{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:02:39Z","timestamp":1790154159924,"version":"4.0.1"},"reference-count":95,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11263-026-02980-3","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:01:08Z","timestamp":1787940068000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes"],"prefix":"10.1007","volume":"134","author":[{"given":"Zhaoyang","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xumeng","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuehui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guorong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-5152","authenticated-orcid":false,"given":"Zhenjun","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"2980_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J. B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., Menick, J., Borgeaud, S., Brock, A., Nematzadeh, A., Sharifzadeh, S., Bin kowski, M., Barreira, R., Vinyals, O., Zisserman, A., & Simonyan, K. (2022). Flamingo: A visual language model for few-shot learning. NeurIPS,35(23), 716\u201323. 736.","DOI":"10.52202\/068431-1723"},{"key":"2980_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015). Vqa: Visual question answering. Proceedings of the IEEE international conference on computer vision (pp. 2425\u20132433)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2980_CR3","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C. & Zhou, J. (2023). Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. Preprint retrieved from arXiv:2308.12966"},{"key":"2980_CR4","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., Zhong, H., Zhu, Y., Yang, M., Li, Z., Wan, J., Wang, P., Ding, W., Fu, Z., Xu, Y., Ye, J., Zhang, X., Xie, T., Cheng, Z., Zhang, H., Yang, Z., Xu, H., & Lin, J. (2025). Qwen2. 5-vl technical report. Preprint retrieved from arXiv:2502.13923"},{"key":"2980_CR5","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. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11621\u201311631)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2980_CR6","unstructured":"Cao, M., Zhao, H., Zhang, C., Chang, X., Reid, I., & Liang, X. (2025). Ground-r1: Incentivizing grounded visual reasoning via reinforcement learning arXiv:2505.20272 Preprint retrieved from."},{"key":"2980_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., Xu, Z., Kirmani, S., Ichter, B., Sadigh, D., Guibas, L., & Xia, F. (2024a). Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14,455\u201314,465","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"2980_CR8","unstructured":"Chen, K., Thapa, R., Chalamala, R., Athiwaratkun, B., Song, S. L.,& Zou, J. (2024b). Dragonfly: Multi-resolution zoom supercharges large visual-language model. Preprint retrieved from arXiv e-prints pp arXiv\u20132406"},{"key":"2980_CR9","doi-asserted-by":"crossref","unstructured":"Chen, K.., Li, Y.., Zhang, W.., Liu, Y., Li, P., Gao, R., Hong, L., Tian, M., Zhao, X., Li, Z., Yeung, D-Y., Lu H., & Jia X. (2025a). Automated evaluation of large vision-language models on self-driving corner cases. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, pp 7817\u20137826","DOI":"10.1109\/WACV61041.2025.00759"},{"key":"2980_CR10","unstructured":"Chen, L., Li, L., Zhao, H., & Song, Y. (2025b). R1-v: Reinforcing super generalization ability in vision-language models with less than $3"},{"key":"2980_CR11","unstructured":"Chen, X., Wu, Z., Liu, X., Pan, Z., Liu, W., Xie, Z., Yu, X., & Ruan, C. (2025c). Janus-pro: Unified multimodal understanding and generation with data and model scaling. Preprint retrieved from arXiv:2501.17811"},{"key":"2980_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Y., & Zhang, Z. (2024c). Drivinggpt: Unifying driving world modeling and planning with multi-modal autoregressive transformers. Preprint retrieved from arXiv:2412.18607","DOI":"10.1109\/ICCV51701.2025.02496"},{"key":"2980_CR13","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z., Gu, L., Wang, X., Li, Q., Ren, Y., Chen, Z., Luo, J., Wang, J., Jiang, T., Wang, B., He, C., Shi, B., Zhang, X., Lv, H., Wang, Y., Shao, W., Chu, P., Tu, Z., He, T., Wu, Z., Deng, H., Ge, J., Chen, K., Zhang, K., Wang, L., Dou, M., Lu, L., Zhu, X., Lu, T., Lin, D., Qiao, Y., Dai, J., & Wang, W. (2024d). Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. Preprint retrieved from arXiv:2412.05271"},{"issue":"12","key":"2980_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., Wang, W., Tian, H., Ye, S., Gao, Z., Cui, E., Tong, W., Hu, K., Luo, J., Ma, Z., Ma, J., Wang, J., Dong, X., Yan, H., Guo, H., He, C., Shi, B., Jin, Z., Xu, C., \u2026 Wang, W. (2024). How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. Science China Information Sciences, 67(12), Article 220101.","journal-title":"Science China Information Sciences"},{"key":"2980_CR15","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., Li, B., Luo, P., Lu, T., Qiao, Y., & Dai, J. (2024f). 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","DOI":"10.1109\/CVPR52733.2024.02283"},{"issue":"1","key":"2980_CR16","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1109\/TIV.2023.3327715","volume":"9","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Huang, S., Zhong, J., Liu, Z., Wang, Y., Sun, C., Li, B., Wang, X., & Khajepour, A. (2024). Drivellm: Charting the path toward full autonomous driving with large language models. IEEE Transactions on Intelligent Vehicles, 9(1), 1450\u20131464. https:\/\/doi.org\/10.1109\/TIV.2023.3327715","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"2980_CR17","unstructured":"DeepMind, G. (2025a). Gemini-2.5-flash. Preprint retrieved from https:\/\/deepmind.google\/models\/gemini\/flash\/"},{"key":"2980_CR18","unstructured":"DeepMind, G. (2025b). Gemini-2.5-pro. Retrieved from https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"2980_CR19","doi-asserted-by":"crossref","unstructured":"Dong, Y., Liu, Z., Sun, H. L., Yang, J., Hu, W., Rao, Y., & Liu, Z. (2024). Insight-v: Exploring long-chain visual reasoning with multimodal large language models. Preprint retrieved from arXiv:2411.14432","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"2980_CR20","doi-asserted-by":"crossref","unstructured":"Duan, H., Yang, J., Qiao, Y., Fang, X., Chen, L., Liu, Y., Dong, X., Zang, Y., Zhang, P., W., & J. (2024). Vlmevalkit: An open-source toolkit for evaluating large multi-modality models. Proceedings of the 32nd ACM international conference on multimedia (pp. 11198\u201311201)","DOI":"10.1145\/3664647.3685520"},{"key":"2980_CR21","doi-asserted-by":"crossref","unstructured":"Fan, Y., He, X., Yang, D., Zheng, K., Kuo, C. C., Zheng, Y., Narayanaraju, S. J, Guan, X., & Wang, X. E. (2025). Grit: Teaching mllms to think with images. Preprint retrieved from arXiv:2505.15879","DOI":"10.52202\/085713-3884"},{"key":"2980_CR22","unstructured":"Fu, C., Zhang, Y-F., Yin, S., Li, B., Fang, X., Zhao, S., Duan, H., Sun, X., Liu, Z., Wang, L., Shan, C., & He, R. (2024a). Mme-survey: A comprehensive survey on evaluation of multimodal llms. Preprint retrieved from arXiv:2411.15296"},{"key":"2980_CR23","doi-asserted-by":"crossref","unstructured":"Fu, C., Chen, P., Shen, Y., Qin, Y., Zhang, M., Lin, X., Yang, J., Zheng, X., Li, K., Sun, X., Wu, Y., Ji, R., Shan, C., & He, R. (2025a). Mme: A comprehensive evaluation benchmark for multimodal large language models. In: The Thirty-ninth annual conference on neural information processing systems datasets and benchmarks track","DOI":"10.52202\/085713-4899"},{"key":"2980_CR24","doi-asserted-by":"crossref","unstructured":"Fu, D., Li, X., Wen, L., Dou, M., Cai, P., Shi, B., Qiao, Y. (2024b). Drive like a human: Rethinking autonomous driving with large language models. In: IEEE\/CVF winter conference on applications of computer vision, pp 910\u2013919","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"2980_CR25","unstructured":"Fu, X., Liu, M., Yang, Z., Corring, J., Lu, Y., Yang, J., Roth, D., Florencio, D., & Zhang, C. (2025b). Refocus: Visual editing as a chain of thought for structured image understanding. Preprint retrieved from arXiv:2501.05452"},{"key":"2980_CR26","doi-asserted-by":"crossref","unstructured":"Guan, T., Liu, F., Wu, X., Xian, R., Li, Z., Liu, X., Wang, X., Chen, L., Huang, F., Yacoob, Y., Manocha, D., & Zhou, T. (2024). Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: CVPR","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"2980_CR27","doi-asserted-by":"crossref","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., Zhu, Q., Xu, R., Zhang, R., Ma, S., Bi, X., Zhang, X., Yu, X., Wu, Y., Wu, Z. F., Gou, Z., Shao, Z., Li, Z., Gao, Z., Liu, A., Xue, B., Wang, B., Wu, B., Feng, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., Dai, D., Chen, D., Ji, D., Li, E., Lin, F., Dai, F., Luo, F., Hao, G., Chen, G., Li, G., Zhang, H., Bao, H., Xu, H., Wang, H., Ding, H., Gao, H., Qu, H., Li, H., Guo, J., Li, J., Chen, J., Yuan, J., Tu, J., Qiu, J., Li, J., Cai, J. L., Ni, J., Liang, J., Chen, J., Dong, K., Hu, K., You, K., Gao, K., Guan, K., Huang, K., Yu, K., Wang, L., Zhang, L., Zhao, L., Wang, L., Zhang, L., Xu, L., Xia, L., Zhang, M., Zhang, M., Tang, M., Zhou, M., Li, M., Wang, M., Li, M., Tian, N., Huang, P., Zhang, P., Wang, Q., Chen, Q., Du, Q., Ge, R., Zhang, R., Pan, R., Wang, R., Chen, R. J., Jin, R. L., Chen, R., Lu, S., Zhou, S., Chen, S., Ye, S., Wang, S., Yu, S., Zhou, S., Pan, S., Li, S. S., Zhou, S., Wu, S., Yun, T., Pei, T., Sun, T., Wang, T., Zeng, W., Liu, W., Liang, W., Gao, W., Yu, W., Zhang, W., Xiao, W. L., An, W., Liu, X., Wang, X., Chen, X., Nie, X., Cheng, X., Liu, X., Xie, X., Liu, X., Yang, X., Li, X., Su, X., Lin, X., Li, X. Q., Jin, X., Shen, X., Chen, X., Sun, X., Wang, X., Song, X., Zhou, X., Wang, X., Shan, X., Li, Y. K., Wang, Y. Q., Wei, Y. X., Zhang, Y., Xu, Y., Li, Y., Zhao, Y., Sun, Y., Wang, Y., Yu, Y., Zhang, Y., Shi, Y., Xiong, Y., He, Y., Piao, Y., Wang, Y., Tan, Y., Ma, Y., Liu, Y., Guo, Y., Ou, Y., Wang, Y., Gong, Y., Zou, Y., He, Y., Xiong, Y., Luo, Y., You, Y., Liu, Y., Zhou, Y., Zhu, Y. X., Huang, Y., Li, Y., Zheng, Y., Zhu, Y., Ma, Y., Tang, Y., Zha, Y., Yan, Y., Ren, Z. Z., Ren, Z., Sha, Z., Fu, Z., Xu, Z., Xie, Z., Zhang, Z., Hao, Z., Ma, Z., Yan, Z., Wu, Z., Gu, Z., Zhu, Z., Liu, Z., Li, Z., Xie, Z., Song, Z., Pan, Z., Huang, Z., Xu, Z., Zhang, Z., & Zhang, Z. (2025). Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. Preprint retrieved from arXiv:2501.12948","DOI":"10.1038\/s41586-025-09422-z"},{"key":"2980_CR28","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s10579-020-09517-1","volume":"55","author":"T Hiippala","year":"2021","unstructured":"Hiippala, T., Alikhani, M., Haverinen, J., Kalliokoski, T., Logacheva, E., Orekhova, S., Tuomainen, A., Stone, M., & Bateman, J. A. (2021). Ai2d-rst: A multimodal corpus of 1000 primary school science diagrams. Language Resources and Evaluation, 55, 661\u2013688.","journal-title":"Language Resources and Evaluation"},{"key":"2980_CR29","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, W., Lv, Q., Xu, J., Yu, W., Ji, J., Wang, Y., Wang, Z., Dong, Y., Ding, M., & Tang, J. (2024). Cogagent: A visual language model for GUI agents. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 14281\u201314290","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"2980_CR30","unstructured":"Huang, W., Jia, B., Zhai, Z., Cao, S., Ye, Z., Zhao, F., Xu, Z., Hu, Y., L., & S. (2025). Vision-r1: Incentivizing reasoning capability in multimodal large language models arXiv:2503.06749 Preprint retrieved from."},{"key":"2980_CR31","doi-asserted-by":"crossref","unstructured":"Inoue, Y., Yada, Y., Tanahashi, K., Y., & Y. (2024). Nuscenes-mqa: Integrated evaluation of captions and QA for autonomous driving datasets using markup annotations. Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 930\u2013938)","DOI":"10.1109\/WACVW60836.2024.00104"},{"key":"2980_CR32","unstructured":"Kenk, M. A., & Hassaballah, M. (2020). Dawn: vehicle detection in adverse weather nature dataset arXiv:2008.05402 Preprint retrieved from."},{"key":"2980_CR33","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., & A. (2018). Textual explanations for self-driving vehicles. Z, ECCV.","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"2980_CR34","doi-asserted-by":"crossref","unstructured":"Li, B., Ge, Y., Ge, Y., Wang, G., Wang, R., Zhang, R., & Shan, Y. (2024a). Seed-bench: Benchmarking multimodal large language models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp 13299\u201313308)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"2980_CR35","unstructured":"Li, F., Zhang, R., Zhang, H., Zhang, Y., Li, B., Li, W., Ma, Z., & Li, C. (2024b). Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. Preprint retrieved from arXiv:2407.07895"},{"key":"2980_CR36","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023a). BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning (ICML). Preprint retrieved from arXiv:2301.12597"},{"key":"2980_CR37","doi-asserted-by":"crossref","unstructured":"Li, K., Chen, K., Wang, H., Hong, L., Ye, C., Han, J., Chen, Y., Zhang, W., Xu, C., Yeung, D-Y., Liang, X., Li, Z., & Xu, H. (2022). Coda: A real-world road corner case dataset for object detection in autonomous driving. In: European Conference on Computer Vision, Springer, pp 406\u2013423","DOI":"10.1007\/978-3-031-19839-7_24"},{"key":"2980_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W. X., & Wen, J. R. (2023b). Evaluating object hallucination in large vision-language models. Preprint retrieved from arXiv:2305.10355","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"2980_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). (pp. 740\u2013755) Microsoft coco: Common objects in context, ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2980_CR40","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. NeurIPS, 36, 34892\u201334916.","journal-title":"Visual instruction tuning. NeurIPS"},{"key":"2980_CR41","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., & Lee, Y. J. (2024a). Improved baselines with visual instruction tuning. In: IEEE\/CVF conference on computer vision and pattern recognition (pp 26296\u201326306)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"2980_CR42","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., & Lee, Y. J. (2024b). Llava-next: Improved reasoning, OCR, and world knowledge. Retrieved from https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"2980_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., Chen, K., & Lin, D. (2023b). Mmbench: Is your multi-modal model an all-around player? Preprint retrieved from arXiv:2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"2980_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., Chen, K., & Lin, D. (2024c). Mmbench: Is your multi-modal model an all-around player? In: European conference on computer vision, Springer, pp 216\u2013233","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"2980_CR45","unstructured":"Liu, Y., Qu, T., Zhong, Z., Peng, B., Liu, S., Yu, B., & Jia, J. (2025a). Visionreasoner: Unified visual perception and reasoning via reinforcement learning. Preprint retrieved from arXiv:2505.12081"},{"key":"2980_CR46","unstructured":"Liu, Z., Dong, Y., Rao, Y., Zhou, J., & Lu, J. (2024d). Chain-of-spot: Interactive reasoning improves large vision-language models. Preprint retrieved from arXiv:2403.12966"},{"key":"2980_CR47","unstructured":"Liu, Z., Dong, Y., Rao, Y., Zhou, J., & Lu, J. (2024e). Chain-of-spot: Interactive reasoning improves large vision-language models. Preprint retrieved from arXiv:2403.12966"},{"key":"2980_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Z., Sun, Z., Zang, Y., Dong, X., Cao, Y., Duan, H., Lin, D., & Wang, J. (2025b). Visual-rft: Visual reinforcement fine-tuning. Preprint retrieved from arXiv:2503.01785","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"2980_CR49","unstructured":"Lu, P., Bansal, H., Xia, T., Liu, J., Li, C., Hajishirzi, H., Cheng, H., Chang, K. W., Galley, M., & Gao, J. (2023). Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts arXiv:2310.02255 Preprint retrieved from."},{"key":"2980_CR50","doi-asserted-by":"crossref","unstructured":"Marcu, A. M., Chen, L., H\u00fcnermann, J., Karnsund, A., Hanotte, B., Chidananda, P., Nair, S., Badrinarayanan, V., Kendall, A., & Shotton, J. (2024). Lingoqa: Visual question answering for autonomous driving. European Conference on Computer Vision (pp. 252\u2013269). Springer.","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"2980_CR51","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D. X., Tan, J. Q., Joty, S., & Hoque, E. (2022). Chartqa: A benchmark for question answering about charts with visual and logical reasoning arXiv:2203.10244 Preprint retrieved from.","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"2980_CR52","unstructured":"Meng, F., Du, L., Liu, Z., Zhou, Z., Lu, Q., Fu, D., Han, T., Shi, B., Wang, W., & He, J. (2025). Mm-eureka: Exploring the frontiers of multimodal reasoning with rule-based reinforcement learning arXiv:2503.07365 Preprint retrieved from."},{"key":"2980_CR53","doi-asserted-by":"crossref","unstructured":"Mondal, D., Modi, S., Panda, S., Singh, R., & Rao, G. S. (2024). Kam-cot: Knowledge augmented multimodal chain-of-thoughts reasoning (pp. 18798\u201318806). AAAI.","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"2980_CR54","unstructured":"OpenAI. (2024a). Openai-gpt-4o. Retrieved from https:\/\/openai.com\/index\/gpt-4o-system-card\/"},{"key":"2980_CR55","unstructured":"OpenAI. (2024b). Openai-o1. Retrieved from https:\/\/openai.com\/o1\/"},{"key":"2980_CR56","unstructured":"OpenAI. (2025). Openai-o3. Retrieved from https:\/\/openai.com\/index\/introducing-o3-and-o4-mini\/"},{"key":"2980_CR57","unstructured":"Peng, Y., Zhang, G., Zhang, M., You, Z., Liu, J., Zhu, Q., Yang, K., Xu, X., Geng, X., & Yang, X. (2025). Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl. Preprint retrieved from arXiv:2503.07536"},{"key":"2980_CR58","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. Proceedings of the AAAI Conference on Artificial Intelligence (pp. 4542\u20134550)","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"2980_CR59","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Goh, R. A., Agarwal, G., Sastry, S., Askell, G., Mishkin, A., Clark, P., & J. (2021). Learning transferable visual models from natural language supervision. ICML (pp. 8748\u20138763)"},{"key":"2980_CR60","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., & Van Gool, L. (2021). Acdc: The adverse conditions dataset with correspondences for semantic driving scene understanding. Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10765\u201310775)","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"2980_CR61","doi-asserted-by":"publisher","first-page":"8612","DOI":"10.52202\/079017-0275","volume":"37","author":"H Shao","year":"2024","unstructured":"Shao, H., Qian, S., Xiao, H., Song, G., Zong, Z., Wang, L., Liu, Y., & Li, H. (2024). Visual-cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. Advances in Neural Information Processing Systems, 37, 8612\u20138642.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2980_CR62","unstructured":"Shen, H., Liu, P., Li, J., Fang, C., Ma, Y., Liao, J., Shen, Q., Zhang, Z., Zhao, K., Zhang, Q., Xu, R., & Zhao, T. (2025). Vlm-r1: A stable and generalizable r1-style large vision-language model. Preprint retrieved from arXiv:2504.07615"},{"key":"2980_CR63","doi-asserted-by":"crossref","unstructured":"Sima, C., Renz, K., Chitta, K., Chen, L., Zhang, H., Xie, C., Bei\u00dfwenger, J., Luo, P., Geiger, A., & Li, H. (2024). Drivelm: Driving with graph visual question answering. European Conference on Computer Vision (pp. 256\u2013274)","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"2980_CR64","unstructured":"Stone, A., Xiao, T., Lu, Y., Gopalakrishnan, K., Lee, K. H., Vuong, Q., Wohlhart, P., Kirmani, S., Zitkovich, B., & Xia, F. (2023). Open-world object manipulation using pre-trained vision-language models arXiv:2303.00905 Preprint retrieved from."},{"key":"2980_CR65","doi-asserted-by":"crossref","unstructured":"Su, A., Wang, H., Ren, W., Lin, F., C., & W. (2025). Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning arXiv:2505.15966 Preprint retrieved from.","DOI":"10.52202\/085713-0280"},{"key":"2980_CR66","unstructured":"Tian, X., Gu, J., Li, B., Liu, Y., Wang, Y., Zhao, Z., Zhan, K., Jia, P., Lang, X., Zhao, H. (2024). Drivevlm: The convergence of autonomous driving and large vision-language models. Preprint retrieved from arXiv:2402.12289"},{"key":"2980_CR67","doi-asserted-by":"crossref","unstructured":"Tong, P., Brown, E., Wu, P., Woo, S., IYER, A. J. V., Akula, S. C., Yang, S., Yang, J., Middepogu, M., & Wang, Z. (2024). Cambrian-1:A fully open, vision-centric exploration of multimodal llms. NeurIPS,37(87), 310\u201387. 356.","DOI":"10.52202\/079017-2771"},{"key":"2980_CR68","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., & Xie, S. (2024b). Eyes wide shut? exploring the visual shortcomings of multimodal llms. In: CVPR. pp 9568\u20139578","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"2980_CR69","unstructured":"Wang, H., Li, X., Huang, Z., Wang, A., Wang, J., Zhang, T., Zheng, J., Bai, S., Kang, Z., Feng, J., Wang, Z., & Zhang Z. (2025a). Traceable evidence enhanced visual grounded reasoning: Evaluation and methodology. Preprint retrieved from arXiv:2507.07999"},{"key":"2980_CR70","doi-asserted-by":"crossref","unstructured":"Wang, J., Wu, B., Jiang, H., Xun, Z., Xiao, X., Guo, H., & Xiao, J. (2024a). World to code: Multi-modal data generation via self-instructed compositional captioning and filtering. In: Proceedings of the 2024 conference on empirical methods in natural language processing, pp 4608\u20134623","DOI":"10.18653\/v1\/2024.emnlp-main.265"},{"key":"2980_CR71","unstructured":"Wang, J., Kang, Z., Wang, H., Jiang, H., Li, J., Wu, B., Wang, Y., Ran, J., Liang, X., Feng, C., & Xiao, J. (2025b). VGR: Visual grounded reasoning. Preprint retrieved from arXiv:2506.11991"},{"key":"2980_CR72","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., Fan, Y., Dang, K., Du, M., Ren, X., Men, R., Liu, D., Zhou, C., Zhou, J., & Lin, J. (2024b). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. Preprint retrieved from arXiv:2409.12191"},{"key":"2980_CR73","doi-asserted-by":"crossref","unstructured":"Wang, W., Ding, L., Zeng, M., Zhou, X., Shen, L., Luo, Y., Yu, W., & Tao, D. (2025c). Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models. In: AAAI, pp 7907\u20137915","DOI":"10.1609\/aaai.v39i8.32852"},{"key":"2980_CR74","unstructured":"Wei, L., Li, Y., Wang, C., Wang, Y., Kong, L., Huang, W., & Sun, L. (2025a). Unsupervised post-training for multi-modal llm reasoning via grpo. Preprint retrieved from arXiv:2505.22453"},{"key":"2980_CR75","unstructured":"Wei, L., Li, Y., Zheng, K., Wang, C., Wang, Y., Kong, L., Sun, L., & Huang, W. (2025b). Advancing multimodal reasoning via reinforcement learning with cold start. Preprint retrieved from arXiv:2505.22334"},{"key":"2980_CR76","unstructured":"Wu, D., Han, W., Wang, T., Liu, Y., Zhang, X., & Shen, J. (2023). Language prompt for autonomous driving arXiv:2309.04379 Preprint retrieved from."},{"key":"2980_CR77","doi-asserted-by":"crossref","unstructured":"Wu, P., & Xie, S. (2024a). V?: Guided visual search as a core mechanism in multimodal llms. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13084\u201313094","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"2980_CR78","doi-asserted-by":"crossref","unstructured":"Wu, P., & Xie, S. (2024b). V*: Guided visual search as a core mechanism in multimodal llms. In: CVPR, pp 13084\u201313094","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"2980_CR79","unstructured":"Wu, Z., Chen, X., Pan, Z., Liu, X., Liu, W., Dai, D., Gao, H., Ma, Y., Wu, C., Wang, B., Xie, Z., Wu, Y., Hu, K., Wang, J., Sun, Y., Li, Y., Piao, Y., Guan, K., Liu, A., Xie, X., You, Y., Dong, K., Yu, X., Zhang, H., Zhao, L., Wang, Y., & Ruan, C. (2024). Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. Preprint retrieved from arXiv:2412.10302"},{"key":"2980_CR80","unstructured":"xAI. (2024). Grok."},{"key":"2980_CR81","unstructured":"Xing, S., Hua, H., Gao, X., Zhu, S., Li, R., Tian, K., Li, X., Huang, H., Yang, T., Wang, Z., Zhou, Y., Yao, H., & Tu, Z. (2024). Autotrust: Benchmarking trustworthiness in large vision language models for autonomous driving. Preprint retrieved from arXiv:2412.15206"},{"key":"2980_CR82","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yang, X., Gong, L., Lin, H. C., Wu, T. Y., Li, Y., & Vasconcelos, N. (2020). Explainable object-induced action decision for autonomous vehicles. IEEE\/CVF conference on computer vision and pattern recognition (pp. 9523\u20139532)","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"2980_CR83","unstructured":"Xu, Y., Hu, Y., Zhang, Z., Meyer, G. P., Mustikovela, S. K., Srinivasa, S., Wolff, E. M., & Huang, X. (2024). Vlm-ad: End-to-end autonomous driving through vision-language model supervision. Preprint retrieved from arXiv:2412.14446"},{"key":"2980_CR84","doi-asserted-by":"crossref","unstructured":"Yang, J., Dong, Y., Liu, S., Li, B., Wang, Z., Tan, H., Jiang, C., Kang, J., Zhang, Y., & Zhou, K. (2025). Octopus: Embodied vision-language programmer from environmental feedback. European conference on computer vision (pp. 20\u201338). Springer.","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"2980_CR85","unstructured":"Yao, Y., Yu, T., Zhang, A., Wang, C., Cui, J., Zhu, H., Cai, T., Li, H., Zhao, W., & He, Z. (2024). Minicpm-v: A gpt-4v level mllm on your phone arXiv:2408.01800 Preprint retrieved from."},{"key":"2980_CR86","unstructured":"Ye, J., Xu, H., Liu, H., Hu, A., Yan, M., Qian, Q., Zhang, J., Huang, F., & Zhou, J. (2024). mplug-owl3: Towards long image-sequence understanding in multi-modal large language models. Preprint retrieved from arXiv:2408.04840"},{"key":"2980_CR87","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2636\u20132645","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"2980_CR88","unstructured":"Yu, W., Yang, Z., Li, L., Wang, J., Lin, K., Liu, Z., Wang, X., & Wang, L. (2023). Mm-vet: Evaluating large multimodal models for integrated capabilities. Preprint retrieved from arXiv:2308.02490"},{"key":"2980_CR89","doi-asserted-by":"crossref","unstructured":"Yue, X., Ni, Y., Zhang, K., Zheng, T., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., Sun, Y., Wei, C., Yu, B., Yuan, R., Sun, R., Yin, M., Zheng, B., Yang, Z., Liu, Y., Huang, W., Sun, H., Su, Y., & Chen, W. (2024). Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: CVPR","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"2980_CR90","unstructured":"Zhang, Y-F., Zhang, H., Tian, H., Fu, C., Zhang, S., Wu, J., Li, F., Wang, K., Wen, Q., Zhang, Z., Wang, L., Jin, R., & Tan, T. (2024). Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenarios that are difficult for humans?. Preprint retrieved from arXiv:2408.13257"},{"key":"2980_CR91","doi-asserted-by":"publisher","first-page":"29733","DOI":"10.1609\/aaai.v39i28.35383","volume":"39","author":"Y Zhao","year":"2025","unstructured":"Zhao, Y., Huang, J., Hu, J., Wang, X., Mao, Y., Zhang, D., Jiang, Z., Wu, Z., Ai, B., Wang, A., Zhou, W., & Chen, Y. (2025). Swift: a scalable lightweight infrastructure for fine-tuning. Proceedings of the AAAI Conference on Artificial Intelligence, 39, 29733\u201329735.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2980_CR92","unstructured":"Zheng, Y., Lu, J., Wang, S., Feng, Z., Kuang, D., & Xiong, Y. (2025a). Easyr1: An efficient, scalable, multi-modality training framework. Retrieved from https:\/\/github.com\/hiyouga\/EasyR1"},{"key":"2980_CR93","unstructured":"Zheng, Z., Yang, M., Hong, J., Zhao, C., Xu, G., Yang, L., Shen, C., & Yu, X. (2025b). Deepeyes: Incentivizing\" thinking with images\" via reinforcement learning. Preprint retrieved from arXiv:2505.14362"},{"key":"2980_CR94","unstructured":"Zhu, J., Wang, W., Chen, Z., Liu, Z., Ye, S., Gu, L., Tian, H., Duan, Y., Su, W., & Shao, J. (2025). Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models arXiv:2504.10479 Preprint retrieved from."},{"issue":"11","key":"2980_CR95","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. (2021). Detection and tracking meet drones challenge. IEEE TPAMI, 44(11), 7380\u20137399.","journal-title":"IEEE TPAMI"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02980-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02980-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02980-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:15:34Z","timestamp":1790151334000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02980-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":95,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["2980"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02980-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"assertion":[{"value":"13 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"413"}}