{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:21Z","timestamp":1788934041884,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372314","type":"print"},{"value":"9783032372321","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\/978-3-032-37232-1_21","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:51:57Z","timestamp":1788933117000},"page":"380-398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["V-Co: A Closer Look at\u00a0Visual Representation Alignment via\u00a0Co-Denoising"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1303-8636","authenticated-orcid":false,"given":"Han","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xichen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9502-050X","authenticated-orcid":false,"given":"Zun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-6536","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-6169","authenticated-orcid":false,"given":"Jaemin","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2965-5354","authenticated-orcid":false,"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"21_CR1","unstructured":"Baade, A., et al.: Latent forcing: Reordering the diffusion trajectory for pixel-space image generation. arXiv preprint arXiv:2602.11401 (2026)"},{"key":"21_CR2","unstructured":"Bi, H., et al.: Motus: A unified latent action world model. arXiv preprint arXiv:2512.13030 (2025)"},{"key":"21_CR3","unstructured":"Chang, H., Cha, B., Ye, J.C.: Dino-sae: Dino spherical autoencoder for high-fidelity image reconstruction and generation. arXiv preprint arXiv:2601.22904 (2026)"},{"key":"21_CR4","unstructured":"Chefer, H., et al.: Videojam: Joint appearance-motion representations for enhanced motion generation in video models. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"21_CR5","unstructured":"Chen, S., Ge, C., Zhang, S., Sun, P., Luo, P.: Pixelflow: Pixel-space generative models with flow. arXiv preprint arXiv:2504.07963 (2025)"},{"key":"21_CR6","unstructured":"Chen, Z., et al.: Dip: Taming diffusion models in pixel space. arXiv preprint arXiv:2511.18822 (2025)"},{"key":"21_CR7","unstructured":"Crowson, K., Baumann, S.A., Birch, A., Abraham, T.M., Kaplan, D.Z., Shippole, E.: Scalable high-resolution pixel-space image synthesis with hourglass diffusion transformers. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"21_CR8","unstructured":"Dang, L., et al.: Syncmv4d: Synchronized multi-view joint diffusion of appearance and motion for hand-object interaction synthesis. arXiv preprint arXiv:2511.19319 (2025)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Dang, L., Shao, R., Zhang, H., Min, W., Liu, Y., Wu, Q.: Svimo: Synchronized diffusion for video and motion generation in hand-object interaction scenarios. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-2574"},{"key":"21_CR10","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":"21_CR11","unstructured":"Deng, M., Li, H., Li, T., Du, Y., He, K.: Generative modeling via drifting. arXiv preprint arXiv:2602.04770 (2026)"},{"key":"21_CR12","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR13","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first international conference on machine learning, (2024)"},{"key":"21_CR14","unstructured":"Han, X., et al.: Tv2tv: A unified framework for interleaved language and video generation. arXiv preprint arXiv:2512.05103 (2025)"},{"key":"21_CR15","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: simple diffusion: End-to-end diffusion for high resolution images. In: International Conference on Machine Learning, pp. 13213\u201313232. PMLR (2023)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Hoogeboom, E., Mensink, T., Heek, J., Lamerigts, K., Gao, R., Salimans, T.: Simpler diffusion: 1.5 fid on imagenet512 with pixel-space diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18062\u201318071 (2025)","DOI":"10.1109\/CVPR52734.2025.01683"},{"key":"21_CR17","unstructured":"Hu, Z., Lai, C.H., Wu, G., Mitsufuji, Y., Ermon, S.: Meanflow transformers with representation autoencoders. arXiv preprint arXiv:2511.13019 (2025)"},{"key":"21_CR18","unstructured":"Huang, J., et al.: Unityvideo: Unified multi-modal multi-task learning for enhancing world-aware video generation. arXiv preprint arXiv:2512.07831 (2025)"},{"key":"21_CR19","unstructured":"Jabri, A., Fleet, D.J., Chen, T.: Scalable adaptive computation for iterative generation. In: International Conference on Machine Learning, pp. 14569\u201314589. PMLR (2023)"},{"key":"21_CR20","doi-asserted-by":"publisher","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) European Conference on Computer Vision, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"21_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Kouzelis, T., Karypidis, E., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: Boosting generative image modeling via joint image-feature synthesis. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0563"},{"key":"21_CR23","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 of latent diffusion transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18262\u201318272 (2025)","DOI":"10.1109\/ICCV51701.2025.01697"},{"key":"21_CR24","unstructured":"Li, T., He, K.: Back to basics: Let denoising generative models denoise. arXiv preprint arXiv:2511.13720 (2025)"},{"key":"21_CR25","unstructured":"Li, T., Sun, Q., Fan, L., He, K.: Fractal generative models. arXiv preprint arXiv:2502.17437 (2025)"},{"key":"21_CR26","unstructured":"Lu, Y., et al.: One-step latent-free image generation with pixel mean flows. arXiv preprint arXiv:2601.22158 (2026)"},{"key":"21_CR27","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.) European Conference on Computer Vision, 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":"21_CR28","unstructured":"Ma, Z., Wei, L., Wang, S., Zhang, S., Tian, Q.: Deco: Frequency-decoupled pixel diffusion for end-to-end image generation. arXiv preprint arXiv:2511.19365 (2025)"},{"key":"21_CR29","unstructured":"Ma, Z., Xu, R., Zhang, S.: Pixelgen: Pixel diffusion beats latent diffusion with perceptual loss. arXiv preprint arXiv:2602.02493 (2026)"},{"key":"21_CR30","unstructured":"Oquab, M., et al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"21_CR31","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":"21_CR32","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR33","unstructured":"Singh, J., et al.: What Matters for Representation Alignment: Global Information or Spatial Structure? arXiv preprint, arXiv:2512.10794 (2025)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Tian, Y., Chen, H., Zheng, M., Liang, Y., Xu, C., Wang, Y.: U-repa: Aligning diffusion u-nets to vits. arXiv preprint arXiv:2503.18414 (2025)","DOI":"10.52202\/085713-0369"},{"key":"21_CR35","unstructured":"Tong, S., et al.: Scaling text-to-image diffusion transformers with representation autoencoders. arXiv preprint arXiv:2601.16208 (2026)"},{"key":"21_CR36","unstructured":"Tschannen, M., Pinto, A.S., Kolesnikov, A.: Jetformer: An autoregressive generative model of raw images and text. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"21_CR37","unstructured":"Wang, M., et al.: Vae-repa: Variational autoencoder representation alignment for efficient diffusion training. arXiv preprint arXiv:2601.17830 (2026)"},{"key":"21_CR38","unstructured":"Wang, S., Gao, Z., Zhu, C., Huang, W., Wang, L.: Pixnerd: Pixel neural field diffusion. arXiv preprint arXiv:2507.23268 (2025)"},{"key":"21_CR39","unstructured":"Wang, S., Tian, Z., Huang, W., Wang, L.: Ddt: Decoupled diffusion transformer. arXiv preprint arXiv:2504.05741 (2025)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: Repa works until it doesn\u2019t: Early-stopped, holistic alignment supercharges diffusion training. arXiv preprint arXiv:2505.16792 (2025)","DOI":"10.52202\/085713-4568"},{"key":"21_CR41","unstructured":"Wu, J., et al.: Does hearing help seeing? investigating audio-video joint denoising for video generation. arXiv preprint arXiv:2512.02457 (2025)"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Yang, L., Qi, L., Li, X., Li, S., Jampani, V., Yang, M.H.: Unified dense prediction of video diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28963\u201328973 (2025)","DOI":"10.1109\/CVPR52734.2025.02697"},{"key":"21_CR43","unstructured":"Yang, Y., et al.: Echomotion: Unified human video and motion generation via dual-modality diffusion transformer. arXiv preprint arXiv:2512.18814 (2025)"},{"key":"21_CR44","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"21_CR45","unstructured":"Yu, Y., Xiong, W., Nie, W., Sheng, Y., Liu, S., Luo, J.: Pixeldit: Pixel diffusion transformers for image generation. arXiv preprint arXiv:2511.20645 (2025)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Videorepa: Learning physics for video generation through relational alignment with foundation models. arXiv preprint arXiv:2505.23656 (2025)","DOI":"10.52202\/085713-4091"},{"key":"21_CR47","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. arXiv preprint arXiv:2510.11690 (2025)"},{"key":"21_CR48","unstructured":"Zheng, R., et al.: Flare: Robot learning with implicit world modeling. arXiv preprint arXiv:2505.15659 (2025)"},{"key":"21_CR49","unstructured":"Zhong, Z., et\u00a0al.: Flowvla: Visual chain of thought-based motion reasoning for vision-language-action models. arXiv preprint arXiv:2508.18269 (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\/978-3-032-37232-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:52:10Z","timestamp":1788933130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37232-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372314","9783032372321"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37232-1_21","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"}}]}}