{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:47:57Z","timestamp":1780465677871,"version":"3.54.1"},"reference-count":68,"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":["92467104"],"award-info":[{"award-number":["92467104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Leading Innovative and Entrepreneur Team Introduction Program","award":["2024R01007"],"award-info":[{"award-number":["2024R01007"]}]}],"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.2025.3611831","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:45:58Z","timestamp":1758217558000},"page":"781-791","source":"Crossref","is-referenced-by-count":3,"title":["Self-Guidance: Boosting Flow and Diffusion Generation on Their Own"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6496-355X","authenticated-orcid":false,"given":"Tiancheng","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9647-3991","authenticated-orcid":false,"given":"Weijian","family":"Luo","sequence":"additional","affiliation":[{"name":"MAPLE Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9006-9180","authenticated-orcid":false,"given":"Zhiyang","family":"Chen","sequence":"additional","affiliation":[{"name":"MAPLE Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"MAPLE Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3508-1851","authenticated-orcid":false,"given":"Guo-Jun","family":"Qi","sequence":"additional","affiliation":[{"name":"MAPLE Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref2","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Karras","year":"2022"},{"key":"ref3","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref4","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. SSW","author":"Oord","year":"2016"},{"key":"ref5","first-page":"8633","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"Neural Inf. Process. Syst."},{"key":"ref6","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Poole","year":"2022"},{"key":"ref7","first-page":"8867","article-title":"Equivariant diffusion for molecule generation in 3D","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hoogeboom","year":"2022"},{"key":"ref8","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2022"},{"key":"ref9","first-page":"10236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Kingma","year":"2018"},{"key":"ref10","first-page":"9916","article-title":"Residual flows for invertible generative modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2019"},{"key":"ref11","article-title":"SDEdit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref12","article-title":"DIFFEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Couairon","year":"2022"},{"key":"ref13","article-title":"Diff-Instruct*: Towards human-preferred one-step text-to-image generative models","author":"Luo","year":"2024"},{"key":"ref14","first-page":"76525","article-title":"Diff-instruct: A universal approach for transferring knowledge from pre-trained diffusion models","author":"Luo","year":"2024","journal-title":"Neural Inf. Process. Syst."},{"key":"ref15","article-title":"Diff-instruct: Training one-step text-to-image generator model to align with human preferences","author":"Luo","year":"2024"},{"key":"ref16","article-title":"Consistency models made easy","author":"Geng","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3664"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref19","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref20","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2021"},{"key":"ref21","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref22","article-title":"Introducing stable diffusion 3.5","author":"AI","year":"2023"},{"key":"ref23","article-title":"Flux.1","author":"Labs","year":"2023"},{"key":"ref24","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"Neural Inf. Process. Syst."},{"key":"ref25","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref26","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref27","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref28","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref29","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref31","article-title":"Flow generator matching","author":"Huang","year":"2024"},{"key":"ref32","first-page":"7137","article-title":"Entropy-based training methods for scalable neural implicit samplers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo","year":"2024"},{"key":"ref33","first-page":"51810","article-title":"Enhancing adversarial robustness via score-based optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2023"},{"key":"ref34","article-title":"Integrating amortized inference with diffusion models for learning clean distribution from corrupted images","author":"Wang","year":"2024"},{"key":"ref35","article-title":"\u201cVariational Schr\u00f6dinger diffusion models","author":"Deng","year":"2024"},{"key":"ref36","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref39","first-page":"52996","article-title":"Guiding a diffusion model with a bad version of itself","author":"Karras","year":"2024","journal-title":"Neural Inf. Process. Syst."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref43","first-page":"5775","article-title":"DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"Neural Inf. Process. Syst."},{"key":"ref44","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref45","first-page":"77632","article-title":"Sa-solver: Stochastic adams solver for fast sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xue","year":"2024"},{"key":"ref46","article-title":"No training, no problem: Rethinking classifier-free guidance for diffusion models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Sadat","year":"2024"},{"key":"ref47","article-title":"Self-improving diffusion models with synthetic data","author":"Alemohammad","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2132"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681506"},{"key":"ref50","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref51","article-title":"Minimum probability flow learning","author":"Sohl-Dickstein","year":"2009"},{"key":"ref52","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","year":"2022"},{"key":"ref53","article-title":"Flow matching for generative modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref55","article-title":"clip-score: CLIP score for PyTorch","author":"Zhengwentai","year":"2023"},{"key":"ref56","article-title":"Improved aesthetic predictor","author":"Schuhmann","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"issue":"13","key":"ref59","first-page":"14838","article-title":"FaceScore: Benchmarking and enhancing face quality in human generation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Liao","year":"2024"},{"key":"ref60","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","author":"Kirstain","year":"2023","journal-title":"Neural Inf. Process. Syst."},{"key":"ref61","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"Neural Inf. Process. Syst."},{"key":"ref62","article-title":"MediaPipe hands: On-device real-time hand tracking","author":"Zhang","year":"2020"},{"key":"ref63","article-title":"Hand captions","year":"2023"},{"key":"ref64","article-title":"HumanCaption-10M","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref67","article-title":"Tag2text: Guiding vision-language model via image tagging","author":"Huang","year":"2024"},{"key":"ref68","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11172684.pdf?arnumber=11172684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:16:26Z","timestamp":1769840186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11172684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":68,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3611831","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":[[2026,1]]}}}