{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:11:06Z","timestamp":1788851466174,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370945","type":"print"},{"value":"9783032370952","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\/978-3-032-37095-2_21","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:01:44Z","timestamp":1788850904000},"page":"374-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Coevolving Representations in\u00a0Joint Image-Feature Diffusion"],"prefix":"10.1007","author":[{"given":"Theodoros","family":"Kouzelis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spyros","family":"Gidaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikos","family":"Komodakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"issue":"209","key":"21_CR1","first-page":"1","volume":"26","author":"M Albergo","year":"2025","unstructured":"Albergo, M., Boffi, N.M., Vanden-Eijnden, E.: Stochastic interpolants: a unifying framework for flows and diffusions. J. Mach. Learn. Res. 26(209), 1\u201380 (2025)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR2","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VicReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"8799","DOI":"10.52202\/068431-0640","volume":"35","author":"A Bardes","year":"2022","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICREGL: self-supervised learning of local visual features. Adv. Neural. Inf. Process. Syst. 35, 8799\u20138810 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR4","unstructured":"Black forest labs: FLUX.2: analyzing and enhancing the latent space of FLUX \u2013 representation comparison (2025). https:\/\/bfl.ai\/research\/representation-comparison"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233444273","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"21_CR6","unstructured":"Chen, B., et al.: Aligning visual foundation encoders to tokenizers for diffusion models. ICLR (2026)"},{"key":"21_CR7","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_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PmLR (2020)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9620\u20139629 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233024948","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"21_CR11","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_CR12","unstructured":"Ermolov, A., Siarohin, A., Sangineto, E., Sebe, N.: Whitening for self-supervised representation learning. In: International Conference on Machine Learning, pp. 3015\u20133024. PMLR (2021)"},{"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","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR15","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":"21_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"21_CR17","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR18","unstructured":"Huang, J., Kumar, R., Mitra, M., Zhu, W.J., Zabih, R.: Image indexing using color correlograms. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 762\u2013768 (1997). https:\/\/api.semanticscholar.org\/CorpusID:9317935"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Karypidis, E., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: Dino-foresight: looking into the future with DINO. arXiv preprint arXiv:2412.11673 (2024)","DOI":"10.52202\/085713-5466"},{"key":"21_CR20","unstructured":"Kouzelis, T., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: EQ-VAE: equivariance regularized latent space for improved generative image modeling. In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=UWhW5YYLo6"},{"key":"21_CR21","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":"21_CR22","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"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 with latent diffusion transformers (2025). arXiv preprint arXiv:2504.10483","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":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"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 (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":"Nash, C., Menick, J., Dieleman, S., Battaglia, P.W.: Generating images with sparse representations. arXiv preprint arXiv:2103.03841 (2021)"},{"key":"21_CR30","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"21_CR31","unstructured":"Pan, Y., et al.: Semantics lead the way: harmonizing semantic and texture modeling with asynchronous latent diffusion. arXiv preprint arXiv:2512.04926 (2025)"},{"key":"21_CR32","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_CR33","unstructured":"Petsangourakis, G., Sgouropoulos, C., Psomas, B., Giannakopoulos, T., Sfikas, G., Kakogeorgiou, I.: Reglue your latents with global and local semantics for entangled diffusion. arXiv preprint arXiv:2512.16636 (2025)"},{"key":"21_CR34","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":"21_CR35","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) International Conference on Medical image computing and computer-assisted intervention, pp. 234\u2013241. Springer (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21_CR36","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"21_CR37","unstructured":"Shi, M., et al.: Latent diffusion model without variational autoencoder. arXiv preprint arXiv:2510.15301 (2025)"},{"key":"21_CR38","unstructured":"Shi, M., et al.: Latent diffusion model without variational autoencoder. ICLR abs\/2510.15301 (2026). https:\/\/api.semanticscholar.org\/CorpusID:282203316"},{"key":"21_CR39","unstructured":"Singh, J., et al.: What matters for representation alignment: global information or spatial structure? arXiv preprint. arXiv:2512.10794 (2025)"},{"key":"21_CR40","unstructured":"Teng, J., et al.: Relay diffusion: unifying diffusion process across resolutions for image synthesis. arXiv preprint arXiv:2309.03350 (2023)"},{"key":"21_CR41","unstructured":"Tong, S., et al.: Scaling text-to-image diffusion transformers with representation autoencoders. arXiv preprint arXiv:2601.16208 (2026)"},{"key":"21_CR42","unstructured":"Tschannen, M., et al.: SigLip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"21_CR43","unstructured":"Venkataramanan, S., et al.: Franca: nested matryoshka clustering for scalable visual representation learning. arXiv preprint arXiv:2507.14137 (2025)"},{"key":"21_CR44","unstructured":"Wang, S., Gao, Z., Zhu, C., Huang, W., Wang, L.: PIXNERD: pixel neural field diffusion. arXiv preprint arXiv:2507.23268 (2025)"},{"key":"21_CR45","unstructured":"Wang, S., Tian, Z., Huang, W., Wang, L.: DDT: decoupled diffusion transformer. arXiv preprint arXiv:2504.05741 (2025)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Wu, G., et\u00a0al.: Representation entanglement for generation: training diffusion transformers is much easier than you think. arXiv preprint arXiv:2507.01467 (2025)","DOI":"10.52202\/085713-0264"},{"key":"21_CR47","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":"21_CR48","unstructured":"Yu, S., et al.: Representation alignment for generation: Training diffusion transformers is easier than you think. In: International Conference on Learning Representations (2025)"},{"key":"21_CR49","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: Self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310\u201312320. PMLR (2021)"},{"key":"21_CR50","unstructured":"Zhai, S., et al.: Normalizing flows are capable generative models. arXiv preprint arXiv:2412.06329 (2024)"},{"key":"21_CR51","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. arXiv preprint arXiv:2510.11690 (2025)"},{"key":"21_CR52","unstructured":"Zheng, K., Chen, Y., Mao, H., Liu, M.Y., Zhu, J., Zhang, Q.: Masked diffusion models are secretly time-agnostic masked models and exploit inaccurate categorical sampling. arXiv preprint arXiv:2409.02908 (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\/978-3-032-37095-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:01:54Z","timestamp":1788850914000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37095-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370945","9783032370952"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37095-2_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":"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"}}]}}