{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:00:56Z","timestamp":1775278856306,"version":"3.50.1"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62405014"],"award-info":[{"award-number":["62405014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325101"],"award-info":[{"award-number":["62325101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62031001"],"award-info":[{"award-number":["62031001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2025.3647857","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:45:42Z","timestamp":1766601942000},"page":"5050-5067","source":"Crossref","is-referenced-by-count":0,"title":["You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling With Gradient Shortcuts"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6185-5369","authenticated-orcid":false,"given":"Hongkun","family":"Dou","sequence":"first","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8693-0334","authenticated-orcid":false,"given":"Zeyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0282-622X","authenticated-orcid":false,"given":"Xingyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0504-2555","authenticated-orcid":false,"given":"Hongjue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Astronautics, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-9834","authenticated-orcid":false,"given":"Wen","family":"Yao","sequence":"additional","affiliation":[{"name":"Defense Innovation Institute, Chinese Academy of Military Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2871-8922","authenticated-orcid":false,"given":"Yue","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref3","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref6","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3522305"},{"key":"ref9","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho","year":"2022"},{"key":"ref10","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3558507"},{"key":"ref12","first-page":"1","article-title":"GeoDiff: A geometric diffusion model for molecular conformation generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2022"},{"key":"ref13","first-page":"8867","article-title":"Equivariant diffusion for molecule generation in 3D","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hoogeboom","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3344758"},{"key":"ref15","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Janner","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref17","article-title":"IDQL: Implicit Q-learning as an actor-critic method with diffusion policies","author":"Hansen-Estruch","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref19","first-page":"66860","article-title":"StyleDrop: Text-to-image generation in any style","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2023"},{"key":"ref20","article-title":"TAGmol: Target-aware gradient-guided molecule generation","volume-title":"Proc. Workshop ML Life Mater. Sci.: From Theory Ind. Appl.","author":"Dorna","year":"2024"},{"key":"ref21","first-page":"1","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref23","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023"},{"key":"ref24","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref25","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"ref26","first-page":"1","article-title":"AdjointDPM: Adjoint sensitivity method for gradient backpropagation of diffusion probabilistic models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Pan","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref28","first-page":"4263","article-title":"Parallel sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shih","year":"2024"},{"key":"ref29","first-page":"1","article-title":"ParaSolver: A hierarchical parallel integral solver for diffusion models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Lu","year":"2025"},{"key":"ref30","first-page":"47800","article-title":"Accelerating parallel sampling of diffusion models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Tang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435448"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3545047"},{"key":"ref35","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref36","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00532-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02331"},{"key":"ref39","first-page":"38426","article-title":"Ditto: Diffusion inference-time t-optimization for music generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Novack","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref41","first-page":"1","article-title":"Nice: Non-linear independent components estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2015"},{"key":"ref42","first-page":"1","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1201\/9780203749319"},{"key":"ref44","first-page":"36520","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0080"},{"key":"ref46","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Stiennon","year":"2020"},{"key":"ref47","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019"},{"key":"ref48","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref49","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref51","first-page":"79858","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fan","year":"2024"},{"key":"ref52","first-page":"1","article-title":"Training diffusion models with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Black","year":"2024"},{"key":"ref53","first-page":"1","article-title":"Directly fine-tuning diffusion models on differentiable rewards","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_7"},{"key":"ref55","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref56","first-page":"1","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref57","first-page":"1","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref58","first-page":"64","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Des. Appl."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21236\/ada164453"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref62","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lorraine","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0378"},{"key":"ref64","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898717761","volume-title":"Evaluating Derivatives: Principles and Techniques of Algorithmic Differentiation","author":"Griewank","year":"2008"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-5981-1"},{"key":"ref66","article-title":"Is attention better than matrix decomposition?","author":"Geng","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20619"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3371"},{"key":"ref69","first-page":"5570","article-title":"Learning iterative reasoning through energy minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2022"},{"key":"ref70","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref71","article-title":"Consistency model is an effective posterior sample approximation for diffusion inverse solvers","author":"Xu","year":"2024"},{"key":"ref72","article-title":"Physics-aligned Schr\u00f6dinger bridge","author":"Li","year":"2024"},{"key":"ref73","article-title":"FuseDream: Training-free text-to-image generation with improved clip GAN space optimization","author":"Liu","year":"2021"},{"key":"ref74","first-page":"1","article-title":"Progressive growing of gans for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref76","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref78","first-page":"1","article-title":"Integrating intermediate layer optimization and projected gradient descent for solving inverse problems with diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng","year":"2025"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref82","article-title":"Large-scale classification of fine-art paintings: Learning the right metric on the right feature","author":"Saleh","year":"2015"},{"key":"ref83","article-title":"Simulacra aesthetic captions","author":"Pressman","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref86","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616679"},{"key":"ref88","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref92","first-page":"1","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref93","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref96","first-page":"1","article-title":"PixArt-$\\alpha$\u03b1 : Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref97","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref98","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref100","article-title":"Diffusers: State-of-the-art diffusion models","author":"Platen","year":"2022"},{"key":"ref101","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref102","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00709"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11314794.pdf?arnumber=11314794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:16:23Z","timestamp":1775276183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":103,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3647857","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}