{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:24Z","timestamp":1777865364121,"version":"3.51.4"},"reference-count":48,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376277"],"award-info":[{"award-number":["62376277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01768","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19022-19031","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Reward Models for High-Quality Image Generation: Beyond Text-Image Alignment"],"prefix":"10.1109","author":[{"given":"Ying","family":"Ba","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence Renmin University of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"iN2X"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yalong","family":"Bai","sequence":"additional","affiliation":[{"name":"iN2X"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyi","family":"Mo","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence Renmin University of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Liang","sequence":"additional","affiliation":[{"name":"iN2X"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Su","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence Renmin University of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence Renmin University of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stability AI","volume-title":"Stable diffusion 3.5 large","year":"2024"},{"key":"ref2","article-title":"Stability AI","volume-title":"Stable diffusion 3.5 large turbo","year":"2024"},{"key":"ref3","author":"Bai","year":"2024","journal-title":"Styleinject: Parameter efficient tuning of text-to-image diffusion models"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref5","author":"Clark","year":"2024","journal-title":"Directly fine-tuning diffusion models on differentiable rewards"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Esser","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2923"},{"key":"ref10","author":"Heusel","year":"2018","journal-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"10918","article-title":"ISO\/IEC. Information technology - digital compression and coding of continuous-tone still images - requirements and guidelines","volume":"1992","year":"1992","journal-title":"International Organization for Standardization"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref14","volume-title":"Black Forest Labs. Flux","year":"2024"},{"key":"ref15","author":"Li","year":"2022","journal-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation"},{"key":"ref16","author":"Loshchilov","year":"2019","journal-title":"Decoupled weight decay regularization"},{"key":"ref17","article-title":"Star: Scale-wise text-conditioned autoregressive image generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Midjourney","volume-title":"Ai-powered image generation","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02514"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00434"},{"key":"ref21","volume-title":"OpenAI. Dall-e 3","year":"2023"},{"key":"ref22","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref23","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref24","article-title":"On the out-ofdistribution generalization of self-supervised learning","author":"Qiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Qiu","year":"2023"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on ma-chine learning","author":"Radford","year":"2021"},{"key":"ref27","article-title":"Hierarchical textconditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref28","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref29","first-page":"1068410695","article-title":"Highresolution image synthesis with latent diffusion models","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Rombach","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref31","author":"Salimans","year":"2016","journal-title":"Improved techniques for training gans"},{"key":"ref32","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref33","article-title":"Learning invariant causal mechanism from vision-language models","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref35","article-title":"Instantstyle: Free lunch towards stylepreserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref37","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume-title":"arXiv preprint","author":"Wu","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref40","author":"Xu","year":"2023","journal-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611887"},{"key":"ref43","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref44","article-title":"V2flow: Unifying visual tokenization and large language model vocabularies for autoregressive image generation","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1238"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3665753"},{"key":"ref47","author":"Zhu","year":"2025","journal-title":"Llada 1.5: Variance-reduced preference optimization for large language diffusion models"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"}],"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\/11445832.pdf?arnumber=11445832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:48Z","timestamp":1777529988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01768","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}