{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:48Z","timestamp":1777888968217,"version":"3.51.4"},"reference-count":51,"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 Science Foundation of China","doi-asserted-by":"publisher","award":["62025401,62341407,U24B200170,62406008,62222606"],"award-info":[{"award-number":["62025401,62341407,U24B200170,62406008,62222606"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Program","doi-asserted-by":"publisher","award":["Z241100004224015"],"award-info":[{"award-number":["Z241100004224015"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223004"],"award-info":[{"award-number":["L223004"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"'111' Project","doi-asserted-by":"publisher","award":["B18001"],"award-info":[{"award-number":["B18001"]}],"id":[{"id":"10.13039\/501100013314","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\/iccv51701.2025.00187","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1924-1934","source":"Crossref","is-referenced-by-count":0,"title":["Entropy-Adaptive Diffusion Policy Optimization with Dynamic Step Alignment"],"prefix":"10.1109","author":[{"given":"Renye","family":"Yan","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jikang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaozhong","family":"Gan","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfan","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Lin","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeshuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimao","family":"Cai","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"SBEED: convergent reinforcement learning with nonlinear function approximation","volume-title":"Proceedings of International Conference on Machine Learning,","author":"Dai","year":"2018"},{"key":"ref3","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3987"},{"key":"ref5","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref6","article-title":"Transductive off-policy proximal policy optimization","author":"Gan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Reflective policy optimization","author":"Gan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","first-page":"10835","article-title":"Scaling laws for reward model overoptimization","volume-title":"International Conference on Machine Learning","author":"Gao","year":"2023"},{"key":"ref9","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2017"},{"key":"ref10","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref11","first-page":"25732","article-title":"A max-min entropy framework for reinforcement learning","volume":"34","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00033"},{"key":"ref15","article-title":"Bk-sdm: Architecturally compressed stable diffusion for efficient text-to-image generation","author":"Kim","year":"2023","journal-title":"Workshop on Efficient Systems for Foundation Models@ ICML2023"},{"key":"ref16","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref18","article-title":"Faster diffusion: Rethinking the role of unet encoder in diffusion models","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/434"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4270"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih","year":"2016"},{"key":"ref23","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref24","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol","year":"2021"},{"key":"ref25","article-title":"Efficient controllable diffusion via optimal classifier guidance","author":"Oertell","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PmLR. 5","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"issue":"2","key":"ref29","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref32","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0687"},{"key":"ref36","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref37","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Is noise conditioning necessary for denoising generative models?","author":"Sun","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755499"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"key":"ref41","article-title":"Finetuning of continuous-time diffusion models as entropyregularized control","author":"Uehara","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref44","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 preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191424"},{"key":"ref48","article-title":"The explorationexploitation dilemma revisited: An entropy perspective","author":"Yan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref50","article-title":"Adadiff: Adaptive step selection for fast diffusion","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","first-page":"60396","article-title":"Confronting reward overoptimization for diffusion models: A perspective of inductive and primacy biases","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2024"}],"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\/11446119.pdf?arnumber=11446119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:57Z","timestamp":1777611837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00187","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}