{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:11Z","timestamp":1789207571840,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","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\/978-3-032-37335-9_7","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:11:53Z","timestamp":1789204313000},"page":"113-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Flash-BoN: Instant Drafts for\u00a0Inference-Time Scaling in\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Ruchit","family":"Rawal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Shirkavand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayak","family":"Paul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Goldstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gowthami","family":"Somepalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"7_CR1","unstructured":"Agarwal, S., Mitra, S., Chakraborty, S., Karanam, S., Mukherjee, K., Saini, S.K.: Approximate caching for efficiently serving Text-to-Image diffusion models. In: 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). pp. 1173\u20131189. USENIX Association, Santa Clara, CA (2024). https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/agarwal-shubham"},{"key":"7_CR2","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). http:\/\/jmlr.org\/papers\/v26\/23-1605.html"},{"key":"7_CR3","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"7_CR4","unstructured":"Black Forest Labs: FLUX.1 [dev]. 12 billion parameter rectified flow transformer for text-to-image generation (2024). https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev. Accessed 28 June 2026"},{"key":"7_CR5","doi-asserted-by":"publisher","unstructured":"Chen, G., Zhao, X., Zhou, Y., Qu, X., Chen, T., Cheng, Y.: Towards stabilized and efficient diffusion transformers through long-skip-connections with spectral constraints. In: 2025 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17708\u201317718 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.01645","DOI":"10.1109\/ICCV51701.2025.01645"},{"key":"7_CR6","unstructured":"Chen, P., et al.: $$\\delta $$-dit: a training-free acceleration method tailored for diffusion transformers (2024). https:\/\/arxiv.org\/abs\/2406.01125"},{"key":"7_CR7","volume-title":"The Rating of Chessplayers","author":"AE Elo","year":"1978","unstructured":"Elo, A.E.: The Rating of Chessplayers. Past and Present. Arco Publishing, New York (1978)"},{"key":"7_CR8","unstructured":"Friedman, D., Dieng, A.B.: The vendi score: a diversity evaluation metric for machine learning. Trans. Mach. Learn. Res. (2023). https:\/\/openreview.net\/forum?id=g97OHbQyk1"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"52132","DOI":"10.52202\/075280-2270","volume":"36","author":"D Ghosh","year":"2023","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: an object-focused framework for evaluating text-to-image alignment. Adv. Neural. Inf. Process. Syst. 36, 52132\u201352152 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR10","unstructured":"Guo, W.M., Qian, Q., Hasan, K., Du, S.: Aesthetic alignment risks assimilation: How image generation and reward models reinforce beauty bias and ideological\" censorship\". arXiv preprint arXiv:2512.11883 (2025)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Y., Yang, Y., Yuan, H., Wang, M.: Training-free guidance beyond differentiability: scalable path steering with tree search in diffusion and flow models. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=nqVLJTPoQC","DOI":"10.52202\/085713-2459"},{"key":"7_CR12","doi-asserted-by":"publisher","unstructured":"Habibian, A., et al.: Clockwork diffusion: efficient generation with model-step distillation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8352\u20138361 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00798","DOI":"10.1109\/CVPR52733.2024.00798"},{"key":"7_CR13","unstructured":"He, H., et al.: Scaling image and video generation via test-time evolutionary search. arXiv preprint arXiv:2505.17618 (2025)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Lee, G., et al.: Adaptive inference-time scaling via cyclic diffusion search. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=jkCH6iwFZm","DOI":"10.52202\/085713-1909"},{"key":"7_CR15","unstructured":"Li, B., et\u00a0al.: Genai-bench: Evaluating and improving compositional text-to-visual generation. arXiv preprint arXiv:2406.13743 (2024)"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Li, L., et al.: Autodiffusion: training-free optimization of time steps and architectures for automated diffusion model acceleration. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7082\u20137091 (2023).https:\/\/doi.org\/10.1109\/ICCV51070.2023.00654","DOI":"10.1109\/ICCV51070.2023.00654"},{"key":"7_CR17","unstructured":"Li, X., et al.: Dynamic search for inference-time alignment in diffusion models. arXiv preprint arXiv:2503.02039 (2025)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Liu, J., Zou, C., Lyu, Y., Chen, J., Zhang, L.: From reusing to forecasting: accelerating diffusion models with taylorseers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15853\u201315863 (2025)","DOI":"10.1109\/ICCV51701.2025.01471"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Flow-grpo: training flow matching models via online RL. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=oCBKGw5HNf","DOI":"10.52202\/085713-1362"},{"key":"7_CR20","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Ma, N., et al.: Scaling inference time compute for diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 2523\u20132534 (2025)","DOI":"10.1109\/CVPR52734.2025.00241"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Ma, Y., Wu, X., Sun, K., Li, H.: Hpsv3: towards wide-spectrum human preference score. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15086\u201315095 (2025)","DOI":"10.1109\/ICCV51701.2025.01400"},{"key":"7_CR23","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt, featured Certification"},{"key":"7_CR24","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":"7_CR25","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"7_CR26","unstructured":"Singhal, R., et al.: A general framework for inference-time scaling and steering of diffusion models. In: Forty-Second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=Jp988ELppQ"},{"key":"7_CR27","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"7_CR28","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"7_CR29","doi-asserted-by":"publisher","unstructured":"Tsallis, C.: Possible Generalization of Boltzmann-Gibbs Statistics. J. Statist. Phys. 52, 479\u2013487 (1988). https:\/\/doi.org\/10.1007\/BF01016429","DOI":"10.1007\/BF01016429"},{"key":"7_CR30","unstructured":"Uehara, M., et al.: Inference-time alignment in diffusion models with reward-guided generation: Tutorial and review. arXiv preprint arXiv:2501.09685 (2025)"},{"key":"7_CR31","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models (2025). https:\/\/arxiv.org\/abs\/2503.20314"},{"key":"7_CR32","unstructured":"Wang, G., Cai, Y., lijiang Li, Peng, W., Su, S.Z.: PFDiff: training-free acceleration of diffusion models combining past and future scores. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=wmmDvZGFK7"},{"key":"7_CR33","unstructured":"Wang, W., et al.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"7_CR34","unstructured":"Wang, Y., et al.: Pref-grpo: Pairwise preference reward-based grpo for stable text-to-image reinforcement learning. arXiv preprint arXiv:2508.20751 (2025)"},{"key":"7_CR35","unstructured":"Whitehouse, C., et al.: J1: Incentivizing thinking in LLM-as-a-judge via reinforcement learning. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=dnJEHl6DI1"},{"key":"7_CR36","unstructured":"Wu, Y., Sun, Z., Li, S., Welleck, S., Yang, Y.: Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=VNckp7JEHn"},{"key":"7_CR37","doi-asserted-by":"publisher","unstructured":"Xiang, Y., Sun, D., Fan, W., Gong, X.: Generalized simulated annealing algorithm and its application to the thomson model. Phys. Lett. A 233(3), 216\u2013220 (1997). https:\/\/doi.org\/10.1016\/S0375-9601(97)00474-Xhttps:\/\/www.sciencedirect.com\/science\/article\/pii\/S037596019700474X","DOI":"10.1016\/S0375-9601(97)00474-X"},{"key":"7_CR38","unstructured":"Xie, E., et al.: SANA 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer. In: Forty-Second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=27hOkXzy9e"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, pp. 15903\u201315935 (2023)","DOI":"10.52202\/075280-0700"},{"key":"7_CR40","doi-asserted-by":"publisher","first-page":"76806","DOI":"10.52202\/075280-3356","volume":"36","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Deng, M., Cheng, X., Tian, Y., Liu, Z., Jaakkola, T.: Restart sampling for improving generative processes. Adv. Neural. Inf. Process. Syst. 36, 76806\u201376838 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR41","doi-asserted-by":"publisher","unstructured":"Xuan, W., Zeng, Q., Qi, H., Wang, J., Yokoya, N.: Seeing is believing, but how much? A comprehensive analysis of verbalized calibration in vision-language models. In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V. (eds.) Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 1408\u20131450. Association for Computational Linguistics, Suzhou, China (2025). https:\/\/doi.org\/10.18653\/v1\/2025.emnlp-main.74, https:\/\/aclanthology.org\/2025.emnlp-main.74\/","DOI":"10.18653\/v1\/2025.emnlp-main.74"},{"key":"7_CR42","unstructured":"Yoon, J., Cho, H., Baek, D., Bengio, Y., Ahn, S.: Monte carlo tree diffusion for system 2 planning. In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=XrCbBdycDc"},{"key":"7_CR43","unstructured":"Zhang, X., et al.: Inference-time scaling of diffusion models through classical search. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=b7Ftp6U78i"},{"key":"7_CR44","doi-asserted-by":"publisher","unstructured":"Zhu, H., et al.: Dip-go: A diffusion pruner via few-step gradient optimization. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems. vol.\u00a037, pp. 92581\u201392604. Curran Associates, Inc. (2024). https:\/\/doi.org\/10.52202\/079017-2940, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/a845fdc3f87751710218718adb634fe7-Paper-Conference.pdf","DOI":"10.52202\/079017-2940"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Zhuo, L., et al.: From reflection to perfection: Scaling inference-time optimization for text-to-image diffusion models via reflection tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15329\u201315339 (2025)","DOI":"10.1109\/ICCV51701.2025.01422"}],"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\/978-3-032-37335-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:12:04Z","timestamp":1789204324000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_7","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"}}]}}