{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T21:42:28Z","timestamp":1763415748438,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Quan Cheng Laboratory","award":["QCLZD202301"],"award-info":[{"award-number":["QCLZD202301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657787","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2145-2155","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Capability-aware Prompt Reformulation Learning for Text-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-5245","authenticated-orcid":false,"given":"Jingtao","family":"Zhan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University &amp; Quan Cheng Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"Quan Cheng Laboratory &amp; Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University &amp; Zhongguancun Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0957-1744","authenticated-orcid":false,"given":"Jia","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8762-8268","authenticated-orcid":false,"given":"Shaoping","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University &amp; Zhongguancun Laboratory, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. PromptHero - Search prompts for Stable Diffusion ChatGPT & Midjourney. https:\/\/prompthero.com\/ Accessed: 2024-01--20."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. Stable Diffusion - Prompts examples. https:\/\/stablediffusion-fr. webpkgcache.com\/doc\/-\/s\/stablediffusion.fr\/prompts Accessed: 2024-01-20."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30192-9_58"},{"key":"e_1_3_2_1_4_1","unstructured":"bluelovers. 2023. ChatGPT Stable Diffusion Prompts Generator. https:\/\/gist.github.com\/bluelovers\/92dac6fe7dcbafd7b5ae0557e638e6ef#filechatgpt-stable-diffusion-prompts-generator-txt. Accessed: 2023-7-20."},{"key":"e_1_3_2_1_5_1","volume-title":"Query reformulation mining: models, patterns, and applications. Information retrieval 14","author":"Boldi Paolo","year":"2011","unstructured":"Paolo Boldi, Francesco Bonchi, Carlos Castillo, and Sebastiano Vigna. 2011. Query reformulation mining: models, patterns, and applications. Information retrieval 14 (2011), 257--289."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606725"},{"key":"e_1_3_2_1_7_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_8_1","volume-title":"Maarten De Rijke, et al","author":"Cai Fei","year":"2016","unstructured":"Fei Cai, Maarten De Rijke, et al. 2016. A survey of query auto completion in information retrieval. Foundations and Trends\u00ae in Information Retrieval 10, 4 (2016), 273--363."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2071389.2071390"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20210"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448127"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450127"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2018.06.009"},{"key":"e_1_3_2_1_14_1","volume-title":"Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning. arXiv preprint arXiv:2012.10033","author":"Chen Jerry Zikun","year":"2020","unstructured":"Jerry Zikun Chen, Shi Yu, and Haoran Wang. 2020. Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning. arXiv preprint arXiv:2012.10033 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Manipulating Embeddings of Stable Diffusion Prompts. arXiv preprint arXiv:2308.12059","author":"Deckers Niklas","year":"2023","unstructured":"Niklas Deckers, Julia Peters, and Martin Potthast. 2023. Manipulating Embeddings of Stable Diffusion Prompts. arXiv preprint arXiv:2308.12059 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133010"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/351325.351327"},{"key":"e_1_3_2_1_18_1","volume-title":"MTTN: Multi-Pair Text to Text Narratives for Prompt Generation. arXiv preprint arXiv:2301.10172","author":"Ghosh Archan","year":"2023","unstructured":"Archan Ghosh, Debgandhar Ghosh, Madhurima Maji, Suchinta Chanda, and Kalporup Goswami. 2023. MTTN: Multi-Pair Text to Text Narratives for Prompt Generation. arXiv preprint arXiv:2301.10172 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484055"},{"key":"e_1_3_2_1_20_1","volume-title":"Georgios Roumpos, Tao Wu, and Ritesh Agarwal.","author":"Halder Kishaloy","year":"2020","unstructured":"Kishaloy Halder, Heng-Tze Cheng, Ellie Ka In Chio, Georgios Roumpos, Tao Wu, and Ritesh Agarwal. 2020. Modeling Information Need of Users in Search Sessions. arXiv preprint arXiv:2001.00861 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"Optimizing prompts for text-to-image generation. arXiv preprint arXiv:2212.09611","author":"Hao Yaru","year":"2022","unstructured":"Yaru Hao, Zewen Chi, Li Dong, and Furu Wei. 2022. Optimizing prompts for text-to-image generation. arXiv preprint arXiv:2212.09611 (2022)."},{"key":"e_1_3_2_1_22_1","unstructured":"Tim Head Manoj Kumar Holger Nahrstaedt Gilles Louppe and Iaroslav Shcherbatyi. 2021. scikit-optimize\/scikit-optimize."},{"key":"e_1_3_2_1_23_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609614"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02239"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"e_1_3_2_1_27_1","volume-title":"Variational diffusion models. Advances in neural information processing systems 34","author":"Kingma Diederik","year":"2021","unstructured":"Diederik Kingma, Tim Salimans, Ben Poole, and Jonathan Ho. 2021. Variational diffusion models. Advances in neural information processing systems 34 (2021), 21696--21707."},{"key":"e_1_3_2_1_28_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"volume-title":"Midjourney: An Independent Research Lab Exploring New Mediums of Thought. https:\/\/www.midjourney.com\/. [Online","year":"2023","key":"e_1_3_2_1_32_1","unstructured":"Midjourney. 2023. Midjourney: An Independent Research Lab Exploring New Mediums of Thought. https:\/\/www.midjourney.com\/. [Online; accessed 21- January-2024]."},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/cdn.openai.com\/papers\/gpt-4.pdf. Accessed: 2023-11-13."},{"key":"e_1_3_2_1_34_1","unstructured":"OpenAI. 2023. Improving Image Generation with Better Captions. https:\/\/cdn. openai.com\/papers\/dall-e-3.pdf. Accessed: 2023-11-13."},{"key":"e_1_3_2_1_35_1","volume-title":"A taxonomy of prompt modifiers for text-to-image generation. arXiv preprint arXiv:2204.13988 2","author":"Oppenlaender Jonas","year":"2022","unstructured":"Jonas Oppenlaender. 2022. A taxonomy of prompt modifiers for text-to-image generation. arXiv preprint arXiv:2204.13988 2 (2022)."},{"key":"e_1_3_2_1_36_1","unstructured":"Guy Parsons. 2022. The DALL\u00b7E 2 Prompt Book. https:\/\/dallery.gallery\/the-dalle-2-prompt-book."},{"key":"e_1_3_2_1_37_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV]","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV]"},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199006)41:4<288::AID-ASI8>3.0.CO;2-H"},{"key":"e_1_3_2_1_41_1","unstructured":"Christoph Schuhmann. 2022. Improved Aesthetic Predictor. https:\/\/github.com\/ christophschuhmann\/improved-aesthetic-predictor."},{"key":"e_1_3_2_1_42_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems 35 (2022), 25278--25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","volume-title":"Prompt Stealing Attacks Against Text-to-Image Generation Models. arXiv preprint arXiv:2302.09923","author":"Shen Xinyue","year":"2023","unstructured":"Xinyue Shen, Yiting Qu, Michael Backes, and Yang Zhang. 2023. Prompt Stealing Attacks Against Text-to-Image Generation Models. arXiv preprint arXiv:2302.09923 (2023)."},{"volume-title":"Acm sigir forum","author":"Silverstein Craig","key":"e_1_3_2_1_44_1","unstructured":"Craig Silverstein, Hannes Marais, Monika Henzinger, and Michael Moricz. 1999. Analysis of a very large web search engine query log. In Acm sigir forum, Vol. 33. ACM New York, NY, USA, 6--12."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806493"},{"key":"e_1_3_2_1_46_1","volume-title":"Use of query reformulation and relevance feedback by Excite users. Internet research 10, 4","author":"Spink Amanda","year":"2000","unstructured":"Amanda Spink, Bernard J Jansen, and H Cenk Ozmultu. 2000. Use of query reformulation and relevance feedback by Excite users. Internet research 10, 4 (2000), 317--328."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"e_1_3_2_1_48_1","volume-title":"Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462","author":"Witteveen Sam","year":"2022","unstructured":"Sam Witteveen and Martin Andrews. 2022. Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. arXiv preprint arXiv:2306.09341","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. arXiv preprint arXiv:2306.09341 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587430"},{"key":"e_1_3_2_1_51_1","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"How neural networks extrapolate: From feedforward to graph neural networks. arXiv preprint arXiv:2009.11848","author":"Xu Keyulu","year":"2020","unstructured":"Keyulu Xu, Mozhi Zhang, Jingling Li, Simon S Du, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2020. How neural networks extrapolate: From feedforward to graph neural networks. arXiv preprint arXiv:2009.11848 (2020)."},{"key":"e_1_3_2_1_53_1","unstructured":"Peiyuan Zhang Guangtao Zeng Tianduo Wang and Wei Lu. 2024. TinyLlama: An Open-Source Small Language Model. arXiv:2401.02385 [cs.CL]"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Washington DC USA","acronym":"SIGIR 2024"},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657787","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:40:42Z","timestamp":1755841242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657787"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":54,"alternative-id":["10.1145\/3626772.3657787","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657787","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}