{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T06:06:04Z","timestamp":1789452364209,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374899","type":"print"},{"value":"9783032374905","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\/978-3-032-37490-5_20","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:53:35Z","timestamp":1789451615000},"page":"355-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ProLaViT: Learning Progressive Latent Visual Thoughts in\u00a0Structured Latent Space"],"prefix":"10.1007","author":[{"given":"Peiming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"20_CR1","unstructured":"Bai, J., et al.: Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond (2023)"},{"key":"20_CR2","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S.: Qwen2.5-VL technical report (2025)"},{"key":"20_CR3","unstructured":"Chern, E., Su, J., Ma, Y., Liu, P.: Anole: An open, autoregressive, native large multimodal models for interleaved image-text generation. arXiv preprint arXiv:2407.06135 (2024)"},{"key":"20_CR4","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"20_CR5","unstructured":"Dong, R., et al.: DreamLLM: Synergistic multimodal comprehension and creation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"20_CR6","unstructured":"Dong, S., Wang, S., Liu, X., Li, C., Hou, H., Wei, Z.: Interleaved latent visual reasoning with selective perceptual modeling. arXiv preprint arXiv:2512.05665 (2025)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: Multimodal large language models can see but not perceive. ArXiv: abs\/2404.12390 (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"20_CR8","unstructured":"Ge, Y., et al.: Making llama see and draw with seed tokenizer. arXiv preprint arXiv:2310.01218 (2023)"},{"key":"20_CR9","unstructured":"Gu, J., et al.: Thinkmorph: Emergent properties in multimodal interleaved chain-of-thought reasoning (2025)"},{"key":"20_CR10","unstructured":"Hao, S., et al.: Training large language models to reason in a continuous latent space (2024). ArXiv: abs\/2412.06769"},{"key":"20_CR11","unstructured":"Hao, Y., et al.: Can mllms reason in multimodality? emma: An enhanced multimodal reasoning benchmark. arXiv preprint arXiv:2501.05444 (2025)"},{"key":"20_CR12","unstructured":"Jiang, D., et\u00a0al.: MME-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency. arXiv preprint arXiv:2502.09621 (2025)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3992\u20134003 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Koh, J.Y., Fried, D., Salakhutdinov, R.: Generating images with multimodal language models, (2023)","DOI":"10.52202\/075280-0939"},{"key":"20_CR15","unstructured":"Li, A., et\u00a0al.: Zebra-cot: A dataset for interleaved vision language reasoning. arXiv preprint arXiv:2507.16746 (2025)"},{"key":"20_CR16","unstructured":"Li, B., et al.: Latent visual reasoning. ArXiv:abs\/2509.24251 (2025)"},{"key":"20_CR17","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. ArXiv:abs\/2304.08485 (2023)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Chameleon: Plug-and-play compositional reasoning with large language models (2023). ArXiv:abs\/2304.09842","DOI":"10.52202\/075280-1882"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S.R., Hoque, E.: ChartQA: A benchmark for question answering about charts with visual and logical reasoning (2022). ArXiv:abs\/2203.10244","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"20_CR20","unstructured":"OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L.: GPT-4 technical report (2024)"},{"key":"20_CR21","unstructured":"Oquab, M., et al.: Dinov2: Learning robust visual features without supervision. ArXiv:abs\/2304.07193 (2023)"},{"key":"20_CR22","unstructured":"Podell, D., : SDXL: Improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: Chain-of-visual-thought: Teaching VLMs to see and think better with continuous visual tokens (2025)","DOI":"10.1007\/978-3-032-37359-5_25"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Shao, H., et al.: Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. Adv. Neural. Inf. Process. Syst. 37 (2024)","DOI":"10.52202\/079017-0275"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: Solving ai tasks with ChatGPT and its friends in hugging face (2023)","DOI":"10.52202\/075280-1657"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Shen, Z., Yan, H., Zhang, L., Hu, Z., Du, Y., He, Y.: Codi: Compressing chain-of-thought into continuous space via self-distillation. arXiv preprint arXiv:2502.21074 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.36"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGpt: Visual inference via python execution for reasoning (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"20_CR28","unstructured":"Team, C.: CVBench: A benchmark for cross-video multimodal reasoning (2025)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., Xie, S.: Eyes wide shut? exploring the visual shortcomings of multimodal LLMs. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9568\u20139578 (2024)","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"20_CR30","unstructured":"Wang, Q., et al.: Monet: Reasoning in latent visual space beyond images and language. arXiv preprint arXiv:2511.21395 (2025)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. ArXiv:abs\/2201.11903 (2022)","DOI":"10.52202\/068431-1800"},{"key":"20_CR32","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual ChatGpt: Talking, drawing and editing with visual foundation models (2023)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V*: Guided visual search as a core mechanism in multimodal LLMs. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13084\u201313094 (2023)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Xu, G., et al.: LLaVA-CoT: Let vision language models reason step-by-step. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2087\u20132098 (2025)","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: Unleashing the power of large-scale unlabeled data. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"20_CR36","unstructured":"Yang, Z., Yu, X., Chen, D., Shen, M., Gan, C.: Machine mental imagery: Empower multimodal reasoning with latent visual tokens. ArXiv: abs\/2506.17218 (2025)"},{"key":"20_CR37","unstructured":"Yang, Z., et al.: MM-REACT: Prompting chatGpt for multimodal reasoning and action (2023)"},{"key":"20_CR38","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models (2024)"}],"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\/978-3-032-37490-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:53:49Z","timestamp":1789451629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37490-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374899","9783032374905"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37490-5_20","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":"16 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"}}]}}