{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:33:40Z","timestamp":1780763620639,"version":"3.54.1"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72920-1_26","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"462-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Parrot: Pareto-Optimal Multi-reward Reinforcement Learning Framework for\u00a0Text-to-Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7773-7858","authenticated-orcid":false,"given":"Seung Hyun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4771-3368","authenticated-orcid":false,"given":"Yinxiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5846-9002","authenticated-orcid":false,"given":"Junjie","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-4644","authenticated-orcid":false,"given":"Innfarn","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7072-2189","authenticated-orcid":false,"given":"Han","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7085-834X","authenticated-orcid":false,"given":"Jiahui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7476-0190","authenticated-orcid":false,"given":"Qifei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0690-1718","authenticated-orcid":false,"given":"Fei","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0764-1353","authenticated-orcid":false,"given":"Glenn","family":"Entis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5465-5659","authenticated-orcid":false,"given":"Junfeng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9490-2990","authenticated-orcid":false,"given":"Gang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-0018","authenticated-orcid":false,"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6236-2969","authenticated-orcid":false,"given":"Irfan","family":"Essa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6195-2089","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"26_CR1","unstructured":"Amazon mechanical turk (2005). https:\/\/www.mturk.com\/"},{"key":"26_CR2","unstructured":"Anil, R., et al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"26_CR3","unstructured":"Bai, Y., et al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"26_CR4","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)"},{"key":"26_CR5","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"26_CR6","unstructured":"Clark, K., Vicol, P., Swersky, K., Fleet, D.J.: Directly fine-tuning diffusion models on differentiable rewards. In: ICLR (2024)"},{"key":"26_CR7","unstructured":"Dai, X., et al.: Emu: enhancing image generation models using photogenic needles in a haystack. arXiv preprint arXiv:2309.15807 (2023)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Deng, F., Wang, Q., Wei, W., Grundmann, M., Hou, T.: PRDP: proximal reward difference prediction for large-scale reward finetuning of diffusion models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00709"},{"key":"26_CR9","unstructured":"Dong, H., et al.: RAFT: reward ranked finetuning for generative foundation model alignment. arXiv preprint arXiv:2304.06767 (2023)"},{"key":"26_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR11","unstructured":"Fan, Y., Lee, K.: Optimizing DDPM sampling with shortcut fine-tuning. In: ICML (2023)"},{"key":"26_CR12","unstructured":"Fan, Y., et al.: DPOK: reinforcement learning for fine-tuning text-to-image diffusion models. In: NeurIPS (2023)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, H., Zeng, Y., Ma, K., Wang, Z.: Perceptual quality assessment of smartphone photography. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: SVDiff: compact parameter space for diffusion fine-tuning. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"26_CR15","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. arXiv preprint arXiv:2212.09611 (2022)"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"He, H., et al.: Learning profitable NFT image diffusions via multiple visual-policy guided reinforcement learning. arXiv preprint arXiv:2306.11731 (2023)","DOI":"10.1145\/3581783.3612595"},{"key":"26_CR17","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"26_CR18","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"26_CR19","first-page":"4041","volume":"29","author":"V Hosu","year":"2020","unstructured":"Hosu, V., Lin, H., Sziranyi, T., Saupe, D.: KonIQ-10k: an ecologically valid database for deep learning of blind image quality assessment. TIP 29, 4041\u20134056 (2020)","journal-title":"TIP"},{"key":"26_CR20","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Jeong, Y., et al.: The power of sound (TPoS): audio reactive video generation with stable diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00719"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: Musiq: multi-scale image quality transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Ke, J., Ye, K., Yu, J., Wu, Y., Milanfar, P., Yang, F.: Vila: learning image aesthetics from user comments with vision-language pretraining. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"26_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"26_CR26","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. arXiv preprint arXiv:2305.01569 (2023)"},{"key":"26_CR27","unstructured":"Lee, K., et al.: Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192 (2023)"},{"key":"26_CR28","unstructured":"Lee, S.H., et al.: Soundini: sound-guided diffusion for natural video editing. arXiv preprint arXiv:2304.06818 (2023)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Gligen: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"26_CR30","unstructured":"Lin, X., Yang, Z., Zhang, X., Zhang, Q.: Pareto set learning for expensive multi-objective optimization. In: NeurIPS (2022)"},{"key":"26_CR31","unstructured":"Mannor, S., Shimkin, N.: The steering approach for multi-criteria reinforcement learning. In: NeurIPS (2001)"},{"key":"26_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5563-6","volume-title":"Nonlinear Multiobjective Optimization","author":"K Miettinen","year":"1999","unstructured":"Miettinen, K.: Nonlinear Multiobjective Optimization, vol. 12. Springer, New York (1999). https:\/\/doi.org\/10.1007\/978-1-4615-5563-6"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: Ava: a large-scale database for aesthetic visual analysis. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"26_CR34","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"26_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"26_CR36","unstructured":"Rame, A., et al.: Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. In: NeurIPS (2023)"},{"key":"26_CR37","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Richardson, E., Goldberg, K., Alaluf, Y., Cohen-Or, D.: Conceptlab: creative generation using diffusion prior constraints. arXiv preprint arXiv:2308.02669 (2023)","DOI":"10.1145\/3659578"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: SIGGRAPH (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"26_CR43","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Serra, A., Carrara, F., Tesconi, M., Falchi, F.: The emotions of the crowd: learning image sentiment from tweets via cross-modal distillation. In: ECAI (2023)","DOI":"10.3233\/FAIA230503"},{"key":"26_CR45","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"26_CR46","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"26_CR47","unstructured":"Tesauro, G., et al.: Managing power consumption and performance of computing systems using reinforcement learning. In: NeurIPS (2007)"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: Maxvit: multi-axis vision transformer. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"26_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Human preference score: better aligning text-to-image models with human preference. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"26_CR51","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977 (2023)"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., Bovik, A.: From patches to pictures (PAQ-2-PIQ): mapping the perceptual space of picture quality. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"26_CR53","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Yu, L., et\u00a0al.: Magvit: masked generative video transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, B., Zhu, Y., Yang, X., Chen, C., Xu, J.: Shifted diffusion for text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00979"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72920-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:19:11Z","timestamp":1727684351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}