model in end-to-end autonomous driving. arXiv preprint arXiv:2505.16278 (2025)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, X., Han, X., Yang, F., Ma, Y., Knoll, A.C.: Opendrivevla: towards end-to-end autonomous driving with large vision language action model. arXiv preprint arXiv:2503.23463 (2025)","DOI":"10.1609\/aaai.v40i16.38386"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Autovla: a vision-language-action model for end-to-end autonomous driving with adaptive reasoning and reinforcement fine-tuning. arXiv preprint arXiv:2506.13757 (2025)","DOI":"10.52202\/085713-0942"},{"key":"18_CR56","unstructured":"Zhou, Z., Wen, Z., Wang, J., Li, Y.H., Huang, Y.K.: Qcnext: a next-generation framework for joint multi-agent trajectory prediction. arXiv preprint arXiv:2306.10508 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37356-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:24Z","timestamp":1788985584000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_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":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}