{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T13:24:30Z","timestamp":1792070670634,"version":"4.4.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376268","type":"print"},{"value":"9783032376275","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\/978-3-032-37627-5_36","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:02:45Z","timestamp":1788984165000},"page":"661-678","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Scalable Pre-training of\u00a0Visual Tokenizers for\u00a0Generation"],"prefix":"10.1007","author":[{"given":"Jingfeng","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuda","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"36_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"36_CR3","unstructured":"Chefer, H., et al.: VideoJAM: joint appearance-motion representations for enhanced motion generation in video models. arXiv preprint arXiv:2502.02492 (2025)"},{"key":"36_CR4","unstructured":"Chen, B., et al.: Aligning visual foundation encoders to tokenizers for diffusion models. In: The Fourteenth International Conference on Learning Representations (2025)"},{"key":"36_CR5","unstructured":"Chen, H., et al.: Masked autoencoders are effective tokenizers for diffusion models. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"36_CR6","unstructured":"Chen, J., et\u00a0al.: BLIP3-o: a family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv:2505.09568 (2025)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"36_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"36_CR9","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"36_CR11","unstructured":"Hansen-Estruch, P., et al.: Learnings from scaling visual tokenizers for reconstruction and generation. arXiv preprint arXiv:2501.09755 (2025)"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Henry, A., Dachapally, P.R., Pawar, S.S., Chen, Y.: Query-key normalization for transformers. In: Findings of the Association for Computational Linguistics, EMNLP 2020, pp. 4246\u20134253 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"36_CR15","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenClip, July 2021. https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"36_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"36_CR17","unstructured":"Kouzelis, T., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: EQ-VAE: equivariance regularized latent space for improved generative image modeling. arXiv preprint arXiv:2502.09509 (2025)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Kouzelis, T., Karypidis, E., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: Boosting generative image modeling via joint image-feature synthesis. arXiv preprint arXiv:2504.16064 (2025)","DOI":"10.52202\/085713-0563"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Leng, X., Singh, J., Hou, Y., Xing, Z., Xie, S., Zheng, L.: REPA-E: unlocking VAE for end-to-end tuning with latent diffusion transformers. arXiv preprint arXiv:2504.10483 (2025)","DOI":"10.1109\/ICCV51701.2025.01697"},{"key":"36_CR20","unstructured":"Li, X., Qiu, K., Chen, H., Kuen, J., Gu, J., Raj, B., Lin, Z.: ImageFolder: autoregressive image generation with folded tokens. arXiv preprint arXiv:2410.01756 (2024)"},{"key":"36_CR21","first-page":"129274","volume":"38","author":"C Ma","year":"2026","unstructured":"Ma, C., et al.: UniTok: a unified tokenizer for visual generation and understanding. Adv. Neural. Inf. Process. Syst. 38, 129274\u2013129297 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR22","doi-asserted-by":"publisher","unstructured":"Ma, N., Goldstein, M., Albergo, M.S., Boffi, N.M., Vanden-Eijnden, E., Xie, S.: SiT: exploring flow and diffusion-based generative models with scalable interpolant transformers. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision, ECCV 2024. LNCS, vol. 15135, pp. 23\u201340. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72980-5_2","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"36_CR23","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"36_CR25","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"36_CR26","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":"36_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, p. 28 (2015)"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"36_CR29","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"36_CR30","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"36_CR31","unstructured":"Singh, J., et al.: What matters for representation alignment: global information or spatial structure? arXiv preprint arXiv:2512.10794 (2025)"},{"key":"36_CR32","unstructured":"Skorokhodov, I., et al.: Improving the diffusability of autoencoders. arXiv preprint arXiv:2502.14831 (2025)"},{"key":"36_CR33","unstructured":"Teng, H., et\u00a0al.: MAGI-1: autoregressive video generation at scale. arXiv preprint arXiv:2505.13211 (2025)"},{"key":"36_CR34","unstructured":"Wang, S., Tian, Z., Huang, W., Wang, L.: DDT: decoupled diffusion transformer. arXiv preprint arXiv:2504.05741 (2025)"},{"key":"36_CR35","unstructured":"Wu, Y., et al.: VILA-U: a unified foundation model integrating visual understanding and generation. In: International Conference on Learning Representations, vol. 2025, pp. 93620\u201393638 (2025)"},{"key":"36_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"36_CR37","unstructured":"Xie, E., et\u00a0al.: SANA: efficient high-resolution image synthesis with linear diffusion transformers. arXiv preprint arXiv:2410.10629 (2024)"},{"key":"36_CR38","unstructured":"Yang, J., Li, T., Fan, L., Tian, Y., Wang, Y.: Latent denoising makes good visual tokenizers. arXiv preprint arXiv:2507.15856 (2025)"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Yao, J., Yang, B., Wang, X.: Reconstruction vs. generation: taming optimization dilemma in latent diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15703\u201315712 (2025)","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"36_CR40","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. arXiv preprint arXiv:2410.06940 (2024)"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"36_CR43","unstructured":"Zheng, A., et al.: Vision foundation models as effective visual tokenizers for autoregressive image generation. arXiv preprint arXiv:2507.08441 (2025)"},{"key":"36_CR44","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. arXiv preprint arXiv:2510.11690 (2025)"},{"key":"36_CR45","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"}],"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\/978-3-032-37627-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:02:54Z","timestamp":1788984174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37627-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376268","9783032376275"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37627-5_36","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":"10 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"}}]}}