{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T19:54:09Z","timestamp":1789070049826,"version":"build-2803163510"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,26]]},"DOI":"10.1109\/wacv61041.2025.00033","type":"proceedings-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:08:13Z","timestamp":1744132093000},"page":"232-242","source":"Crossref","is-referenced-by-count":3,"title":["Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Rohit","family":"Jena","sequence":"first","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Taghibakhshi","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahil","family":"Jain","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerald","family":"Shen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nima","family":"Tajbakhsh","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arash","family":"Vahdat","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","first-page":"32","article-title":"Spot the fake lungs: Generating synthetic medical images using neural dif-fusion models","volume-title":"Irish Conference on Artificial Intelligence and Cognitive Science","author":"Ali","year":"2022"},{"key":"ref3","article-title":"Anonymous submission","author":"Anon","journal-title":"Anonymous Venue"},{"key":"ref4","author":"Black","year":"2023","journal-title":"Training diffusion models with reinforce-ment learning"},{"key":"ref5","author":"Black","year":"2023","journal-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.75.056707"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref11","first-page":"9353","article-title":"Textdiffuser: Diffusion models as text painters","volume":"36","author":"Chen","year":"2023","journal-title":"Advances in Neural Infor-mation Processing Systems"},{"key":"ref12","article-title":"Deep reinforcement learning from human preferences","author":"F Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Directly fine-tuning diffusion models on differentiable re-wards","author":"Clark","year":"2023","journal-title":"ICLR"},{"key":"ref14","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback","volume":"36","author":"Dubois","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","author":"Eyring","year":"2024","journal-title":"Reno: Enhancing one-step text-to-image models through reward-based noise optimization"},{"key":"ref16","author":"Fan","year":"2023","journal-title":"Optimizing ddpm sampling with shortcut fine-tuning"},{"key":"ref17","article-title":"Re-inforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","volume-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Xi Feng","year":"2022"},{"key":"ref19","article-title":"Optimizing prompts for text-to-image generation","volume":"36","author":"Hao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","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":"Advances in Neural Information Processing Systems"},{"key":"ref21","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref22","first-page":"6840","article-title":"Denoising dif-fusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","author":"Hong","year":"2024","journal-title":"Margin-aware preference op-timization for aligning diffusion models without reference"},{"key":"ref24","first-page":"78723","article-title":"T2i-compbench: A comprehensive bench-mark for open-world compositional text-to-image generation","volume":"36","author":"Huang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"ref25","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyvarinen","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref29","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Advances in neural infor-mation processing systems"},{"key":"ref30","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","author":"Kuchaiev","year":"2019","journal-title":"Nemo: a toolkit for building ai applications using neural modules"},{"key":"ref32","article-title":"Improved precision and recall metric for assessing generative models","volume":"32","author":"Kynkaanniemi","year":"2019","journal-title":"Advances in neural in-formation processing systems"},{"key":"ref33","author":"Liu","year":"2023","journal-title":"Audi-oldm: Text-to-audio generation with latent diffusion models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref35","author":"Liu","year":"2022","journal-title":"Character-aware models improve visual text rendering"},{"key":"ref36","article-title":"Diff-foley: Synchronized video-to-audio synthesis with la-tent diffusion models","volume-title":"Advances in Neural Information Pro-cessing Systems","volume":"36","author":"Luo","year":"2024"},{"key":"ref37","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008923215028"},{"key":"ref39","first-page":"67021","article-title":"Auto decoding latent 3d diffusion models","volume":"36","author":"Ntavelis","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","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":"ref41","article-title":"Un-supervised medical image translation with adversarial diffu-sion models","author":"Ozbey","journal-title":"IEEE Transactions on Medical Imaging, 2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18576-2_12"},{"key":"ref43","volume-title":"Sdxl: Improving latent diffusion mod-els for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref44","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref45","volume-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervi-sion","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref47","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"International confer-ence on machine learning"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref53","article-title":"Assessing generative models via precision and recall","volume":"31","author":"SM Sajjadi","year":"2018","journal-title":"Advances in neural information pro-cessing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref55","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 In-formation Processing Systems"},{"key":"ref56","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume":"35","author":"Skalse","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"International conference on machine learning"},{"key":"ref58","article-title":"Generative modeling by esti-mating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref59","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref60","first-page":"574","article-title":"Sliced score matching: A scalable approach to density and score estimation","author":"Song","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1142\/9789814354110_0008"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref64","first-page":"8228","article-title":"Diffusion model align-ment using direct preference optimization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wallace","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref66","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural In-formation Processing Systems"},{"key":"ref67","first-page":"1623","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2024","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref69","article-title":"Imagere-ward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Pro-cessing Systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34048-2_30"}],"event":{"name":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2025,2,26]]},"end":{"date-parts":[[2025,3,6]]}},"container-title":["2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10943266\/10943193\/10943603.pdf?arnumber=10943603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T05:40:37Z","timestamp":1744177237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10943603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/wacv61041.2025.00033","relation":{},"subject":[],"published":{"date-parts":[[2025,2,26]]}}}