{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:06:28Z","timestamp":1773378388088,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3669916","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:51:06Z","timestamp":1772657466000},"page":"36534-36547","source":"Crossref","is-referenced-by-count":0,"title":["CAPO: Causal-Adaptive Preference Optimization for Diffusion Models via Causal Inference Uncertainty"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5276-5828","authenticated-orcid":false,"given":"Sihan","family":"Hu","sequence":"first","affiliation":[{"name":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref2","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681498"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref5","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref6","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"ref10","article-title":"Adjoint matching: Fine-tuning flow and diffusion generative models with memoryless stochastic optimal control","author":"Domingo-Enrich","year":"2024","journal-title":"arXiv:2409.08861"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3584554"},{"key":"ref12","article-title":"Reward guided latent consistency distillation","author":"Li","year":"2024","journal-title":"arXiv:2403.11027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680597"},{"key":"ref14","article-title":"Feedback efficient online fine-tuning of diffusion models","author":"Uehara","year":"2024","journal-title":"arXiv:2402.16359"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref16","article-title":"Aligning few-step diffusion models with dense reward difference learning","author":"Zhang","year":"2024","journal-title":"arXiv:2411.11727"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref18","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv:2204.05862"},{"key":"ref19","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref22","first-page":"15086","article-title":"HPSv3: Towards wide-spectrum human preference score","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Ma"},{"key":"ref23","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref24","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rafailov"},{"key":"ref25","article-title":"Directly fine-tuning diffusion models on differentiable rewards","author":"Clark","year":"2023","journal-title":"arXiv:2309.17400"},{"key":"ref26","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref29","article-title":"Self-play preference optimization for language model alignment","author":"Wu","year":"2024","journal-title":"arXiv:2405.00675"},{"key":"ref30","article-title":"Contrastive preference optimization: Pushing the boundaries of LLM performance in machine translation","author":"Xu","year":"2024","journal-title":"arXiv:2401.08417"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00269"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01721"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref35","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Gal"},{"key":"ref36","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Malinin"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref38","volume-title":"Flux","year":"2024"},{"key":"ref39","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3067"},{"key":"ref41","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann"},{"key":"ref42","article-title":"Diffusion-NPO: Negative preference optimization for better preference aligned generation of diffusion models","author":"Wang","year":"2025","journal-title":"arXiv:2505.11245"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11421317.pdf?arnumber=11421317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:40Z","timestamp":1773347920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11421317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3669916","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}