{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:14:16Z","timestamp":1789125256956,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370150","type":"print"},{"value":"9783032370167","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\/978-3-032-37016-7_10","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:58:55Z","timestamp":1789124335000},"page":"177-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RoadBench: Benchmarking MLLMs on\u00a0Fine-Grained Spatial Understanding and\u00a0Reasoning Under Urban Road Scenarios"],"prefix":"10.1007","author":[{"given":"Jun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Depeng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"10_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"10_CR2","unstructured":"Azzolini, A., et al.: Cosmos-reason1: From physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558 (2025)"},{"key":"10_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"10_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"10_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chang, X., Xue, M., Liu, X., Pan, Z., Wei, X.: Driving by the rules: A benchmark for integrating traffic sign regulations into vectorized HD map. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6823\u20136833 (2025)","DOI":"10.1109\/CVPR52734.2025.00640"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, H., Li, J., Liu, Y., Dong, Z., Yang, B.: Spatialllm: From multi-modality data to urban spatial intelligence. arXiv preprint arXiv:2505.12703 (2025)","DOI":"10.1016\/j.jag.2026.105177"},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C.: Spatialrgpt: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR10","unstructured":"Comanici, G., et al.: Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Cui, C., et\u00a0al.: A survey on multimodal large language models for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 958\u2013979 (2024)","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Daxberger, E., et al.: MM-spatial: Exploring 3D spatial understanding in multimodal LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7395\u20137408 (2025)","DOI":"10.1109\/ICCV51701.2025.00694"},{"key":"10_CR13","unstructured":"Driess, D., et al.: PaLM-E: An embodied multimodal language model. In: International Conference on Machine Learning, pp. 8469\u20138488. PMLR (2023)"},{"key":"10_CR14","unstructured":"Eiter, T., Mannila, H.: Computing discrete fr\u00e9chet distance (1994)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Feng, J., Liu, T., Du, Y., Guo, S., Lin, Y., Li, Y.: CityGPT: Empowering urban spatial cognition of large language models. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pp. 591\u2013602 (2025)","DOI":"10.1145\/3711896.3736878"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Feng, J., Wang, S., Liu, T., Xi, Y., Li, Y.: UrbanLLaVA: A multi-modal large language model for urban intelligence with spatial reasoning and understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6209\u20136219 (2025)","DOI":"10.1109\/ICCV51701.2025.00586"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Feng, J., et al.: Citybench: Evaluating the capabilities of large language models for urban tasks. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V. 2, pp. 5413\u20135424 (2025)","DOI":"10.1145\/3711896.3737375"},{"key":"10_CR18","unstructured":"Fu, C., et al.: MME: A comprehensive evaluation benchmark for multimodal large language models (2024). https:\/\/arxiv.org\/abs\/2306.13394"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Q., et al.: Regiongpt: Towards region understanding vision language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13796\u201313806 (2024)","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Hu, H., et\u00a0al.: RS-vHeat: Heat conduction guided efficient remote sensing foundation model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9876\u20139887 (2025)","DOI":"10.1109\/ICCV51701.2025.00921"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Seed-bench: Benchmarking multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13299\u201313308 (2024)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"10_CR22","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: ManipLLM: Embodied multimodal large language model for object-centric robotic manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18061\u201318070 (2024)","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: Is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"10_CR25","unstructured":"Lu, P., et al.: MathVista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"10_CR26","unstructured":"OpenDataLab: Labelu (2025). https:\/\/github.com\/opendatalab\/labelU-kit. Accessed 01 Sept 2025"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Ou, R., Hu, Y., Zhang, F., Chen, J., Liu, Y.: GeoPix: A multimodal large language model for pixel-level image understanding in remote sensing. IEEE Geosci. Remote Sensing Mag. (2025)","DOI":"10.1109\/MGRS.2025.3560293"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Park, S.Y., et al.: NuPlanQA: A large-scale dataset and benchmark for multi-view driving scene understanding in multi-modal large language models. arXiv preprint arXiv:2503.12772 (2025)","DOI":"10.1109\/ICCV51701.2025.00756"},{"key":"10_CR29","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":"10_CR30","unstructured":"Ramakrishnan, S.K., Wijmans, E., Kraehenbuehl, P., Koltun, V.: Does spatial cognition emerge in frontier models? arXiv preprint arXiv:2410.06468 (2024)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Roberts, J., L\u00fcddecke, T., Sheikh, R., Han, K., Albanie, S.: Charting new territories: Exploring the geographic and geospatial capabilities of multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 554\u2013563 (2024)","DOI":"10.1109\/CVPRW63382.2024.00060"},{"key":"10_CR32","unstructured":"Team, G., et al.: Gemma 3 technical report. arXiv preprint arXiv:2503.19786 (2025)"},{"key":"10_CR33","unstructured":"Team, V., et al.: GLM4.5v and GLM-4.1v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning (2025). https:\/\/arxiv.org\/abs\/2507.01006"},{"key":"10_CR34","unstructured":"Tian, X., et al.: DriveVLM: The convergence of autonomous driving and large vision-language models. In: Conference on Robot Learning, pp. 4698\u20134726. PMLR (2025)"},{"key":"10_CR35","unstructured":"Touvron, H., et al.: LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"10_CR36","doi-asserted-by":"publisher","first-page":"75392","DOI":"10.52202\/079017-2400","volume":"37","author":"J Wang","year":"2024","unstructured":"Wang, J., et al.: Is a picture worth a thousand words? delving into spatial reasoning for vision language models. Adv. Neural. Inf. Process. Syst. 37, 75392\u201375421 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Ma, W., Zhang, T., de\u00a0Melo, C.M., Chen, J., Yuille, A.: Spatial457: A diagnostic benchmark for 6D spatial reasoning of large multimodal models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24669\u201324679 (2025)","DOI":"10.1109\/CVPR52734.2025.02297"},{"key":"10_CR38","unstructured":"Wei, H., et al.: Slow perception: Let\u2019s perceive geometric figures step-by-step. arXiv preprint arXiv:2412.20631 (2024)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Xiao, H., et al.: A comprehensive survey of large language models and multimodal large language models in medicine. Inform. Fusion 102888 (2024)","DOI":"10.1016\/j.inffus.2024.102888"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Xie, S., et al.: Are VLMs ready for autonomous driving? an empirical study from the reliability, data, and metric perspectives. arXiv preprint arXiv:2501.04003 (2025)","DOI":"10.1109\/ICCV51701.2025.00621"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Xuan, W., et al.: DynamicVL: Benchmarking multimodal large language models for dynamic city understanding. arXiv preprint (2025). arXiv:2505.21076 (2025)","DOI":"10.52202\/085713-1114"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: How multimodal large language models see, remember, and recall spaces. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Yin, S., Fu, C., Zhao, S., Li, K., Sun, X., Xu, T., Chen, E.: A survey on multimodal large language models. National Sci. Rev. 11(12), nwae403 (2024)","DOI":"10.1093\/nsr\/nwae403"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: VLDrive: Vision-augmented lightweight MLLMs for efficient language-grounded autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5923\u20135933 (2025)","DOI":"10.1109\/ICCV51701.2025.00560"},{"key":"10_CR45","unstructured":"Zhang, S., et al.: Open eyes, then reason: Fine-grained visual mathematical understanding in mllms. arXiv preprint arXiv:2501.06430 (2025)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, W., Cai, M., Zhang, T., Zhuang, Y., Li, J., Mao, X.: EarthMarker: A visual prompting multi-modal large language model for remote sensing. IEEE Trans. Geosci. Remote Sensing (2024)","DOI":"10.1109\/TGRS.2024.3523505"},{"key":"10_CR47","unstructured":"Zhang, X., Ouyang, T., Shang, Y., Liao, Q., Li, Y.: UrbanMLLM: Joint learning of cross-view imagery for urban understanding. In: Forty-third International Conference on Machine Learning (2026). https:\/\/openreview.net\/forum?id=Av10FtirO4"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Nie, Y.: Interndrive: A multimodal large language model for autonomous driving scenario understanding. In: Proceedings of the 2024 4th International Conference on Artificial Intelligence, Automation and High Performance Computing, pp. 294\u2013305 (2024)","DOI":"10.1145\/3690931.3690982"},{"key":"10_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, B., et al.: Embodied-r: Collaborative framework for activating embodied spatial reasoning in foundation models via reinforcement learning. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 11071\u201311080 (2025)","DOI":"10.1145\/3746027.3755703"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Cityeqa: A hierarchical LLM agent on embodied question answering benchmark in city space. In: EMNLP (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.630"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Urbench: A comprehensive benchmark for evaluating large multimodal models in multi-view urban scenarios. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 10707\u201310715 (2025)","DOI":"10.1609\/aaai.v39i10.33163"}],"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\/978-3-032-37016-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:59:08Z","timestamp":1789124348000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37016-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370150","9783032370167"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37016-7_10","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":"12 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RoadBench is intended solely for academic research and benchmark evaluation. The FPV street-view images are obtained from AMAP with authorization for research use and public release, and all released images have undergone privacy screening, including the removal or blurring of personally identifiable information such as recognizable faces and license plates. We also randomize all sample IDs into UUIDs and convert geographic coordinates into image-level pixel coordinates. The BEV satellite images are based on Google satellite imagery; to support reproducibility while respecting commercial imagery constraints, we provide region-image mappings, geographic coordinates, image filenames, acquisition instructions, construction scripts, prompts, evaluation code, and raw model outputs, enabling users to obtain or reconstruct the images without their own Google API key or paid Google Maps Platform account. Since online map services may update imagery over time, we document the data provenance and provide consistency checks for diagnosing noticeable deviations from the benchmark reference version. RoadBench focuses on five Chinese cities with relatively consistent traffic conventions, and should not be directly used for operational, enforcement, or safety-critical decisions without further ethical review, fairness assessment, and domain-specific validation.","order":1,"name":"Ethics","label":"Data Ethics and Reproducibility","group":{"name":"EthicsHeading","label":"Ethics"}},{"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"}}]}}