{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:30Z","timestamp":1784268570171,"version":"3.55.0"},"reference-count":87,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.01670","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17972-17983","source":"Crossref","is-referenced-by-count":1,"title":["Dual-Process Image Generation"],"prefix":"10.1109","author":[{"given":"Grace","family":"Luo","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Granskog","sequence":"additional","affiliation":[{"name":"Runway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksander","family":"Holynski","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Building normalizing flows with stochastic interpolants","volume-title":"The Eleventh International Conference on Learning Representations","author":"Albergo","year":"2023"},{"key":"ref4","article-title":"Qwen2.5vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00091"},{"key":"ref6","author":"Betker","journal-title":"Improving image generation with better captions"},{"key":"ref7","article-title":"Training diffusion models with reinforcement learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Black","year":"2024"},{"key":"ref8","author":"Brown","year":"2025","journal-title":"Large language monkeys: Scaling inference compute with repeated sampling"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01227"},{"key":"ref12","article-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref14","article-title":"Davidsonian Scene Graph: Improving Reliability in Fine-Grained Evaluation for Text-to-Image Generation","volume-title":"ICLR","author":"Cho","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems, Red Hook, NY, USA","author":"Dhariwal","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref19","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref20","article-title":"Reno: Enhancing one-step text-to-image models through reward-based noise optimization","author":"Eyring","year":"2024","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","article-title":"Dpok: reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, Red Hook, NY, USA","author":"Fan","year":"2023"},{"key":"ref22","article-title":"Commonsense-t2i challenge: Can text-to-image generation models understand commonsense? In First Conference on Language Modeling, 2024","volume-title":"2, 4, 1","author":"Fu"},{"key":"ref23","article-title":"Concept sliders: Lora adaptors for precise control in diffusion models","author":"Gandikota","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"10835","article-title":"Scaling laws for reward model overoptimization","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Gao","year":"2023"},{"key":"ref25","author":"Gao","year":"2024","journal-title":"Diffusion meets flow matching: Two sides of the same coin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref27","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref30","volume-title":"Faulty reward functions in the wild","author":"Amodei","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"ref34","article-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011","journal-title":"Farrar, Straus and Giroux"},{"key":"ref35","article-title":"Dag: Depthaware guidance with denoising diffusion probabilistic models","author":"Kim","year":"2022","journal-title":"arXiv preprint arXiv: Arxiv-2212.08861"},{"key":"ref36","article-title":"Testtime alignment of diffusion models without reward overoptimization","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kim","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref39","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref40","article-title":"What matters when building vision-language models? In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024","volume-title":"2, 4, 7, 1","author":"Laurencon"},{"key":"ref41","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref42","article-title":"LLMgrounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","first-page":"366","article-title":"Evaluating text-to-visual generation with image-to-text generation","volume-title":"Computer Vision - ECCV 2024: 18th European Conference, Milan, Italy","author":"Lin","year":"2024"},{"key":"ref45","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref47","volume-title":"System prompt of chatgpt","author":"Liu","year":"2024"},{"key":"ref48","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"ref50","author":"Luo","journal-title":"Latent consistency models: Synthesizing highresolution images with few-step inference"},{"key":"ref51","author":"Ma","journal-title":"Inference-time scaling for diffusion models beyond scaling denoising steps"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref53","author":"Mondrian","year":"1929","journal-title":"Composition"},{"key":"ref54","author":"Mondrian","year":"1930","journal-title":"Composition with red, blue, and yellow"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.374"},{"key":"ref56","article-title":"OpenAI","volume-title":"Gpt-4o system card","year":"2024"},{"key":"ref57","article-title":"OpenAI","volume-title":"Introducing 4o image generation","year":"2025"},{"key":"ref58","article-title":"The effects of reward misspecification: Mapping and mitigating misaligned models","volume-title":"International Conference on Learning Representations","author":"Pan","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref60","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole","year":"2023"},{"key":"ref61","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref63","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"ref67","article-title":"Quantifying language models\u2019 sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting","volume-title":"ICLR","author":"Sclar","year":"2024"},{"key":"ref68","author":"Singhal","year":"2025","journal-title":"A general framework for inference-time scaling and steering of diffusion models"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.119.1.3"},{"key":"ref70","article-title":"Scaling LLM test-time compute optimally can be more effective than scaling parameters for reasoning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Victor Snell","year":"2025"},{"key":"ref71","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, pages 22562265, Lille, France","author":"Sohl-Dickstein","year":"2015"},{"key":"ref72","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref73","volume-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024"},{"key":"ref74","volume-title":"Gemma 3","year":"2025"},{"key":"ref75","author":"Tong","year":"2024","journal-title":"Metamorph: Multimodal understanding and generation via instruction tuning"},{"key":"ref76","article-title":"Sketchguided text-to-image diffusion models","volume-title":"New York, NY, USA, 2023. Association for Computing Machinery","author":"Voynov"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref80","volume-title":"Piet mondrian - Wikipedia, the free encyclopedia","year":"2025"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref82","article-title":"Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wu","year":"2025"},{"key":"ref83","volume-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie"},{"key":"ref84","first-page":"15903","article-title":"Imagereward: learning and evaluating human preferences for text-to-image generation","volume-title":"Proceedings of the 37 th International Conference on Neural Information Processing Systems","author":"Xu","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38107"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref87","author":"Zhang","journal-title":"Adding conditional control to text-to-image diffusion models, 2023"},{"key":"ref88","author":"Zhang","year":"2023","journal-title":"Gpt-4v(ision) as a generalist evaluator for vision-language tasks"}],"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\/11445163.pdf?arnumber=11445163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:15Z","timestamp":1777612755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01670","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}