{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:02:28Z","timestamp":1790272948804,"version":"4.1.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"funder":[{"name":"Beijing Natural Science Xiaomi Innovation Joint Foundation","award":["L253007"],"award-info":[{"award-number":["L253007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3708691","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:36:20Z","timestamp":1782934580000},"page":"13636-13652","source":"Crossref","is-referenced-by-count":0,"title":["Mixture of Global and Local Experts With Diffusion Transformer for Controllable Face Generation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-7738","authenticated-orcid":false,"given":"Xuechao","family":"Zou","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Fu","sequence":"additional","affiliation":[{"name":"Ant Group","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Li","sequence":"additional","affiliation":[{"name":"Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3019","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"],"department":["Department of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushe","family":"Cao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"],"department":["Department of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6059-7943","authenticated-orcid":false,"given":"Congyan","family":"Lang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2687-7997","authenticated-orcid":false,"given":"Pin","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"],"department":["Department of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"],"department":["Department of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00598"},{"key":"ref6","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":"ref7","first-page":"9841","article-title":"GANSpace: Discovering interpretable GAN controls","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"H\u00e4rk\u00f6nen"},{"key":"ref8","first-page":"1","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref10","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088914"},{"key":"ref16","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4094"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00588"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref22","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref23","article-title":"Flux","author":"Labs","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91838-4_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4410"},{"key":"ref26","first-page":"60605","article-title":"Fast text-to-3D-aware face generation and manipulation via direct cross-modal mapping and geometric regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref27","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref28","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"ref32","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref33","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612067"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00787"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3167305"},{"key":"ref40","first-page":"1","article-title":"clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Pinkney"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00698"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00990"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01223"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00472"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref46","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer"},{"key":"ref47","first-page":"1","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lepikhin"},{"issue":"120","key":"ref48","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Riquelme"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"140","key":"ref51","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref53","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01386"},{"key":"ref55","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481026"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32661"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref61","first-page":"35779","article-title":"Prodigy: An expeditiously adaptive parameter-free learner","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mishchenko"},{"key":"ref62","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref63","first-page":"1","article-title":"Demystifying MMD GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bi\u0144kowski"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref66","article-title":"One-step image translation with text-to-image models","author":"Parmar","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00180"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3603618"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11592693.pdf?arnumber=11592693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:10:04Z","timestamp":1790269804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11592693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":73,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3708691","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":[[2026,10]]}}}