{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:06:25Z","timestamp":1784203585050,"version":"3.55.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1003305"],"award-info":[{"award-number":["2021YFA1003305"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109023","type":"journal-article","created":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T05:40:38Z","timestamp":1776577238000},"page":"109023","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Toward theoretical insights into diffusion trajectory distillation via operator merging"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6675-8754","authenticated-orcid":false,"given":"Weiguo","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1276-3340","authenticated-orcid":false,"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109023_bib0001","unstructured":"Berthelot, D., Autef, A., Lin, J., Yap, D. A., Zhai, S., Hu, S., Zheng, D., Talbott, W., & Gu, E. (2023). TRACT: Denoising diffusion models with transitive closure time-distillation. arXiv: 2303.04248."},{"key":"10.1016\/j.neunet.2026.109023_bib0002","series-title":"Interational conference on learning representations","article-title":"One step diffusion via shortcut models","author":"Frans","year":"2025"},{"key":"10.1016\/j.neunet.2026.109023_bib0003","series-title":"Advances in neural information processing systems","article-title":"Mean flows for one-step generative modeling","author":"Geng","year":"2025"},{"key":"10.1016\/j.neunet.2026.109023_bib0004","series-title":"ICML 2023 Workshop on structured probabilistic inference & generative modeling","article-title":"BOOT: Data-free distillation of denoising diffusion models with bootstrapping","author":"Gu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109023_bib0005","series-title":"Advances in neural information processing systems","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"10.1016\/j.neunet.2026.109023_bib0006","series-title":"Advances in neural information processing systems","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"10.1016\/j.neunet.2026.109023_bib0007","series-title":"Advances in neural information processing systems","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022"},{"key":"10.1016\/j.neunet.2026.109023_bib0008","series-title":"International conference on learning representations","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.neunet.2026.109023_bib0009","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neunet.2026.109023_bib0010","article-title":"Reward guided latent consistency distillation","author":"Li","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109023_bib0011","series-title":"Advances in neural information processing systems","article-title":"Understanding generalizability of diffusion models requires rethinking the hidden Gaussian structure","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109023_bib0012","unstructured":"Lin, S., Wang, A., & Yang, X. (2024). SDXL-Lightning: Progressive adversarial diffusion distillation. arXiv: 2402.13929."},{"key":"10.1016\/j.neunet.2026.109023_bib0013","series-title":"International conference on learning representations","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109023_bib0014","series-title":"International conference on computer vision","article-title":"Deep learning face attributes in the wild","author":"Liu","year":"2015"},{"key":"10.1016\/j.neunet.2026.109023_bib0015","series-title":"International conference on learning representations","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.neunet.2026.109023_bib0016","series-title":"Advances in neural information processing systems","article-title":"DPM-Solver: A fast ODE Solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109023_bib0017","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J. (2022b). DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models. arXiv: 2211.01095."},{"key":"10.1016\/j.neunet.2026.109023_bib0018","unstructured":"Luhman, E., & Luhman, T. (2021). Knowledge distillation in iterative generative models for improved sampling speed. arXiv: 2101.02388."},{"key":"10.1016\/j.neunet.2026.109023_bib0019","unstructured":"Luo, T., Yuan, H., & Liu, Z. (2025). SoFlow: Solution flow models for one-step generative modeling. arXiv: 2512.15657."},{"key":"10.1016\/j.neunet.2026.109023_bib0020","series-title":"Advances in neural information processing systems","article-title":"Diff-Instruct: A universal approach for transferring knowledge from pre-trained diffusion models","author":"Luo","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2026.109023_bib0021","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","article-title":"Principal components analysis (PCA)","volume":"19","author":"Ma\u0107kiewicz","year":"1993","journal-title":"Computers & Geosciences"},{"key":"10.1016\/j.neunet.2026.109023_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","article-title":"On distillation of guided diffusion models","author":"Meng","year":"2023"},{"key":"10.1016\/j.neunet.2026.109023_bib0023","series-title":"International conference on machine learning","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021"},{"key":"10.1016\/j.neunet.2026.109023_bib0024","unstructured":"Ren, T., Zhang, Z., Li, Z., Jiang, J., Qin, S., Li, G., Li, Y., Zheng, Y., Li, X., Zhan, M., & Peng, Y. (2025). Zeroth-order informed fine-tuning for diffusion model: A recursive likelihood ratio optimizer. arXiv: 2502.00639."},{"key":"10.1016\/j.neunet.2026.109023_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109023_bib0026","series-title":"International conference on medical image computing and computer-assisted intervention","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.neunet.2026.109023_bib0027","series-title":"International conference on learning representations","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"10.1016\/j.neunet.2026.109023_bib0028","series-title":"Optimal transport for applied mathematicians","author":"Santambrogio","year":"2015"},{"key":"10.1016\/j.neunet.2026.109023_bib0029","series-title":"European conference on computer vision","article-title":"Adversarial diffusion distillation","author":"Sauer","year":"2024"},{"key":"10.1016\/j.neunet.2026.109023_bib0030","series-title":"International conference on image processing","article-title":"Learning to generate images with perceptual similarity metrics","author":"Snell","year":"2017"},{"key":"10.1016\/j.neunet.2026.109023_bib0031","series-title":"International conference on learning representations","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.109023_bib0032","series-title":"International conference on machine learning","article-title":"Consistency models","author":"Song","year":"2023"},{"key":"10.1016\/j.neunet.2026.109023_bib0033","series-title":"Advances in neural information processing systems","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019"},{"key":"10.1016\/j.neunet.2026.109023_bib0034","series-title":"International conference on learning representations","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.109023_bib0035","unstructured":"Wang, B., & Vastola, J. J. (2023a). Diffusion models generate images like painters: An analytical theory of outline first, details later. arXiv: 2303.02490."},{"key":"10.1016\/j.neunet.2026.109023_bib0036","unstructured":"Wang, B., & Vastola, J. J. (2023b). The hidden linear structure in score-based models and its application. arXiv: 2311.10892."},{"key":"10.1016\/j.neunet.2026.109023_bib0037","unstructured":"Xu, C., Cheng, X., & Xie, Y. (2024). Local flow matching generative models. arXiv: 2410.02548."},{"key":"10.1016\/j.neunet.2026.109023_bib0038","unstructured":"Xu, Y., Nie, W., & Vahdat, A. (2025). One-step diffusion models with f-divergence distribution matching. arXiv: 2502.15681."},{"key":"10.1016\/j.neunet.2026.109023_bib0039","series-title":"Advances in neural information processing systems","article-title":"Improved distribution matching distillation for fast image synthesis","author":"Yin","year":"2024"},{"key":"10.1016\/j.neunet.2026.109023_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","article-title":"One-step diffusion with distribution matching distillation","author":"Yin","year":"2024"},{"key":"10.1016\/j.neunet.2026.109023_bib0041","unstructured":"Yu, Z., Li, M., Zhang, W., & Gao, W. (2025). Tree reward-aligned search for TReASURe in masked diffusion language models. arXiv: 2509.23146."},{"key":"10.1016\/j.neunet.2026.109023_bib0042","unstructured":"Zhang, H., Siarohin, A., Menapace, W., Vasilkovsky, M., Tulyakov, S., Qu, Q., & Skorokhodov, I. (2025). AlphaFlow: Understanding and improving MeanFlow models. arXiv: 2510.20771."},{"key":"10.1016\/j.neunet.2026.109023_bib0043","series-title":"Advances in neural information processing systems","article-title":"UniPC: A unified predictor-corrector framework for fast sampling of diffusion models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109023_bib0044","series-title":"International conference on learning representations","article-title":"Adversarial score identity distillation: Rapidly surpassing the teacher in one step","author":"Zhou","year":"2025"},{"key":"10.1016\/j.neunet.2026.109023_bib0045","series-title":"International conference on machine learning","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","author":"Zhou","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004831?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004831?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:21:49Z","timestamp":1784200909000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S0893608026004831"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109023","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Toward theoretical insights into diffusion trajectory distillation via operator merging","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109023","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109023"}}