{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T03:17:00Z","timestamp":1791170220141,"version":"4.1.0"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","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\/978-3-032-37577-3_37","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:02:25Z","timestamp":1788994945000},"page":"679-697","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SimFlow: Simplified and\u00a0End-to-End Training of\u00a0Latent Normalizing Flows"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0245-1676","authenticated-orcid":false,"given":"Qinyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9276-5956","authenticated-orcid":false,"given":"Guangting","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4371-9847","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-247X","authenticated-orcid":false,"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3342-4541","authenticated-orcid":false,"given":"Xingjian","family":"Leng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8929-7899","authenticated-orcid":false,"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-9500","authenticated-orcid":false,"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: A vit backbone for diffusion models. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 22669\u201322679 (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"37_CR2","unstructured":"Bhattacharyya, A., Hanselmann, M., Fritz, M., Schiele, B., Straehle, C.N.: Conditional flow variational autoencoders for structured sequence prediction. arXiv preprint arXiv:1908.09008 (2019)"},{"key":"37_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Represent (2019)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: International Conference Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"37_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":"37_CR6","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: Diverse image synthesis for multiple domains. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"37_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: IEEE Conference on Computer Vision Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"37_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural Inform. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR9","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"37_CR10","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. In: International Conference on Learning Representions (2017)"},{"key":"37_CR11","unstructured":"Draxler, F., Sorrenson, P., Zimmermann, L., Rousselot, A., K\u00f6the, U.: Free-form flows: Make any architecture a normalizing flow. In: International Conference on Artificial Intelligence and Statistics, pp. 2197\u20132205. PMLR (2024)"},{"key":"37_CR12","unstructured":"Draxler, F., Wahl, S., Schnoerr, C., Koethe, U.: On the universality of volume-preserving and coupling-based normalizing flows. In: International Conference on Machine Learning, pp. 11613\u201311641. PMLR (2024)"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, P., Cheng, M.M., Yan, S.: Mdtv2: Masked diffusion transformer is a strong image synthesizer. arXiv preprint arXiv:2303.14389 (2023)","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"37_CR14","first-page":"22104","volume":"33","author":"R Giaquinto","year":"2020","unstructured":"Giaquinto, R., Banerjee, A.: Gradient boosted normalizing flows. Adv. Neural Inform. Process. Syst. 33, 22104\u201322117 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR15","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. Adv. Neural Inform. Process. Syst. 27 (2014)"},{"key":"37_CR16","first-page":"120986","volume":"38","author":"J Gu","year":"2026","unstructured":"Gu, J., et al.: Starflow: Scaling latent normalizing flows for high-resolution image synthesis. Adv. Neural Inform. Process. Syst. 38, 120986\u2013121022 (2026)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR17","unstructured":"Gu, J., et al.: Starflow-v: End-to-end video generative modeling with autoregressive normalizing flows. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 9084\u20139094 (2026)"},{"key":"37_CR18","unstructured":"Han, C., et al.: Nextstep-1: Toward autoregressive image generation with continuous tokens at scale. In: International Conference on Learning Representions (2026)"},{"key":"37_CR19","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A., Song, J., Liu, G., Kautz, J., Vahdat, A.: Diffit: Diffusion vision transformers for image generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference Computer Vision, pp. 37\u201355. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73242-3_3","DOI":"10.1007\/978-3-031-73242-3_3"},{"key":"37_CR20","unstructured":"Heek, J., Hoogeboom, E., Mensink, T., Salimans, T.: Unified latents (ul): How to train your latents. arXiv preprint arXiv:2602.17270 (2026)"},{"key":"37_CR21","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. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"37_CR22","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"37_CR23","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: IEEE Conference on Computer Vision Pattern Recognition, pp. 18062\u201318071 (2025)","DOI":"10.1109\/CVPR52734.2025.01683"},{"key":"37_CR24","unstructured":"Huang, C.W., Krueger, D., Lacoste, A., Courville, A.: Neural autoregressive flows. In: International Conference on Machine Learning, pp. 2078\u20132087. PMLR (2018)"},{"issue":"13","key":"37_CR25","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","volume":"44","author":"Q Huynh-Thu","year":"2008","unstructured":"Huynh-Thu, Q., Ghanbari, M.: Scope of validity of psnr in image\/video quality assessment. Electron. Lett. 44(13), 800\u2013801 (2008)","journal-title":"Electron. Lett."},{"key":"37_CR26","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":"37_CR27","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representions (2018)"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Lehtinen, J., Hellsten, J., Aila, T., Laine, S.: Analyzing and improving the training dynamics of diffusion models. In: IEEE International Conference on Learning Representions, pp. 24174\u201324184 (2024)","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"37_CR29","unstructured":"Ke, G., XUE, H.: Hyperspherical latents improve continuous-token autoregressive generation. In: International Conference on Learning Representions (2026)"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Kim, C.D., Kim, B., Lee, H., Kim, G.: Audiocaps: Generating captions for audios in the wild. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 119\u2013132 (2019)","DOI":"10.18653\/v1\/N19-1011"},{"key":"37_CR31","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"37_CR32","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: Generative flow with invertible 1x1 convolutions. Adv. Neural Inform. Process. Syst. 31 (2018)"},{"key":"37_CR33","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. Adv. Neural Inform. Process. Syst. 29 (2016)"},{"issue":"11","key":"37_CR34","doi-asserted-by":"publisher","first-page":"3964","DOI":"10.1109\/TPAMI.2020.2992934","volume":"43","author":"I Kobyzev","year":"2020","unstructured":"Kobyzev, I., Prince, S.J., Brubaker, M.A.: Normalizing flows: An introduction and review of current methods. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3964\u20133979 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR35","unstructured":"Kouzelis, T., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: Eq-vae: Equivariance regularized latent space for improved generative image modeling. In: International Conference on Machine Learning, pp. 31648\u201331666. PMLR (2025)"},{"key":"37_CR36","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: International Conference Computer Vision, pp. 18262\u201318272 (2025)","DOI":"10.1109\/ICCV51701.2025.01697"},{"key":"37_CR37","doi-asserted-by":"publisher","first-page":"56424","DOI":"10.52202\/079017-1797","volume":"37","author":"T Li","year":"2024","unstructured":"Li, T., Tian, Y., Li, H., Deng, M., He, K.: Autoregressive image generation without vector quantization. Adv. Neural Inform. Process. Syst. 37, 56424\u201356445 (2024)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Audiolcm: Efficient and high-quality text-to-audio generation with minimal inference steps. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7008\u20137017. Association for Computing Machinery (2024)","DOI":"10.1145\/3664647.3681072"},{"key":"37_CR39","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 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":"37_CR40","doi-asserted-by":"publisher","first-page":"35478","DOI":"10.52202\/068431-2571","volume":"35","author":"B M\u00e1t\u00e9","year":"2022","unstructured":"M\u00e1t\u00e9, B., Klein, S., Golling, T., Fleuret, F.: Flowification: Everything is a normalizing flow. Adv. Neural Inform. Process. Syst. 35, 35478\u201335489 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR41","first-page":"2503","volume":"33","author":"E Mathieu","year":"2020","unstructured":"Mathieu, E., Nickel, M.: Riemannian continuous normalizing flows. Adv. Neural Inform. Process. Syst. 33, 2503\u20132515 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Meshchaninov, V., Chimbulatov, E., Shabalin, A., Abramov, A., Vetrov, D.: Cosmos: Compressed and smooth latent space for text diffusion modeling. Adv. Neural Inform. Process. Syst. (2026)","DOI":"10.52202\/085713-0479"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Pang, Z., et al.: Randar: Decoder-only autoregressive visual generation in random orders. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 45\u201355 (2025)","DOI":"10.1109\/CVPR52734.2025.00014"},{"issue":"57","key":"37_CR44","first-page":"1","volume":"22","author":"G Papamakarios","year":"2021","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. J. Mach. Learn. Res. 22(57), 1\u201364 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"37_CR45","unstructured":"Papamakarios, G., Pavlakou, T., Murray, I.: Masked autoregressive flow for density estimation. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"37_CR46","unstructured":"Patacchiola, M., Shysheya, A., Hofmann, K., Turner, R.E.: Transformer neural autoregressive flows. arXiv preprint arXiv:2401.01855 (2024)"},{"key":"37_CR47","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: International Conference Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"37_CR48","unstructured":"Qiu, K., et al.: Image tokenizer needs post-training. arXiv preprint arXiv:2509.12474 (2025)"},{"key":"37_CR49","doi-asserted-by":"crossref","unstructured":"Ren, S., Yu, Q., He, J., Shen, X., Yuille, A., Chen, L.C.: Beyond next-token: Next-x prediction for autoregressive visual generation. In: International Conference Computer Vision, pp. 15781\u201315791 (2025)","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"37_CR50","unstructured":"Ren, S., Yu, Q., He, J., Shen, X., Yuille, A., Chen, L.C.: Flowar: Scale-wise autoregressive image generation meets flow matching. In: International Conference on Machine Learning, pp. 51489\u201351502. PMLR (2025)"},{"key":"37_CR51","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530\u20131538. PMLR (2015)"},{"key":"37_CR52","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"37_CR53","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Adv. Neural Inform. Process. Syst. 29 (2016)"},{"key":"37_CR54","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: Scaling stylegan to large diverse datasets. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"37_CR55","unstructured":"Skorokhodov, I., et al.: Improving the diffusability of autoencoders. In: International Conference on Machine Learning, pp. 55876\u201355905. PMLR (2025)"},{"key":"37_CR56","unstructured":"Su, J., Wu, G.: f-vaes: Improve vaes with conditional flows. arXiv preprint arXiv:1809.05861 (2018)"},{"key":"37_CR57","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"37_CR58","unstructured":"Sun, Y., et al.: Multimodal latent language modeling with next-token diffusion. In: IInternational Conference on Machine Learning (2026)"},{"key":"37_CR59","doi-asserted-by":"publisher","first-page":"84839","DOI":"10.52202\/079017-2694","volume":"37","author":"K Tian","year":"2024","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: Scalable image generation via next-scale prediction. Adv. Neural Inform. Process. Syst. 37, 84839\u201384865 (2024)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR60","unstructured":"Tschannen, M., Pinto, A.S., Kolesnikov, A.: Jetformer: An autoregressive generative model of raw images and text. In: International Conference on Learning Representions (2025)"},{"key":"37_CR61","first-page":"11287","volume":"34","author":"A Vahdat","year":"2021","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Adv. Neural Inform. Process. Syst. 34, 11287\u201311302 (2021)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR62","unstructured":"Van Den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning. PMLR (2016)"},{"key":"37_CR63","unstructured":"Wang, S., Gao, Z., Zhu, C., Huang, W., Wang, L.: Pixnerd: Pixel neural field diffusion. In: International Conference on Learning Representions (2026)"},{"key":"37_CR64","unstructured":"Wang, S., Tian, Z., Huang, W., Wang, L.: Ddt: Decoupled diffusion transformer. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 40633\u201340642 (2026)"},{"issue":"4","key":"37_CR65","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"37_CR66","unstructured":"Yang, J., Li, T., Fan, L., Tian, Y., Wang, Y.: Latent denoising makes good tokenizers. InIn: International Conference on Learning Representions (2026)"},{"key":"37_CR67","doi-asserted-by":"crossref","unstructured":"Yao, J., Yang, B., Wang, X.: Reconstruction vs. generation: Taming optimization dilemma in latent diffusion models. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 15703\u201315712 (2025)","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"37_CR68","unstructured":"Yu, L., et al.: Language model beats diffusion - tokenizer is key to visual generation. In: International Conference on Learning Representions (2024)"},{"key":"37_CR69","unstructured":"Yu, S., et al.: Representation alignment for generation: Training diffusion transformers is easier than you think. In:International Conference on Learning Representions (2025)"},{"key":"37_CR70","unstructured":"Zhai, S., et al.: Normalizing flows are capable generative models. In: International Conference on Machine Learning, pp. 74348\u201374369. PMLR (2025)"},{"key":"37_CR71","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: IEEE Conference on Computer Vision Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"37_CR72","first-page":"173273","volume":"38","author":"R Zhang","year":"2026","unstructured":"Zhang, R., et al.: Flexible language modeling in continuous space with transformer-based autoregressive flows. Adv. Neural Inform. Process. Syst. 38, 173273\u2013173323 (2026)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"37_CR73","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. In: International Conference on Learning Representions (2026)"},{"key":"37_CR74","unstructured":"Zheng, G., et al.: Farmer: Flow autoregressive transformer over pixels. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 25730\u201325741 (2026)"},{"key":"37_CR75","unstructured":"Zheng, H., Nie, W., Vahdat, A., Anandkumar, A.: Fast training of diffusion models with masked transformers. Trans. Mach. Learn. Res. (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\/978-3-032-37577-3_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:02:38Z","timestamp":1788994958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_37","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"}}]}}