{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:22:09Z","timestamp":1791912129781,"version":"4.3.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01637","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17618-17628","source":"Crossref","is-referenced-by-count":4,"title":["The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation"],"prefix":"10.1109","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayang","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Zhu","sequence":"additional","affiliation":[{"name":"Princeton University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Russakovsky","sequence":"additional","affiliation":[{"name":"Princeton University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A noise is worth diffusion guidance","author":"Ahn","year":"2024","journal-title":"arXiv"},{"key":"ref2","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2024","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01657"},{"key":"ref6","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref7","article-title":"Restoration-degradation beyond linear diffusions: A non-asymptotic analysis for ddim-type samplers","author":"Chen","year":"2023","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"ref9","article-title":"Layoutdiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023","journal-title":"arXiv"},{"key":"ref10","article-title":"Cfg++: Manifold-constrained classifier free guidance for diffusion models","author":"Chung","year":"2024","journal-title":"arXiv"},{"key":"ref11","first-page":"125487","article-title":"Reno: Enhancing one-step text-to-image models through reward-based noise optimization","volume":"37","author":"Eyring","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Dpok: Reinforcement learning for fine-tuning text-to-image diffusion models","author":"Fan","year":"2023","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01635"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref17","article-title":"S2st: Image-to-image translation in the seed space of latent diffusion","author":"Greenberg","year":"2023","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1973.4309314"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1962.1057692"},{"key":"ref23","article-title":"Ella: Equip diffusion models with llm for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0129"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref26","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref28","article-title":"Towards non-asymptotic convergence for diffusion-based generative models","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref29","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref30","article-title":"Aligning diffusion models by optimizing human utility","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Divide & bind your attention for improved generative semantic nursing","author":"Li","year":"2023","journal-title":"arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref36","article-title":"Inference-time scaling for diffusion models beyond scaling denoising steps","author":"Ma","year":"2025","journal-title":"arXiv"},{"key":"ref37","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","article-title":"Sowing information: Cultivating contextual coherence with mllms in image generation","author":"Pei","year":"2024","journal-title":"arXiv"},{"key":"ref41","article-title":"Not all noises are created equally: Diffusion noise selection and optimization","author":"Qi","year":"2024","journal-title":"arXiv"},{"key":"ref42","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref47","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref51","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref52","article-title":"Inference-time alignment of diffusion models with direct noise optimization","author":"Tang","year":"2024","journal-title":"arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref54","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref55","article-title":"Instantid: Zeroshot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref56","article-title":"Diffusion in diffusion: Cyclic one-way diffusion for text-vision-conditioned generation","author":"Wang","year":"2024","journal-title":"ICLR"},{"key":"ref57","article-title":"Analysis of classifier-free guidance weight schedulers","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref58","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref60","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2024","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Good seed makes a good crop: Discovering secret seeds in text-toimage diffusion models","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref63","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref65","author":"Zhang","year":"2024","journal-title":"Ic-light github page"},{"key":"ref66","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_5"},{"key":"ref68","article-title":"Unipc: A unified predictor-corrector framework for fast sampling of diffusion models","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","article-title":"Magnet: We never know how text-to-image diffusion models work, until we learn how vision-language models function","author":"Zhuang","year":"2024","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445857.pdf?arnumber=11445857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:29Z","timestamp":1777611809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01637","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}