{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T16:10:14Z","timestamp":1788883814803,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374462","type":"print"},{"value":"9783032374479","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\/978-3-032-37447-9_8","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:47:23Z","timestamp":1788882443000},"page":"135-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViewFusion: Structured Spatial Thinking Chains for\u00a0Multi-view Reasoning"],"prefix":"10.1007","author":[{"given":"Xingjian","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"8_CR3","unstructured":"Bai, S., et al.: Qwen3-VL technical report (2025). https:\/\/arxiv.org\/abs\/2511.21631"},{"key":"8_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"8_CR5","unstructured":"Batra, H., et al.: Spatialthinker: reinforcing 3D reasoning in multimodal LLMs via spatial rewards. arXiv preprint arXiv:2511.07403 (2025)"},{"key":"8_CR6","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, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, K., et al.: Seeclick: Harnessing GUI grounding for advanced visual GUI agents. arXiv preprint arXiv:2401.10935 (2024)","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Dong, Y., et al.: Insight-v: exploring long-chain visual reasoning with multimodal large language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9062\u20139072 (2025)","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"8_CR9","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. arXiv preprint arXiv:2505.20279 (2025)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-r1: reinforcing video reasoning in MLLMs. arXiv preprint arXiv:2503.21776 (2025)","DOI":"10.52202\/085713-3310"},{"key":"8_CR11","unstructured":"Gholami, Met al.: Spatial reasoning with vision-language models in ego-centric multi-view scenes. arXiv preprint arXiv:2509.06266 (2025)"},{"key":"8_CR12","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"8_CR13","unstructured":"Guo, Z., Hong, M., Jin, T.: Observe-r1: Unlocking reasoning abilities of MLLMs with dynamic progressive reinforcement learning. arXiv preprint arXiv:2505.12432 (2025)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Hong, W., et\u00a0al.: Cogagent: a visual language model for GUI agents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14281\u201314290 (2024)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"8_CR15","unstructured":"Huang, W., et al.: Vision-r1: incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749 (2025)"},{"key":"8_CR16","unstructured":"Lee, K., et al.: Spatialmosaic: a multiview VLM dataset for partial visibility. arXiv preprint arXiv:2512.23365 (2025)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Topviewrs: vision-language models as top-view spatial reasoners. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1786\u20131807 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.106"},{"key":"8_CR18","unstructured":"Li, D., et\u00a0al.: Viewspatial-bench: evaluating multi-perspective spatial localization in vision-language models. arXiv preprint arXiv:2505.21500 (2025)"},{"key":"8_CR19","unstructured":"Li, F., et al.: Llava-next-interleave: tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)"},{"key":"8_CR20","unstructured":"Li, H., et al.: Spatialladder: progressive training for spatial reasoning in vision-language models. arXiv preprint arXiv:2510.08531 (2025)"},{"key":"8_CR21","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1162\/tacl_a_00566","volume":"11","author":"F Liu","year":"2023","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguist. 11, 635\u2013651 (2023)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Proceedings of the Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"8_CR25","unstructured":"Ouyang, K., et al.: Spacer: reinforcing MLLMs in video spatial reasoning. arXiv preprint arXiv:2504.01805 (2025)"},{"key":"8_CR26","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world, (2023). arXiv:2306.14824 arXiv preprint"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Sun, Z., et\u00a0al.: Aligning large multimodal models with factually augmented RLHF. In: Proceedings of the Findings of the Association for Computational Linguistics: ACL 2024, pp. 13088\u201313110 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Tao, X., et al.: Mitigating coordinate prediction bias from positional encoding failures. arXiv preprint arXiv:2510.22102 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.1034"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Tao, X., Wang, Y., Cai, Y., Yang, Z., Tang, J.: Understanding GUI agent localization biases through logit sharpness. In: Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 23361\u201323374 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.1268"},{"key":"8_CR30","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"8_CR31","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., et\u00a0al.: Cambrian-1: A fully open, vision-centric exploration of multimodal llms. Advances in Neural Information Processing Systems 37, 87310\u201387356 (2024)","DOI":"10.52202\/079017-2771"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Wang, F., Luo, N., Wu, W.: Visioncube: 3D-aware vision-language model for multi-step spatial reasoning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3270\u20133279 (2025)","DOI":"10.1109\/CVPRW67362.2025.00309"},{"key":"8_CR33","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"8_CR34","unstructured":"Wang, W., et\u00a0al.: Video-str: Reinforcing MLLMs in video spatio-temporal reasoning with relation graph. arXiv preprint arXiv:2510.10976 (2025)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yoon, J., Yu, S., Islam, M.M., Bertasius, G., Bansal, M.: Video-RTS: rethinking reinforcement learning and test-time scaling for efficient and enhanced video reasoning. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 28114\u201328128 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1428"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence. arXiv preprint arXiv:2505.23747 (2025)","DOI":"10.52202\/085713-0457"},{"key":"8_CR37","unstructured":"Wu, H., et al.: Spatialscore: towards comprehensive evaluation for spatial intelligence. arXiv preprint arXiv:2505.17012 (2025)"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Reinforcing spatial reasoning in vision-language models with interwoven thinking and visual drawing. arXiv preprint arXiv:2506.09965 (2025)","DOI":"10.52202\/085713-4797"},{"key":"8_CR39","unstructured":"Xia, J., Zang, Y., Gao, P., Li, S., Zhou, K.: Visionary-r1: mitigating shortcuts in visual reasoning with reinforcement learning. arXiv preprint arXiv:2505.14677 (2025)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, G., Xu, X., Kan, M.Y.: V-DPO: mitigating hallucination in large vision language models via vision-guided direct preference optimization. arXiv preprint arXiv:2411.02712 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.775"},{"key":"8_CR41","unstructured":"Yang, Q., et al.: Humanomniv2: from understanding to omni-modal reasoning with context. arXiv preprint arXiv:2506.21277 (2025)"},{"key":"8_CR42","unstructured":"Yang, R., et\u00a0al.: Visual spatial tuning. arXiv preprint arXiv:2511.05491 (2025)"},{"key":"8_CR43","unstructured":"Yang, S., et\u00a0al.: Cambrian-s: Towards spatial supersensing in video. arXiv preprint arXiv:2511.04670 (2025)"},{"key":"8_CR44","unstructured":"Yang, S., et\u00a0al.: MMSI-bench: a benchmark for multi-image spatial intelligence. arXiv preprint arXiv:2505.23764 (2025)"},{"key":"8_CR45","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. In: Proceedings of the Structural Priors for Vision Workshop at ICCV\u201925 (2025)"},{"key":"8_CR46","unstructured":"Yu, S., et\u00a0al.: How far are VLMs from visual spatial intelligence? a benchmark-driven perspective. arXiv preprint arXiv:2509.18905 (2025)"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: RLHF-V: towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13807\u201313816 (2024)","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"8_CR48","unstructured":"Yu, T., et al.: Rlaif-v: Aligning MLLMs through open-source ai feedback for super GPT-4v trustworthiness 2(3), 8. arXiv preprint arXiv:2405.17220 (2024)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: R1-VL: learning to reason with multimodal large language models via step-wise group relative policy optimization. arXiv preprint arXiv:2503.12937 (2025)","DOI":"10.1109\/ICCV51701.2025.00181"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Sphere: unveiling spatial blind spots in vision-language models through hierarchical evaluation. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 11591\u201311609 (2025)","DOI":"10.18653\/v1\/2025.acl-long.568"},{"key":"8_CR51","unstructured":"Zhao, R., et al.: Spacemind: camera-guided modality fusion for spatial reasoning in vision-language models. arXiv preprint arXiv:2511.23075 (2025)"},{"key":"8_CR52","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-37447-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:47:34Z","timestamp":1788882454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37447-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374462","9783032374479"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37447-9_8","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":"9 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"}}]}}