{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T01:04:37Z","timestamp":1759971877016,"version":"build-2065373602"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0114903"],"award-info":[{"award-number":["2022ZD0114903"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42327901","62321005"],"award-info":[{"award-number":["42327901","62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M741952"],"award-info":[{"award-number":["2023M741952"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3587724","type":"journal-article","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T18:31:06Z","timestamp":1753813866000},"page":"18478-18491","source":"Crossref","is-referenced-by-count":0,"title":["A-SDM: Accelerating Stable Diffusion Through Model Assembly and Feature Inheritance Strategies"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2821-4847","authenticated-orcid":false,"given":"Jinchao","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Software, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Pan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Saharia"},{"key":"ref4","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Nichol"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Meng","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00392"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27890"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230302"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02575"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref21","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"article-title":"Photoswap: Personalized subject swapping in images","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Gu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367327"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Poole","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_22"},{"article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Li","key":"ref35"},{"article-title":"Structural pruning for diffusion models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Fang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Salimans","key":"ref40"},{"article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"L\u00fc","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"article-title":"Token merging: Your ViT but faster","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bolya","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref46","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref51","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Sohn"},{"key":"ref52","first-page":"2391","article-title":"Adversarial variational Bayes: Unifying variational autoencoders and generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Mescheder"},{"key":"ref53","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Vahdat"},{"key":"ref54","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. NIPS","author":"Van Den Oord"},{"key":"ref55","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho","key":"ref56"},{"article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song","key":"ref57"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00403"},{"key":"ref63","article-title":"DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv:2211.01095"},{"article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu","key":"ref64"},{"article-title":"Fast sampling of diffusion models with exponential integrator","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang","key":"ref65"},{"article-title":"Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bao","key":"ref66"},{"key":"ref67","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Song"},{"key":"ref68","article-title":"BOOT: Data-free distillation of denoising diffusion models with bootstrapping","author":"Gu","year":"2023","journal-title":"arXiv:2306.05544"},{"volume-title":"Small Stable Diffusion","year":"2023","author":"Pinkney","key":"ref69"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"ref71","first-page":"13213","article-title":"Simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML))","author":"Hoogeboom"},{"key":"ref72","article-title":"MobileDiffusion: Instant text-to-image generation on mobile devices","author":"Zhao","year":"2023","journal-title":"arXiv:2311.16567"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"volume-title":"Accelerate Stable Diffusion With Intel Neural Compressor","year":"2022","author":"Shen","key":"ref74"},{"volume-title":"World\u2019s First On-device Demonstration of Stable Diffusion on an Android Phone","year":"2023","author":"Hou","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00654"},{"key":"ref77","article-title":"Deediff: Dynamic uncertainty-aware early exiting for accelerating diffusion model generation","author":"Tang","year":"2023","journal-title":"arXiv:2309.17074v2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"volume-title":"Laion-aesthetics","year":"2022","author":"Schuhmann","key":"ref79"},{"article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop (NeurIPSw)","author":"Schuhmann","key":"ref80"},{"key":"ref81","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref83","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref84","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Salimans"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Workshop (NeurIPSW)","author":"Ho","key":"ref86"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11099049.pdf?arnumber=11099049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:39:32Z","timestamp":1759945172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":86,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3587724","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}