{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T18:05:56Z","timestamp":1789236356649,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375490","type":"print"},{"value":"9783032375506","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\/978-3-032-37550-6_27","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:24:24Z","timestamp":1789233864000},"page":"468-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion-SDPO: Safeguarded Direct Preference Optimization for\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4685-6600","authenticated-orcid":false,"given":"Minghao","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5446-1051","authenticated-orcid":false,"given":"Guo-Hua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing-Guo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihua","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaifu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","DOI":"10.1093\/biomet\/39.3-4.324"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Cho, J.H., Oh, J., Kim, M., Lee, B.J.: Rethinking DPO: The role of rejected responses in preference misalignment, (2025). arXiv:2506.12725","DOI":"10.18653\/v1\/2025.findings-emnlp.433"},{"key":"27_CR3","unstructured":"Chowdhury, S.R., Kini, A., Natarajan, N.: Provably robust DPO: aligning language models with noisy feedback. In: ICML. pp. 42258 \u2013 42274 (2024)"},{"key":"27_CR4","unstructured":"Christiano, P.F., Leike, J., Brown, T.B., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. NeurIPS. pp, 4302\u20134310 (2017)"},{"issue":"9","key":"27_CR5","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: A survey. IEEE TPAMI 45(9), 10850\u201310869 (2023)","journal-title":"IEEE TPAMI"},{"key":"27_CR6","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. NeurIPS. pp, 8780\u20138794 (2021)"},{"key":"27_CR7","unstructured":"Esser, P., Kulal, S., Blattmann, A., et\u00a0al.: Scaling rectified flow Transformers for high-resolution image synthesis. In: ICML. pp. 12606\u201312633 (2024)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Gambashidze, A., Kulikov, A., Sosnin, Y., Makarov, I.: Aligning diffusion models with noise-conditioned perception, (2024). arXiv:2406.17636","DOI":"10.1109\/ACCESS.2025.3632092"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: GENEVAL: An object-focused framework for evaluating text-to-image alignment. NeurIPS, (2023)","DOI":"10.52202\/075280-2270"},{"key":"27_CR10","unstructured":"Google: Introducing gemini 2.5 flash image (aka nano-banana). https:\/\/developers.googleblog.com\/en\/introducing-gemini-2-5-flash-image\/ (2025), accessed: 27 June 2026"},{"key":"27_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS. pp, 6840\u20136851 (2020)"},{"key":"27_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance, (2022). arXiv:2207.12598"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hong, J., Paul, S., Lee, N., Rasul, K., Thorne, J., Jeong, J.: Margin-aware preference optimization for aligning diffusion models without reference. In: ICLR Workshop, (2025)","DOI":"10.1609\/aaai.v40i6.42476"},{"key":"27_CR14","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: ELLA: Equip diffusion models with LLM for enhanced semantic alignment, (2024). arXiv:2403.05135"},{"key":"27_CR15","unstructured":"Huang, A., Zhan, W., Xie, T., Lee, J.D., Sun, W., Krishnamurthy, A., Foster, D.J.: Correcting the mythos of KL-regularization: Direct alignment without overparameterization via chi-squared preference optimization. ICLR. pp, 1\u201316 (2025)"},{"key":"27_CR16","unstructured":"Jo, J., Lee, S., Hwang, S.J.: Score-based generative modeling of graphs via the system of stochastic differential equations. In: ICML. pp. 10362\u201310383 (2022)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Laine, S., Aila, T.: Elucidating the design space of diffusion-based generative models. NeurIPS. pp, 26565\u201326577 (2022)","DOI":"10.52202\/068431-1926"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-Pic: An open dataset of user preferences for text-to-image generation. NeurIPS. pp, 36652\u201336663 (2023)","DOI":"10.52202\/075280-1594"},{"key":"27_CR19","unstructured":"Labs, B.F.: FLUX.1-dev. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev (2024), accessed: 27 June 2026"},{"key":"27_CR20","unstructured":"Lan, G., Zhang, S., Wang, T.: MaPPO: Maximum a posteriori preference optimization with prior knowledge, (2025). arXiv:2507.21183"},{"key":"27_CR21","unstructured":"Li, B., Xu, M., Dang, M., Ermon, S.: Divergence minimization preference optimization for diffusion model alignment, (2025). arXiv:2507.07510"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, S., Kallidromitis, K., Gokul, A., Kato, Y., Kozuka, K.: Aligning diffusion models by optimizing human utility. NeurIPS. pp, 24897\u201324925 (2025)","DOI":"10.52202\/079017-0785"},{"key":"27_CR23","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. ICLR. pp, 1\u201313 (2023)"},{"key":"27_CR24","unstructured":"Liu, S., Han, Y., Xing, P.: Step1X-Edit: A practical framework for general image editing, (2025). arXiv:2504.17761"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. In: ICLR. pp. 1\u201315 (2023)","DOI":"10.3390\/en15041320"},{"key":"27_CR26","unstructured":"Pal, A., Karkhanis, D., Dooley, S., Roberts, M., Naidu, S., White, C.: Smaug: Fixing failure modes of preference optimisation with dpo-positive, (2024). arXiv:2402.13228"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with Transformers. In: ICCV. pp. 4172\u20134182 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"27_CR28","unstructured":"Podell, D., English, Z., Lacey, K.: SDXL: Improving latent diffusion models for high-resolution image synthesis. ICLR. pp, 1\u201313 (2024)"},{"key":"27_CR29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML. pp. 8748\u20138763 (2021)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct preference optimization: your language model is secretly a reward model. NeurIPS. pp, 53728\u201353741 (2023)","DOI":"10.52202\/075280-2338"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10674\u201310685. (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. MICCAI. pp, 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"27_CR33","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., et\u00a0al.: LAION-Aesthetics: Predicting the aesthetic quality of images. https:\/\/laion.ai\/blog\/laion-aesthetics\/ (2022), accessed: 27 June 2026"},{"key":"27_CR34","unstructured":"Shekhar, S., Singh, S., Zhang, T.: SEE-DPO: Self entropy enhanced direct preference optimization. TMLR, (2025)"},{"key":"27_CR35","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML. p. 2256\u20132265 (2015)"},{"key":"27_CR36","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. ICLR. pp, 1\u201312 (2022)"},{"key":"27_CR37","unstructured":"Tamboli, D., Chakraborty, S., Malusare, A., Banerjee, B., Bedi, A.S., Aggarwal, V.: BalancedDPO: Adaptive multi-metric alignment, (2025). arXiv:2503.12575"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Wallace, B., Dang, M., Rafailov, R.: Diffusion model alignment using direct preference optimization. In: CVPR. pp, pp. 8228\u20138238. (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"27_CR39","unstructured":"Wang, G.H., Zhao, S., Zhang, X.: Ovis-U1 technical report, (2025). arXiv:2506.23044"},{"key":"27_CR40","unstructured":"Wang, R., Sun, Q., Song, C., Wu, J., Chen, T., Zeng, Z., Li, Y.: Linear preference optimization: Decoupled gradient control via absolute regularization, (2025). arXiv:2508.14947"},{"key":"27_CR41","unstructured":"Wu, X., Hao, Y., Sun, K., Chen, Y., Zhu, F., Zhao, R., Li, H.: Human Preference Score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis, (2023). arXiv:2306.09341"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Xiao, T., Yuan, Y., Zhu, H., Li, M., Honavar, V.G.: Cal-DPO: Calibrated direct preference optimization for language model alignment. NeurIPS. pp, 114289\u2013114320 (2024)","DOI":"10.52202\/079017-3630"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, X., Wu, Y.: ImageReward: Learning and evaluating human preferences for text-to-image generation. NeurIPS. pp, 15903\u201315935 (2024)","DOI":"10.52202\/075280-0700"},{"key":"27_CR44","unstructured":"Yang, C., Jia, R., Gu, N.: Orthogonal finetuning for direct preference optimization, (2024). arXiv:2409.14836"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Ye, Y., He, X., Li, Z.: ImgEdit: A unified image editing dataset and benchmark, (2025). arXiv:2505.20275","DOI":"10.52202\/085713-4387"},{"key":"27_CR46","unstructured":"Yu, J., Xu, Y., Koh, J.Y.: Scaling autoregressive models for content-rich text-to-image generation, (2022). arXiv:2206.10789"},{"key":"27_CR47","unstructured":"Zhao, W.X., Zhou, K., Li, J.: A survey of large language models, (2023). arXiv:2303.18223"},{"key":"27_CR48","unstructured":"Zhu, H., Xiao, T., Honavar, V.G.: DSPO: Direct score preference optimization for diffusion model alignment. ICLR. pp, 1\u201313 (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\/978-3-032-37550-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:24:34Z","timestamp":1789233874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37550-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375490","9783032375506"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37550-6_27","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":"13 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"}}]}}