{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:07:05Z","timestamp":1764882425321,"version":"3.46.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["U24A20220"],"award-info":[{"award-number":["U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2024-GZL-RGZN-01008"],"award-info":[{"award-number":["2024-GZL-RGZN-01008"]}],"id":[{"id":"10.13039\/501100008838","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":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3604039","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:09:25Z","timestamp":1756404565000},"page":"359-373","source":"Crossref","is-referenced-by-count":0,"title":["Bidirectional Beta-Tuned Diffusion Model"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5270-4746","authenticated-orcid":false,"given":"Tianyi","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering in School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6002-7175","authenticated-orcid":false,"given":"Jiayang","family":"Zou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering in School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1786-4943","authenticated-orcid":false,"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1175-5918","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8954-0873","authenticated-orcid":false,"given":"Jinwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3206","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering in School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7817-0665","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Vivo Mobile Communication Co., Ltd, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"article-title":"Content-based unrestricted adversarial attack","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680894"},{"article-title":"Pinco: Position-induced consistent adapter for diffusion transformer in foreground-conditioned inpainting","year":"2024","author":"Lu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01709"},{"article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li","key":"ref6"},{"article-title":"Exploring discrete diffusion models for image captioning","year":"2022","author":"Zhu","key":"ref7"},{"article-title":"Imagen Video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref8"},{"article-title":"MimicMotion: High-quality human motion video generation with confidence-aware pose guidance","year":"2024","author":"Zhang","key":"ref9"},{"article-title":"Towards generalizable data protection with transferable unlearnable examples","year":"2023","author":"Fang","key":"ref10"},{"article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","key":"ref11"},{"key":"ref12","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"article-title":"Addressing negative transfer in diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Go","key":"ref16"},{"article-title":"Eliminating Lipschitz singularities in diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680912"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01207"},{"article-title":"Denoising task routing for diffusion models","year":"2023","author":"Park","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_27"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00240"},{"article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karras","key":"ref23"},{"key":"ref24","first-page":"11201","article-title":"Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"article-title":"Towards faster training of diffusion models: An inspiration of a consistency phenomenon","year":"2024","author":"Xu","key":"ref25"},{"article-title":"Denoising task difficulty-based curriculum for training diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref29","first-page":"2292","article-title":"Sinkhorn Distances: Lightspeed computation of optimal transport","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref30","first-page":"2681","article-title":"Interpolating between optimal transport and MMD using Sinkhorn divergences","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Feydy"},{"article-title":"DPM-Solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","key":"ref31"},{"article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","key":"ref32"},{"article-title":"Elucidating the exposure bias in diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ning","key":"ref33"},{"key":"ref34","first-page":"10236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","key":"ref35"},{"article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00127"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_20"},{"article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00387"},{"key":"ref45","first-page":"26245","article-title":"Input perturbation reduces exposure bias in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ning"},{"article-title":"DeBias the training of diffusion models","year":"2023","author":"Yu","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4008"},{"key":"ref48","first-page":"16567","article-title":"Refining generative process with discriminator guidance in score-based diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref50","article-title":"Fast training of diffusion models with masked transformers","volume":"2024","author":"Zheng","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"article-title":"MC-DiT: Contextual enhancement via clean-to-clean reconstruction for masked diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zheng","key":"ref51"},{"article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"article-title":"No other representation component is needed: Diffusion transformers can provide representation guidance by themselves","year":"2025","author":"Jiang","key":"ref54"},{"article-title":"Alleviating exposure bias in diffusion models through sampling with shifted time steps","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","key":"ref55"},{"article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref58","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref59","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"article-title":"Convergence for score-based generative modeling with polynomial complexity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61544-3_4"},{"article-title":"Input perturbation: A new paradigm between central and local differential privacy","year":"2020","author":"Kang","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67786-6_6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"article-title":"Progressive growing of GANs for improved quality, stability, and variation","year":"2017","author":"Karras","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","first-page":"6626","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":"ref71","first-page":"7958","article-title":"Generating images with sparse representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nash"},{"key":"ref72","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref73","first-page":"3929","article-title":"Improved precision and recall metric for assessing generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kynk\u00e4\u00e4nniemi"},{"article-title":"Flow matching for generative modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lipman","key":"ref74"},{"article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"article-title":"Q-ALIGN: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","key":"ref78"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00414"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11143960.pdf?arnumber=11143960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:01:37Z","timestamp":1764882097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11143960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":82,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3604039","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}