{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:19Z","timestamp":1774420159192,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888279","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Text-to-Image Diffusion Models without Human Feedback"],"prefix":"10.1109","author":[{"given":"Tao","family":"Liu","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"}]},{"given":"Huafeng","family":"Kuang","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"}]},{"given":"Xianming","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023"},{"key":"ref5","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref8","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Constitutional ai: Harmlessness from ai feedback","author":"Bai","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.626"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref12","article-title":"Rlaif: Scaling reinforcement learning from human feedback with ai feedback","author":"Lee","year":"2023"},{"key":"ref13","article-title":"Raft: Reward ranked finetuning for generative foundation model alignment","author":"Dong","year":"2023"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref15","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref17","article-title":"Selective annotation makes language models better few-shot learners","author":"Su","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"3","key":"ref19","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref21","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref22","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888279.pdf?arnumber=10888279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:44Z","timestamp":1774416404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888279","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}