{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T18:46:21Z","timestamp":1789757181620,"version":"4.0.1"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368386","type":"print"},{"value":"9783032368393","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\/978-3-032-36839-3_19","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:30:26Z","timestamp":1789317026000},"page":"339-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training"],"prefix":"10.1007","author":[{"given":"Fangfu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diankun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimo","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Hsin","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xumin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongming","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"19_CR1","unstructured":"Aky\u00fcrek, E., et al.: The surprising effectiveness of test-time training for few-shot learning. In: Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 267, pp. 942\u2013963. PMLR (2025)"},{"key":"19_CR2","unstructured":"Ba, J., Hinton, G.E., Mnih, V.: Using fast weights to attend to the recent past. NeurIPS (2016)"},{"key":"19_CR3","unstructured":"Bai, S., et al.: Qwen3-VL Technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"19_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL Technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"19_CR5","unstructured":"Baruch, G., et al.: ArkitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. arXiv preprint arXiv:2111.08897 (2021)"},{"key":"19_CR6","unstructured":"Behrouz, A., et al.: ATLAS: learning to optimally memorize the context at test time (2025). https:\/\/arxiv.org\/abs\/2505.23735"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Behrouz, A., Razaviyayn, M., Zhong, P., Mirrokni, V.: Nested Learning: the illusion of deep learning architectures. arXiv:2512.24695 arXiv preprint (2025)","DOI":"10.52202\/085713-1565"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Behrouz, A., Zhong, P., Mirrokni, V.: Titans: Learning to memorize at test time. arXiv preprint arXiv:2501.00663 (2024)","DOI":"10.52202\/085713-3786"},{"key":"19_CR9","unstructured":"Bytedance Seed: Seed2.0 model card: towards intelligence frontier for real-world complexity. Technical report Bytedance (2025),.https:\/\/lf3-static.bytednsdoc.com\/obj\/eden-cn\/lapzild-tss\/ljhwZthlaukjlkulzlp\/seed2\/0214\/Seed2.0%20Model%20Card.pdf\/. Accessed 29 June 2026"},{"key":"19_CR10","unstructured":"Cai, Z., et al.: Scaling spatial intelligence with multimodal foundation models (2025). https:\/\/arxiv.org\/abs\/2511.13719"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Spatial-VLM: endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"19_CR12","unstructured":"Chen, Z., et al.: Think with 3D: geometric imagination grounded spatial reasoning from limited views. arXiv preprint arXiv:2510.18632 (2025)"},{"key":"19_CR13","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":"19_CR14","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"19_CR15","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 (ICCV), pp. 7395\u20137408 (2025)","DOI":"10.1109\/ICCV51701.2025.00694"},{"key":"19_CR16","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., et\u00a0al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. Nature 645, 633\u2013638 (2025). https:\/\/doi.org\/10.1038\/s41586-025-09422-z","DOI":"10.1038\/s41586-025-09422-z"},{"key":"19_CR17","unstructured":"Driess, D., Xia, F., Sajjadi, M.S.M., Lynch, C., Chowdhery, A., Ichter, B.: PaLM-E: an embodied multimodal language model. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"19_CR18","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. arXiv preprint arXiv:2505.20279 (2025)"},{"key":"19_CR19","unstructured":"Fu, C., Chen, P., Shen, Y., Qin, Y., Zhang, M., Lin, X.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Gandelsman, Y., Sun, Y., Chen, X., Efros, A.A.: Test-time training with masked autoencoders. NeurIPS (2022)","DOI":"10.52202\/068431-2130"},{"key":"19_CR21","unstructured":"Google: a new era of intelligence with Gemini 3. https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3. Accessed 29 June 2026"},{"key":"19_CR22","unstructured":"Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)"},{"key":"19_CR23","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-VL Technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Hong, Y., Zhen, H.: 3D-LLM: injecting the 3D world into large language models. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-0900"},{"key":"19_CR25","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 (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"19_CR26","unstructured":"Huang, W., Wang, C., Li, Y., Zhang, R., Fei-Fei, L.: Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation. arXiv preprint arXiv:2409.01652 (2024)"},{"key":"19_CR27","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Jia, B., et al.: SceneVerse: Scaling 3D vision-language learning for grounded scene understanding. In: European Conference on Computer Vision, pp. 289\u2013310. Springer (2024)","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"19_CR29","unstructured":"Jordan, K., Jin, Y., Boza, V., You, J., Cesista, F., Newhouse, L., Bernstein, J.: Muon: An optimizer for hidden layers in neural networks (2024). https:\/\/kellerjordan.github.io\/posts\/muon\/. Accessed 29 June 2026"},{"key":"19_CR30","unstructured":"Karami, M., Mirrokni, V.: Lattice: learning to efficiently compress the memory. arXiv preprint arXiv:2504.05646 (2025)"},{"key":"19_CR31","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"19_CR32","unstructured":"Li, H., et al.: SpatialLadder: progressive training for spatial reasoning in vision-language models. arXiv preprint arXiv:2510.08531 (2025)"},{"key":"19_CR33","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning. pp. 19730\u201319742. PMLR (2023)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., He, Y.: MVBench: a comprehensive multi-modal video understanding benchmark, CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Li, M., Wang, Y.X., Ramanan, D.: Towards streaming perception. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58536-5_28"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, M.: ManipLLM: Embodied multimodal large language model for object-centric robotic manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: STI-Bench: are MLLMs ready for precise spatial-temporal world understanding? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 25332\u201325342 (2025)","DOI":"10.1109\/ICCV51701.2025.00533"},{"issue":"1","key":"19_CR38","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s11263-024-02181-w","volume":"133","author":"J Liang","year":"2024","unstructured":"Liang, J., He, R., Tan, T.: A comprehensive survey on test-time adaptation under distribution shifts. Int. J. Comput. Vision 133(1), 31\u201364 (2024). https:\/\/doi.org\/10.1007\/s11263-024-02181-w","journal-title":"Int. J. Comput. Vision"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-LLaVA: learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-1516"},{"key":"19_CR41","unstructured":"OpenAI: openAI o1 system card. Technical report OpenAI (2024). https:\/\/openai.com\/index\/openai-o1-system-card\/. Accessed 29 June 2026"},{"key":"19_CR42","unstructured":"OpenAI: GPT-5 System Card. Technical report, OpenAI (2025). Accessed 10 Aug 2025"},{"key":"19_CR43","unstructured":"Ouyang, K., et al.: SpaceR: reinforcing MLLMs in video spatial reasoning. arXiv preprint arXiv:2504.01805 (2025)"},{"key":"19_CR44","unstructured":"Schlag, I., Irie, K., Schmidhuber, J.: Linear transformers are secretly fast weight programmers. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 9355\u20139366. PMLR (2021)"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Shu, M., Nie, W., Huang, D.A.: Test-time prompt tuning for zero-shot generalization in vision-language models. In: NeurIPS (2022)","DOI":"10.52202\/068431-1038"},{"key":"19_CR46","unstructured":"Snell, C., Jaeckle, L., Li, R., Kumar, A., Levine, S.: Scaling LLM test-time compute optimally can be more effective than scaling parameters. In: Proceedings of the 41st International Conference on Machine Learning (ICML) (2024)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"19_CR48","unstructured":"Sun, Y., Dong, X., Menon, S., Schwab, D., Kolter, J.Z.: Learning to (learn at test time): Rnns with expressive hidden states. arXiv preprint arXiv:2407.04620 (2024)"},{"key":"19_CR49","unstructured":"Sun, Y., et al.: Learning to (Learn at Test Time): RNNs with expressive hidden states. In: Proceedings of the 41st International Conference on Machine Learning (ICML) (2024). https:\/\/arxiv.org\/abs\/2407.04620"},{"key":"19_CR50","unstructured":"Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A., Hardt, M.: Test-time training with self-supervision for generalization under distribution shifts. In: International Conference on Machine Learning, pp. 9229\u20139248. PMLR (2020)"},{"key":"19_CR51","unstructured":"Sun, Y., et al.: Retentive Network: a successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)"},{"key":"19_CR52","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"19_CR53","unstructured":"Team, K., et al.: Kimi K2.5: visual agentic intelligence (2026). https:\/\/arxiv.org\/abs\/2602.02276"},{"key":"19_CR54","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"19_CR55","unstructured":"Wang, D., Shelhamer, E., Liu, S.: Tent: Fully test-time adaptation by entropy minimization, p. ICLR (2021)"},{"key":"19_CR56","unstructured":"Wang, K.A., Shi, J., Fox, E.B.: Test-Time Regression: a unifying framework for designing sequence models with associative memory. arXiv preprint arXiv:2501.12352 (2025)"},{"key":"19_CR57","unstructured":"Wei, W., Luo, Z., Feng, L., Liong, V.E.: Spatial-aware vision language model for autonomous driving. arXiv preprint arXiv:2512.24331 (2025)"},{"key":"19_CR58","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":"19_CR59","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":"19_CR60","unstructured":"xAI: Grok 4. https:\/\/x.ai\/news\/grok-4. Accessed 29 June 2026"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Zhang, T.: PointLLM: empowering large language models to understand point clouds, CVPR (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"19_CR62","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"19_CR63","unstructured":"Yang, R., et\u00a0al.: Visual spatial tuning. arXiv preprint arXiv:2511.05491 (2025)"},{"key":"19_CR64","unstructured":"Yang, S., et al.: Cambrian-S: towards spatial supersensing in video (2025). https:\/\/arxiv.org\/abs\/2511.04670"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: a high-fidelity dataset of 3d indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12\u201322 (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"19_CR66","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. In: Structural Priors for Vision Workshop at ICCV\u201925 (2025)"},{"key":"19_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Flash-Vstream: memory-based real-time understanding for long video streams. arXiv preprint arXiv:2406.08085 (2024)","DOI":"10.1109\/ICCV51701.2025.01957"},{"key":"19_CR68","unstructured":"Zhang, P., et al.: Long context transfer from language to vision. arXiv preprint arXiv:2406.16852 (2024)"},{"key":"19_CR69","unstructured":"Zhang, T., et al.: Test-time training done right. arXiv preprint arXiv:2505.23884 (2025). https:\/\/arxiv.org\/abs\/2505.23884"},{"key":"19_CR70","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\/978-3-032-36839-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:30:39Z","timestamp":1789317039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36839-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368386","9783032368393"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36839-3_19","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":"14 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"}}]}}