{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:08:27Z","timestamp":1789258107347,"version":"build-2803163510"},"reference-count":85,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134466","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:23:56Z","timestamp":1783639436000},"page":"134466","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Recent advances in human preference alignment of text-to-image diffusion models"],"prefix":"10.1016","volume":"700","author":[{"given":"Yingjie","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134466_bib0005","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134466_bib0010","author":"Wu"},{"key":"10.1016\/j.neucom.2026.134466_bib0015","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"issue":"3\/4","key":"10.1016\/j.neucom.2026.134466_bib0025","doi-asserted-by":"crossref","first-page":"324","DOI":"10.2307\/2334029","article-title":"Rank analysis of incomplete block designs: I. the method of paired comparisons","volume":"39","author":"Bradley","year":"1952","journal-title":"Biometrika"},{"key":"10.1016\/j.neucom.2026.134466_bib0030","author":"Black"},{"key":"10.1016\/j.neucom.2026.134466_bib0035","author":"Lee"},{"key":"10.1016\/j.neucom.2026.134466_bib0040","doi-asserted-by":"crossref","first-page":"79858","DOI":"10.52202\/075280-3497","article-title":"Dpok: reinforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0045","doi-asserted-by":"crossref","first-page":"15903","DOI":"10.52202\/075280-0700","article-title":"Imagereward: learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0050","author":"Clark"},{"key":"10.1016\/j.neucom.2026.134466_bib0055","series-title":"European Conference on Computer Vision","first-page":"182","article-title":"Enhancing diffusion models with text-encoder reinforcement learning","author":"Chen","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0060","series-title":"Proceedings of the 41st International Conference on Machine Learning, 235","first-page":"48892","article-title":"Feedback efficient online fine-tuning of diffusion models","author":"Uehara","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0065","doi-asserted-by":"crossref","first-page":"76177","DOI":"10.52202\/079017-2425","article-title":"Comat: aligning text-to-image diffusion model with image-to-text concept matching","volume":"37","author":"Jiang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0070","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"23604","article-title":"Towards better alignment: training diffusion models with reinforcement learning against sparse rewards","author":"Hu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0075","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 39","first-page":"15696","article-title":"DiffExp: efficient exploration in reward fine-tuning for text-to-image diffusion models","author":"Chae","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0080","author":"Xue"},{"key":"10.1016\/j.neucom.2026.134466_bib0085","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134466_bib0090","author":"Li"},{"key":"10.1016\/j.neucom.2026.134466_bib0095","series-title":"Reinforcement Learning: An Introduction","volume":"vol. 1","author":"Sutton","year":"1998"},{"issue":"3","key":"10.1016\/j.neucom.2026.134466_bib0100","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134466_bib0105","series-title":"International Conference on Machine Learning","first-page":"1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"10.1016\/j.neucom.2026.134466_bib0110","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.134466_bib0115","author":"Shao"},{"key":"10.1016\/j.neucom.2026.134466_bib0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2096","article-title":"Human preference score: better aligning text-to-image models with human preference","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0125","author":"Rafailov"},{"key":"10.1016\/j.neucom.2026.134466_bib0130","series-title":"Proceedings of the 24th International Conference on Machine Learning","first-page":"745","article-title":"Reinforcement learning by reward-weighted regression for operational space control","author":"Peters","year":"2007"},{"key":"10.1016\/j.neucom.2026.134466_bib0135","author":"Peng"},{"key":"10.1016\/j.neucom.2026.134466_bib0140","doi-asserted-by":"crossref","first-page":"16203","DOI":"10.52202\/068431-1179","article-title":"On reinforcement learning and distribution matching for fine-tuning language models with no catastrophic forgetting","volume":"35","author":"Korbak","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7423","article-title":"PRDP: proximal reward difference prediction for large-scale reward finetuning of diffusion models","author":"Deng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8228","article-title":"Diffusion model alignment using direct preference optimization","author":"Wallace","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8941","article-title":"Using human feedback to fine-tune diffusion models without any reward model","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0160","doi-asserted-by":"crossref","first-page":"24897","DOI":"10.52202\/079017-0785","article-title":"Aligning diffusion models by optimizing human utility","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0165","author":"Gu"},{"key":"10.1016\/j.neucom.2026.134466_bib0170","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134466_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13199","article-title":"Aesthetic post-training diffusion models from generic preferences with step-by-step preference optimization","author":"Liang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0180","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"DSPO: direct score preference optimization for diffusion model alignment","author":"Zhu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0185","author":"Fu"},{"key":"10.1016\/j.neucom.2026.134466_bib0190","doi-asserted-by":"crossref","first-page":"36652","DOI":"10.52202\/075280-1594","article-title":"Pick-a-Pic: an open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0195","author":"Karthik"},{"key":"10.1016\/j.neucom.2026.134466_bib0200","doi-asserted-by":"crossref","first-page":"52811","DOI":"10.52202\/075280-2299","article-title":"Censored sampling of diffusion models using 3 minutes of human feedback","volume":"36","author":"Yoon","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0205","author":"Yu"},{"key":"10.1016\/j.neucom.2026.134466_bib0210","author":"Kim"},{"key":"10.1016\/j.neucom.2026.134466_bib0215","author":"Jain"},{"key":"10.1016\/j.neucom.2026.134466_bib0220","author":"Li"},{"key":"10.1016\/j.neucom.2026.134466_bib0225","series-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","first-page":"1","article-title":"Reprompt: automatic prompt editing to refine AI-generative art towards precise expressions","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0230","doi-asserted-by":"crossref","first-page":"66923","DOI":"10.52202\/075280-2923","article-title":"Optimizing prompts for text-to-image generation","volume":"36","author":"Hao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9380","article-title":"Initno: boosting text-to-image diffusion models via initial noise optimization","author":"Guo","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0240","doi-asserted-by":"crossref","first-page":"125487","DOI":"10.52202\/079017-3987","article-title":"Reno: enhancing one-step text-to-image models through reward-based noise optimization","volume":"37","author":"Eyring","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0245","author":"Tang"},{"key":"10.1016\/j.neucom.2026.134466_bib0250","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26627","article-title":"Dynamic prompt optimizing for text-to-image generation","author":"Mo","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0255","series-title":"Companion Proceedings of the ACM Web Conference 2024","first-page":"1530","article-title":"Prompt optimizer of text-to-image diffusion models for abstract concept understanding","author":"Fan","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0260","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"9862","article-title":"Cocono: attention contrast-and-complete for initial noise optimization in text-to-image synthesis","author":"Sundaram","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0265","author":"Zhai"},{"issue":"4","key":"10.1016\/j.neucom.2026.134466_bib0270","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592116","article-title":"Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models","volume":"42","author":"Chefer","year":"2023","journal-title":"ACM trans. Graph. (TOG)"},{"key":"10.1016\/j.neucom.2026.134466_bib0275","author":"Li"},{"key":"10.1016\/j.neucom.2026.134466_bib0280","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"23636","article-title":"Reneg: learning negative embedding with reward guidance","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0285","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"13220","article-title":"DyMO: training-free diffusion model alignment with dynamic multi-objective scheduling","author":"Xie","year":"2025"},{"key":"10.1016\/j.neucom.2026.134466_bib0290","author":"Jin"},{"key":"10.1016\/j.neucom.2026.134466_bib0295","author":"Cheng"},{"key":"10.1016\/j.neucom.2026.134466_bib0300","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"7514","article-title":"CLIPScore: a reference-free evaluation metric for image captioning","author":"Hessel","year":"2021"},{"key":"10.1016\/j.neucom.2026.134466_bib0305","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134466_bib0310","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10910","article-title":"Crepe: can vision-language foundation models reason compositionally?","author":"Ma","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0315","series-title":"European Conference on Computer Vision","first-page":"366","article-title":"Evaluating text-to-visual generation with image-to-text generation","author":"Lin","year":"2024"},{"key":"10.1016\/j.neucom.2026.134466_bib0320","first-page":"1","article-title":"A size-aware graph embedding approach to remote sensing image captioning with object relative size information","volume":"64","author":"Ni","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134466_bib0325","article-title":"Improved techniques for training GANs","volume":"29","author":"Salimans","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0330","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0335","author":"Wu"},{"key":"10.1016\/j.neucom.2026.134466_bib0340","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"893","article-title":"Diffusiondb: a large-scale prompt gallery dataset for text-to-image generative models","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0345","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134466_bib0350","doi-asserted-by":"crossref","first-page":"52132","DOI":"10.52202\/075280-2270","article-title":"Geneval: an object-focused framework for evaluating text-to-image alignment","volume":"36","author":"Ghosh","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0355","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8317","article-title":"Towards VQA models that can read","author":"Singh","year":"2019"},{"key":"10.1016\/j.neucom.2026.134466_bib0360","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134466_bib0365","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"20406","article-title":"Tifa: accurate and interpretable text-to-image faithfulness evaluation with question answering","author":"Hu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0370","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neucom.2026.134466_bib0375","doi-asserted-by":"crossref","first-page":"36479","DOI":"10.52202\/068431-2643","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0380","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3043","article-title":"Dall-eval: probing the reasoning skills and social biases of text-to-image generation models","author":"Cho","year":"2023"},{"key":"10.1016\/j.neucom.2026.134466_bib0385","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.52202\/075280-0079","article-title":"What you see is what you read? Improving text-image alignment evaluation","volume":"36","author":"Yarom","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134466_bib0390","author":"Wiles"},{"key":"10.1016\/j.neucom.2026.134466_bib0395","author":"Han"},{"key":"10.1016\/j.neucom.2026.134466_bib0400","author":"Wang"},{"issue":"2","key":"10.1016\/j.neucom.2026.134466_bib0405","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MMUL.2025.3538862","article-title":"Quality assessment for text-to-image generation: a survey","volume":"32","author":"Tian","year":"2025","journal-title":"IEEE Multimed."},{"key":"10.1016\/j.neucom.2026.134466_bib0410","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1109\/TIP.2026.3654370","article-title":"Rethinking multi-focus image fusion: an input space optimisation view","volume":"35","author":"Wang","year":"2026","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"10.1016\/j.neucom.2026.134466_bib0415","doi-asserted-by":"crossref","first-page":"4646","DOI":"10.1007\/s11263-025-02409-3","article-title":"Multi-text guidance is important: multi-modality image fusion via large generative vision-language model","volume":"133","author":"Wang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134466_bib0420","article-title":"SD-fuse: an image structure-driven model for multi-focus image fusion","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"issue":"11","key":"10.1016\/j.neucom.2026.134466_bib0425","first-page":"12747","article-title":"Dynamic unary convolution in transformers","volume":"45","author":"Duan","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018643?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018643?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:31:18Z","timestamp":1789255878000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":85,"alternative-id":["S0925231226018643"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134466","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Recent advances in human preference alignment of text-to-image diffusion models","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134466","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134466"}}