{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:28:48Z","timestamp":1789468128630,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373137","type":"print"},{"value":"9783032373144","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\/978-3-032-37314-4_35","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:54:48Z","timestamp":1789462488000},"page":"639-657","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Importance-Aware Low-Rank Distillation of\u00a0Diffusion Transformers"],"prefix":"10.1007","author":[{"given":"Denis","family":"Zavadski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Heid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damjan","family":"Kal\u0161an","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Rother","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Ben Noach, M., Goldberg, Y.: Compressing pre-trained language models by matrix decomposition. In: Assoc, A.-P. (ed.) Comput. Ling. and the 10th International Joint Conference on Natural Language Processing, pp. 884\u2013889 (2020)","DOI":"10.18653\/v1\/2020.aacl-main.88"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Cai, F., Guo, Y., Li, J., Li, W., Chen, J., Fang, X.: FastFLUX: Pruning FLUX with block-wise replacement and sandwich training. In: AAAI, pp. 2507\u20132515 (2026)","DOI":"10.1609\/aaai.v40i4.37237"},{"key":"35_CR3","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: PixArt-$$\\sigma $$: Weak-to-strong training of diffusion transformer for 4K text-to-image generation. In: European Conference Computer Vision, pp. 74\u201391. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73411-3_5","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: SANA-Sprint: One-step diffusion with continuous-time consistency distillation. In: International Conference Computer Vision, pp. 16185\u201316195 (2025)","DOI":"10.1109\/ICCV51701.2025.01502"},{"key":"35_CR5","unstructured":"Chen, P., et al.: $$\\Delta $$-DiT: A training-free acceleration method tailored for diffusion transformers. arXiv preprint arXiv:2406.01125 (2024)"},{"key":"35_CR6","unstructured":"Denton, E., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advance Neural Informatics Processing System, vol.\u00a027. Curran Associates, Inc. (2014)"},{"key":"35_CR7","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. Int. Conf. Mach. Learn. (2024)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Fang, G., Li, K., Ma, X., Wang, X.: TinyFusion: Diffusion transformers learned shallow. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 18144\u201318154 (2025)","DOI":"10.1109\/CVPR52734.2025.01691"},{"key":"35_CR9","unstructured":"fpgaminer: JoyCaption (2024). https:\/\/github.com\/fpgaminer\/joycaption"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: GenEval: An object-focused framework for evaluating text-to-image alignment. Adv. Neural Inform. Process. Syst 36, 52132\u201352152 (2023). Curran Associates, Inc","DOI":"10.52202\/075280-2270"},{"key":"35_CR11","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). Curran Associates, Inc"},{"key":"35_CR12","unstructured":"Hsu, Y.C., Hua, T., Chang, S., Lou, Q., Shen, Y., Jin, H.: Language model compression with weighted low-rank factorization. Int. Conference on Learning Representations (2022)"},{"key":"35_CR13","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: ELLA: Equip diffusion models with LLM for enhanced semantic alignment. arXiv preprint arXiv:2403.05135 (2024)"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Huang, T., Zhang, Y., Zheng, M., You, S., Wang, F., Qian, C., Xu, C.: Knowledge diffusion for distillation. Adv. Neural Inform. Process. Syst 36, 65299\u201365316 (2023). Curran Associates, Inc.","DOI":"10.52202\/075280-2849"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking FID: Towards a better evaluation metric for image generation. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 9307\u20139315 (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"35_CR16","doi-asserted-by":"publisher","unstructured":"Kang, M., et al.: Distilling diffusion models into conditional GANs. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference Computer Vision, pp. 428\u2013447. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73390-1_25","DOI":"10.1007\/978-3-031-73390-1_25"},{"key":"35_CR17","doi-asserted-by":"publisher","unstructured":"Kim, B.K., Song, H.K., Castells, T., Choi, S.: BK-SDM: A lightweight, fast, and cheap version of Stable Diffusion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference Computer Vision, pp. 381\u2013399. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72949-2_22","DOI":"10.1007\/978-3-031-72949-2_22"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Kwon, Y.D., Li, R., Li, S., Li, D., Bhattacharya, S., Venieris, S.I.: HierarchicalPrune: Position-aware compression for large-scale diffusion models. In: AAAI, pp. 22716\u201322724 (2026)","DOI":"10.1609\/aaai.v40i27.39433"},{"key":"35_CR19","unstructured":"Labs, B.F.: FLUX (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: OmniFlow: Any-to-any generation with multi-modal rectified flows. In: IEEE Conference on Computer Vision Pattern Recognition, pp. 13178\u201313188 (2025)","DOI":"10.1109\/CVPR52734.2025.01230"},{"key":"35_CR21","unstructured":"Lin, S., Wang, A., Yang, X.: SDXL-Lightning: Progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"35_CR22","unstructured":"Liu, B., et al.: Playground v3: Improving text-to-image alignment with deep-fusion large language models. arXiv preprint arXiv:2409.10695 (2024)"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Liu, K., Zhang, Y., Cheng, N., Li, Z., Wang, S., Xiao, J.: GRASP: Replace redundant layers with adaptive singular parameters for efficient model compression. In: Conference on Empirical Methods in Natural Language Processing, pp. 26344\u201326359 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1338"},{"key":"35_CR24","unstructured":"Ma, J., Peng, Q., Zhu, X., Xie, P., Chen, C., Lu, H.: Pluggable pruning with contiguous layer distillation for diffusion transformers. arXiv preprint arXiv:2511.16156 (2025)"},{"issue":"1","key":"35_CR25","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1093\/qmath\/11.1.50","volume":"11","author":"L Mirsky","year":"1960","unstructured":"Mirsky, L.: Symmetric gauge functions and unitarily invariant norms. Quart. J. Math. 11(1), 50\u201359 (1960)","journal-title":"Quart. J. Math."},{"key":"35_CR26","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":"35_CR27","unstructured":"Podell, D., et al.: SDXL: Improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations (2024)"},{"key":"35_CR28","unstructured":"Qinsi, W., Ke, J., Tomizuka, M., Keutzer, K., Xu, C.: Dobi-SVD: Differentiable SVD for LLM compression and some new perspectives. In: International Conference on Learning Representations (2025)"},{"key":"35_CR29","unstructured":"Rock, L.: Chroma1-HD (2025). https:\/\/huggingface.co\/lodestones\/Chroma1-HD"},{"key":"35_CR30","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":"35_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"35_CR32","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022)"},{"key":"35_CR33","doi-asserted-by":"publisher","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference Computer Vision, pp. 87\u2013103. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73016-0_6","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., et al.: LAION-5B: An open large-scale dataset for training next generation image-text models. Adv. Neural Inform. Process. Syst. 35, 25278\u201325294 (2022) Curran Associates, Inc","DOI":"10.52202\/068431-1833"},{"key":"35_CR35","unstructured":"Shazeer, N., Stern, M.: Adafactor: Adaptive learning rates with sublinear memory cost. In: International Conference on Machine Learning, pp. 4596\u20134604. PMLR (2018)"},{"key":"35_CR36","unstructured":"Verd\u00fa, D., Mart\u00edn, J.: Flux. 1 Lite: Distilling FLUX1.dev for efficient text-to-image generation (2024)"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Alam, S., Wan, Z., Shen, H., Zhang, M.: SVD-LLM V2: Optimizing singular value truncation for large language model compression. Nation. Am. Assoc. for Comput. Ling. 4287\u20134296 (2025)","DOI":"10.18653\/v1\/2025.naacl-long.217"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Zheng, Y., Wan, Z., Zhang, M.: SVD-LLM: Truncation-aware singular value decomposition for large language model compression. In: International Conference on Learning Representations (2025)","DOI":"10.18653\/v1\/2025.naacl-long.217"},{"key":"35_CR39","unstructured":"Wu, C., et al.: Qwen-Image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"35_CR40","unstructured":"Wu, X., et al.: Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"35_CR41","unstructured":"Xie, E., et al.: SANA 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer. In: International Conference on Machine Learning (2025)"},{"key":"35_CR42","unstructured":"Yuan, Z., et al.: ASVD: Activation-aware singular value decomposition for compressing large language models. arXiv preprint arXiv:2312.05821 (2023)"},{"key":"35_CR43","doi-asserted-by":"publisher","unstructured":"Zavadski, D., Feiden, J.F., Rother, C.: ControlNet-XS: Rethinking the control of text-to-image diffusion models as feedback-control systems. In: European Conference Computer Vision, pp. 343\u2013362. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73223-2_20","DOI":"10.1007\/978-3-031-73223-2_20"},{"key":"35_CR44","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":"35_CR45","unstructured":"Zhang, Y., et al.: Learnable sparsity for vision generative models. In: International Conference on Learning Representations (2026)"},{"key":"35_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Ren, Y., Xia, X., Xiao, X., Xie, X.: Dense2MoE: Restructuring diffusion transformer to moe for efficient text-to-image generation. In: International Conference Computer Vision, pp. 18661\u201318670 (2025)","DOI":"10.1109\/ICCV51701.2025.01734"},{"key":"35_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: DiP-GO: A diffusion pruner via few-step gradient optimization. In: Advance Neural Informatics Processing System, vol.\u00a037, pp. 92581\u201392604. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-2940"}],"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\/978-3-032-37314-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:55:19Z","timestamp":1789462519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37314-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373137","9783032373144"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37314-4_35","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"}}]}}