{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:58Z","timestamp":1777889278816,"version":"3.51.4"},"reference-count":59,"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\/501100012166","name":"National Key Research and Development Plan","doi-asserted-by":"publisher","award":["2024YFB3309302"],"award-info":[{"award-number":["2024YFB3309302"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.00071","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"678-687","source":"Crossref","is-referenced-by-count":0,"title":["ShortFT: Diffusion Model Alignment via Shortcut-Based Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Xiefan","family":"Guo","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex and Critical Software Environment,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaomiao","family":"Cui","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex and Critical Software Environment,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex and Critical Software Environment,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex and Critical Software Environment,Beijing,China,100191"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_11"},{"key":"ref5","article-title":"Deep reinforcement learning from human preferences","volume-title":"NeurIPS","author":"Christiano","year":"2017"},{"key":"ref6","article-title":"Directly fine-tuning diffusion models on differentiable rewards","volume-title":"ICLR","author":"Clark","year":"2024"},{"key":"ref7","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00709"},{"key":"ref9","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref10","article-title":"Raft: Reward ranked finetuning for generative foundation model alignment","author":"Dong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"NeurIPS","author":"Fan","year":"2023"},{"key":"ref12","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"NeurIPS","author":"Fan","year":"2023"},{"key":"ref13","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume-title":"NeurIPS","author":"Griffith","year":"2013"},{"key":"ref14","article-title":"Matryoshka diffusion models","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"I4vgen: Image as free stepping stone for text-tovideo generation","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref17","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref19","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_25"},{"key":"ref22","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"NeurIPS","author":"Karras","year":"2022"},{"key":"ref23","article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref25","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Reward guided latent consistency distillation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"T2vturbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Aligning diffusion models by optimizing human utility","volume-title":"NeurIPS","author":"Li","year":"2024"},{"key":"ref30","article-title":"Step-aware preference optimization: Aligning preference with denoising performance at each step","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Sdxllightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Improved denoising diffusion probabilistic models","volume-title":"ICML","author":"Nichol","year":"2021"},{"key":"ref33","article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurIPS","author":"Ouyang","year":"2022"},{"key":"ref34","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref36","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"NeurIPS","author":"Rafailov","year":"2023"},{"key":"ref37","article-title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans","year":"2022"},{"key":"ref40","article-title":"Fast highresolution image synthesis with latent adversarial diffusion distillation","author":"Sauer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Adversarial diffusion distillation","volume-title":"ECCV","author":"Sauer","year":"2024"},{"key":"ref42","volume-title":"Laoin aesthetic predictor","author":"Schuhmann","year":"2022"},{"key":"ref43","article-title":"A picture is worth a thousand words: Principled recaptioning improves image generation","author":"Segalis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref45","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref46","article-title":"Consistency models","volume-title":"ICML","author":"Song","year":"2023"},{"key":"ref47","article-title":"Learning to summarize with human feedback","volume-title":"NeurIPS","author":"Stiennon","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref49","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 preprint"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00200","article-title":"Human preference score: Better aligning text-toimage models with human preference","volume-title":"ICCV","author":"Wu","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_7"},{"key":"ref52","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"NeurIPS","author":"Xu","year":"2023"},{"key":"ref53","article-title":"Raphael: Text-to-image generation via large mixture of diffusion paths","volume-title":"NeurIPS","author":"Xue","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref55","article-title":"A dense reward view on aligning text-to-image diffusion with preference","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_1"},{"key":"ref59","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019","journal-title":"arXiv preprint"}],"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\/11446180.pdf?arnumber=11446180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:50Z","timestamp":1777612130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00071","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}