{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:57Z","timestamp":1778048517991,"version":"3.51.4"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00644","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6664-6675","source":"Crossref","is-referenced-by-count":0,"title":["Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment"],"prefix":"10.1109","author":[{"given":"Sangha","family":"Park","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunji","family":"Kim","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeongtak","family":"Oh","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jooyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Qwen2","author":"Bai"},{"issue":"3","key":"ref3","first-page":"8","article-title":"Improving image generation with better captions","volume-title":"Computer Science","volume":"2","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01803"},{"key":"ref6","article-title":"Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset","author":"Chen","year":"2025"},{"key":"ref7","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025"},{"key":"ref8","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-toimage generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cho"},{"issue":"70","key":"ref9","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","article-title":"Emerging properties in unified multimodal pretraining","author":"Deng","year":"2025"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_18"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2923"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Ella: Equip diffusion models with llm for enhanced semantic alignment","author":"Hu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref21","article-title":"Image generation from contextuallycontradictory prompts","author":"Huberman","year":"2025"},{"key":"ref22","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref24","article-title":"T2i-r1: Reinforcing image generation with collaborative semantic-level and token-level cot","author":"Jiang","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00680"},{"key":"ref26","journal-title":"Black Forest Labs; Frontier AI Lab"},{"key":"ref27","article-title":"Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space","author":"Batifol","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref31","article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref34","article-title":"Uniworld: High-resolution semantic encoders for unified visual understanding and generation","author":"Lin","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref36","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref38","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"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02514"},{"key":"ref41","article-title":"Personalized and sequential text-to-image generation","author":"Nabati","year":"2024"},{"key":"ref42","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref43","article-title":"Gpt-4.1","year":"2025"},{"key":"ref44","article-title":"Gpt-4o","year":"2025"},{"key":"ref45","article-title":"Rare-to-frequent: Unlocking compositional generation power of diffusion models on rare concepts with llm guidance","author":"Park","year":"2024"},{"key":"ref46","article-title":"Rare-to-frequent: Unlocking compositional generation power of diffusion models on rare concepts with LLM guidance","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Park"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref49","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00243"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref52","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":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0157"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3101"},{"key":"ref57","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref58","article-title":"Maestro: Self-improving text-to-image generation via agent orchestration","author":"Wan","year":"2025"},{"key":"ref59","article-title":"Promptenhancer: A simple approach to enhance text-to-image models via chain-of-thought prompt rewriting","author":"Wang","year":"2025"},{"key":"ref60","first-page":"50992","article-title":"On discrete prompt optimization for diffusion models","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref62","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024"},{"key":"ref63","article-title":"Tokencompose: Grounding diffusion with token-level supervision","author":"Wang","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4077"},{"key":"ref65","article-title":"Omnigen2: Exploration to advanced multimodal generation","author":"Wu","year":"2025"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref70","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xie"},{"key":"ref71","article-title":"Imagereward: Learning and evaluating human preferences for textto-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref72","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref73","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0079"},{"key":"ref75","article-title":"Echo-4o: Harnessing the power of gpt4o synthetic images for improved image generation","author":"Ye","year":"2025"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3074"},{"key":"ref77","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492087.pdf?arnumber=11492087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:04:59Z","timestamp":1778047499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00644","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}