{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:56:46Z","timestamp":1791478606449,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":98,"publisher":"ACM","funder":[{"name":"Hong Kong Research Grants Council","award":["GRF-15229423"],"award-info":[{"award-number":["GRF-15229423"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754961","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"6634-6643","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal LLMs Can Reason about Aesthetics in Zero-Shot"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-6767","authenticated-orcid":false,"given":"Ruixiang","family":"Jiang","sequence":"first","affiliation":[{"name":"Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00043125.2014.11519256"},{"key":"e_1_3_2_1_3_1","volume-title":"Meet Claude. https:\/\/www.anthropic.com\/claude.","unstructured":"Anthropic. [n.d.]. Meet Claude. https:\/\/www.anthropic.com\/claude."},{"key":"e_1_3_2_1_4_1","volume-title":"Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930","author":"Bai Zechen","year":"2024","unstructured":"Zechen Bai, Pichao Wang, Tianjun Xiao, Tong He, Zongbo Han, Zheng Zhang, and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930 (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Sylvan Barnet. 2015. A short guide to writing about art. Pearson Upper Saddle River NJ."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681656"},{"key":"e_1_3_2_1_7_1","volume-title":"Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301","author":"Black Kevin","year":"2023","unstructured":"Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, and Sergey Levine. 2023. Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Computational aesthetics and applications. Visual computing for industry, biomedicine, and art","author":"Bo Yihang","year":"2018","unstructured":"Yihang Bo, Jinhui Yu, and Kang Zhang. 2018. Computational aesthetics and applications. Visual computing for industry, biomedicine, and art, Vol. 1 (2018), 1-19."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1037\/aca0000136"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410672"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv15wxp3j.10"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_2_1_15_1","volume-title":"Directly fine-tuning diffusion models on differentiable rewards. arXiv preprint arXiv:2309.17400","author":"Clark Kevin","year":"2023","unstructured":"Kevin Clark, Paul Vicol, Kevin Swersky, and David J Fleet. 2023. Directly fine-tuning diffusion models on differentiable rewards. arXiv preprint arXiv:2309.17400 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/1540_6245.jaac25.2.0197"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"e_1_3_2_1_18_1","volume-title":"Can: Creative adversarial networks, generating'' art'' by learning about styles and deviating from style norms. arXiv preprint arXiv:1706.07068","author":"Elgammal Ahmed","year":"2017","unstructured":"Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, and Marian Mazzone. 2017. Can: Creative adversarial networks, generating'' art'' by learning about styles and deviating from style norms. arXiv preprint arXiv:1706.07068 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"The rating of chessplayers: Past and present. (No Title)","author":"Elo Arpad E","year":"1978","unstructured":"Arpad E Elo and Sam Sloan. 1978. The rating of chessplayers: Past and present. (No Title) (1978)."},{"key":"e_1_3_2_1_20_1","volume-title":"Styleshot: A snapshot on any style. arXiv preprint arXiv:2407.01414","author":"Gao Junyao","year":"2024","unstructured":"Junyao Gao, Yanchen Liu, Yanan Sun, Yinhao Tang, Yanhong Zeng, Kai Chen, and Cairong Zhao. 2024. Styleshot: A snapshot on any style. arXiv preprint arXiv:2407.01414 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_22_1","volume-title":"This AI Helps You Paint Like Van Gogh. https:\/\/www.livescience.com\/60536-ai-helps-you-paint-like-van-gogh.html. Live Science (sep","author":"Ghose Tia","year":"2017","unstructured":"Tia Ghose. 2017. This AI Helps You Paint Like Van Gogh. https:\/\/www.livescience.com\/60536-ai-helps-you-paint-like-van-gogh.html. Live Science (sep 2017). Accessed: 2025-04-09."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.2307\/1573240"},{"key":"e_1_3_2_1_24_1","volume-title":"The story of art","author":"Gombrich Ernst Hans","unstructured":"Ernst Hans Gombrich and EH Gombrich. 1995. The story of art. Vol. 12. Phaidon London."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/jade.12233"},{"key":"e_1_3_2_1_26_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025a. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step. arXiv preprint arXiv:2501.13926","author":"Guo Ziyu","year":"2025","unstructured":"Ziyu Guo, Renrui Zhang, Chengzhuo Tong, Zhizheng Zhao, Peng Gao, Hongsheng Li, and Pheng-Ann Heng. 2025b. Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step. arXiv preprint arXiv:2501.13926 (2025)."},{"key":"e_1_3_2_1_28_1","volume-title":"Training large language models to reason in a continuous latent space. arXiv preprint arXiv:2412.06769","author":"Hao Shibo","year":"2024","unstructured":"Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. 2024. Training large language models to reason in a continuous latent space. arXiv preprint arXiv:2412.06769 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asx076"},{"key":"e_1_3_2_1_30_1","volume-title":"Aesthetics: Lectures on fine art.","author":"Friedrich Hegel Georg Wilhelm","year":"1998","unstructured":"Georg Wilhelm Friedrich Hegel and GWF Hegel. 1998. Aesthetics: Lectures on fine art. Vol. 1. Oxford University Press."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.976235"},{"key":"e_1_3_2_1_32_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_34_1","volume-title":"Diffstyler: Controllable dual diffusion for text-driven image stylization","author":"Huang Nisha","year":"2024","unstructured":"Nisha Huang, Yuxin Zhang, Fan Tang, Chongyang Ma, Haibin Huang, Weiming Dong, and Changsheng Xu. 2024b. Diffstyler: Controllable dual diffusion for text-driven image stylization. IEEE Transactions on Neural Networks and Learning Systems (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680649"},{"key":"e_1_3_2_1_37_1","volume-title":"Artificial intelligence and aesthetic judgment. arXiv preprint arXiv:2309.12338","author":"Hullman Jessica","year":"2023","unstructured":"Jessica Hullman, Ari Holtzman, and Andrew Gelman. 2023. Artificial intelligence and aesthetic judgment. arXiv preprint arXiv:2309.12338 (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"David Hume. 1757. Of the Standard of Taste. Essays Moral Political and Literary ( 1757). https:\/\/oll.libertyfund.org\/titles\/hume-essays-moral-political-literary-lf-ed"},{"key":"e_1_3_2_1_39_1","volume-title":"Computer Graphics Forum","author":"Ioannou Eleftherios","unstructured":"Eleftherios Ioannou and Steve Maddock. 2024. Evaluation in Neural Style Transfer: A Review. In Computer Graphics Forum. Wiley Online Library, e15165."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.676032"},{"key":"e_1_3_2_1_41_1","volume-title":"Artist: Aesthetically Controllable Text-Driven Stylization without Training. arXiv preprint arXiv:2407.15842","author":"Jiang Ruixiang","year":"2024","unstructured":"Ruixiang Jiang and Changwen Chen. 2024. Artist: Aesthetically Controllable Text-Driven Stylization without Training. arXiv preprint arXiv:2407.15842 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2011.941851"},{"key":"e_1_3_2_1_44_1","volume-title":"Ed. Lewis White Beck. Indianapolis: Bobbs-Merrill","volume":"950","author":"Kant Immanuel","year":"1950","unstructured":"Immanuel Kant. 1950. Prolegomena to any future metaphysics (1783). Ed. Lewis White Beck. Indianapolis: Bobbs-Merrill, Vol. 950 (1950)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804656"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"e_1_3_2_1_47_1","volume-title":"Formal analysis of art: Proxy learning of visual concepts from style through language models. arXiv preprint arXiv:2201.01819","author":"Kim Diana","year":"2022","unstructured":"Diana Kim, Ahmed Elgammal, and Marian Mazzone. 2022. Formal analysis of art: Proxy learning of visual concepts from style through language models. arXiv preprint arXiv:2201.01819 (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_49_1","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 36652-36663.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199-22213."},{"key":"e_1_3_2_1_51_1","volume-title":"On dominance relations and the structure of animal societies: I. Effect of inherent characteristics. The bulletin of mathematical biophysics","author":"Landau G","year":"1951","unstructured":"HymanG Landau. 1951. On dominance relations and the structure of animal societies: I. Effect of inherent characteristics. The bulletin of mathematical biophysics, Vol. 13, 1 (1951), 1-19."},{"key":"e_1_3_2_1_52_1","volume-title":"Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245","author":"Li Daiqing","year":"2024","unstructured":"Daiqing Li, Aleks Kamko, Ehsan Akhgari, Ali Sabet, Linmiao Xu, and Suhail Doshi. 2024. Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245 (2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_54_1","volume-title":"M2iv: Towards efficient and fine-grained multimodal in-context learning in large vision-language models. arXiv preprint arXiv:2504.04633","author":"Li Yanshu","year":"2025","unstructured":"Yanshu Li, Hongyang He, Yi Cao, Qisen Cheng, Xiang Fu, and Ruixiang Tang. 2025a. M2iv: Towards efficient and fine-grained multimodal in-context learning in large vision-language models. arXiv preprint arXiv:2504.04633 (2025)."},{"key":"e_1_3_2_1_55_1","volume-title":"TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration. arXiv preprint arXiv:2505.17098","author":"Li Yanshu","year":"2025","unstructured":"Yanshu Li, Tian Yun, Jianjiang Yang, Pinyuan Feng, Jinfa Huang, and Ruixiang Tang. 2025b. TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration. arXiv preprint arXiv:2505.17098 (2025)."},{"key":"e_1_3_2_1_56_1","volume-title":"The artbench dataset: Benchmarking generative models with artworks. arXiv preprint arXiv:2206.11404","author":"Liao Peiyuan","year":"2022","unstructured":"Peiyuan Liao, Xiuyu Li, Xihui Liu, and Kurt Keutzer. 2022. The artbench dataset: Benchmarking generative models with artworks. arXiv preprint arXiv:2206.11404 (2022)."},{"key":"e_1_3_2_1_57_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1080\/20445911.2011.539556"},{"key":"e_1_3_2_1_59_1","volume-title":"Heli Ben-Hamu, Maximilian Nickel, and Matt Le.","author":"Lipman Yaron","year":"2022","unstructured":"Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)."},{"key":"e_1_3_2_1_60_1","volume-title":"Mind your step (by step): Chain-of-thought can reduce performance on tasks where thinking makes humans worse. arXiv preprint arXiv:2410.21333","author":"Liu Ryan","year":"2024","unstructured":"Ryan Liu, Jiayi Geng, Addison J Wu, Ilia Sucholutsky, Tania Lombrozo, and Thomas L Griffiths. 2024. Mind your step (by step): Chain-of-thought can reduce performance on tasks where thinking makes humans worse. arXiv preprint arXiv:2410.21333 (2024)."},{"key":"e_1_3_2_1_61_1","volume-title":"Fine-Grained Zero-Shot Object Detection. arXiv preprint arXiv:2507.10358","author":"Ma Hongxu","year":"2025","unstructured":"Hongxu Ma, Chenbo Zhang, Lu Zhang, Jiaogen Zhou, Jihong Guan, and Shuigeng Zhou. 2025. Fine-Grained Zero-Shot Object Detection. arXiv preprint arXiv:2507.10358 (2025)."},{"key":"e_1_3_2_1_62_1","volume-title":"Conditional logit analysis of qualitative choice behavior. Frontiers in Econometrics","author":"McFadden Daniel","year":"1972","unstructured":"Daniel McFadden. 1972. Conditional logit analysis of qualitative choice behavior. Frontiers in Econometrics (1972)."},{"key":"e_1_3_2_1_63_1","volume-title":"View in Article","volume":"2","author":"R","year":"2023","unstructured":"R OpenAI. 2023. Gpt-4 technical report. arxiv 2303.08774. View in Article, Vol. 2, 5 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"A functional model of kitsch and art: linking aesthetic appreciation to the dynamics of social motivation. Frontiers in psychology","author":"Ortlieb Stefan A","year":"2019","unstructured":"Stefan A Ortlieb and Claus-Christian Carbon. 2019. A functional model of kitsch and art: linking aesthetic appreciation to the dynamics of social motivation. Frontiers in psychology, Vol. 9 (2019), 2437."},{"key":"e_1_3_2_1_65_1","volume-title":"Visual aesthetics and human preference. Annual review of psychology","author":"Palmer Stephen E","year":"2013","unstructured":"Stephen E Palmer, Karen B Schloss, and Jonathan Sammartino. 2013. Visual aesthetics and human preference. Annual review of psychology, Vol. 64, 1 (2013), 77-107."},{"key":"e_1_3_2_1_66_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_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_68_1","volume-title":"Artificial intelligence and art: Identifying the aesthetic judgment factors that distinguish human-and machine-generated artwork. Psychology of Aesthetics, Creativity, and the Arts","author":"Samo Andrew","year":"2023","unstructured":"Andrew Samo and Scott Highhouse. 2023. Artificial intelligence and art: Identifying the aesthetic judgment factors that distinguish human-and machine-generated artwork. Psychology of Aesthetics, Creativity, and the Arts (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"The philosophy of art","author":"Joseph Schelling Friedrich Wilhelm","unstructured":"Friedrich Wilhelm Joseph Schelling, Douglas W Stott, and David Simpson. 2008. The philosophy of art. University of Minnesota Press."},{"key":"e_1_3_2_1_70_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, Vol. 35 (2022), 25278-25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_71_1","volume-title":"Aesthetics","author":"Sibley Frank","unstructured":"Frank Sibley. 2017. Aesthetic concepts. In Aesthetics. Routledge, 501-505."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1111\/1540_6245.jaac27.1.0003"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2022.2049081"},{"key":"e_1_3_2_1_74_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_75_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. (2023)."},{"key":"e_1_3_2_1_76_1","volume-title":"The proof and measurement of association between two things. The American journal of psychology","author":"Spearman Charles","year":"1987","unstructured":"Charles Spearman. 1987. The proof and measurement of association between two things. The American journal of psychology, Vol. 100, 3\/4 (1987), 441-471."},{"key":"e_1_3_2_1_77_1","volume-title":"Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, and Greg Durrett.","author":"Sprague Zayne","year":"2024","unstructured":"Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, and Greg Durrett. 2024. To cot or not to cot? chain-of-thought helps mainly on math and symbolic reasoning. arXiv preprint arXiv:2409.12183 (2024)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.4300\/JGME-5-4-18"},{"key":"e_1_3_2_1_79_1","volume-title":"Objectivity and Subjectivity in the History of Aesthetics. Philosophy and phenomenological research","author":"Tatarkiewicz Wladyslaw","year":"1963","unstructured":"Wladyslaw Tatarkiewicz. 1963. Objectivity and Subjectivity in the History of Aesthetics. Philosophy and phenomenological research, Vol. 24, 2 (1963), 157-173."},{"key":"e_1_3_2_1_80_1","volume-title":"A history of six ideas: An essay in aesthetics","author":"Tatarkiewicz W\u0142adys\u0142aw","unstructured":"W\u0142adys\u0142aw Tatarkiewicz. 2012. A history of six ideas: An essay in aesthetics. Vol. 5. Springer Science & Business Media."},{"key":"e_1_3_2_1_81_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_82_1","volume-title":"The handbook of visual analysis","author":"Leeuwen Theo Van","unstructured":"Theo Van Leeuwen and Carey Jewitt. 2000. The handbook of visual analysis. Sage."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3283400"},{"key":"e_1_3_2_1_84_1","volume-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733","author":"Wang Haofan","year":"2024","unstructured":"Haofan Wang, Matteo Spinelli, Qixun Wang, Xu Bai, Zekui Qin, and Anthony Chen. 2024. Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_86_1","volume-title":"Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896","author":"Wang Zijie J","year":"2022","unstructured":"Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2022. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)."},{"key":"e_1_3_2_1_87_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_88_1","unstructured":"Wikiart. [n.d.]. WikiArt.org - Visual Art Encyclopedia. https:\/\/www.wikiart.org. Accessed: 2025-08-02."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_34"},{"key":"e_1_3_2_1_90_1","first-page":"81287","article-title":"Multimodal large language models make text-to-image generative models align better","volume":"37","author":"Wu Xun","year":"2024","unstructured":"Xun Wu, Shaohan Huang, Guolong Wang, Jing Xiong, and Furu Wei. 2024. Multimodal large language models make text-to-image generative models align better. Advances in Neural Information Processing Systems, Vol. 37 (2024), 81287-81323.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.61935\/asder.3.1.2024.P60"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCT.1963.1082116"},{"key":"e_1_3_2_1_95_1","volume-title":"ArtGPT-4: Towards artistic-understanding large vision-language models with enhanced adapter. arXiv preprint arXiv:2305.07490","author":"Yuan Zhengqing","year":"2023","unstructured":"Zhengqing Yuan, Yunhong He, Kun Wang, Yanfang Ye, and Lichao Sun. 2023. ArtGPT-4: Towards artistic-understanding large vision-language models with enhanced adapter. arXiv preprint arXiv:2305.07490 (2023)."},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_97_1","volume-title":"William Yang Wang, and Linda Ruth Petzold","author":"Zhang Xinlu","year":"2023","unstructured":"Xinlu Zhang, Yujie Lu, Weizhi Wang, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, and Linda Ruth Petzold. 2023a. Gpt-4v (ision) as a generalist evaluator for vision-language tasks. arXiv preprint arXiv:2311.01361 (2023)."},{"key":"e_1_3_2_1_98_1","volume-title":"Adaptive image quality assessment via teaching large multimodal model to compare. arXiv preprint arXiv:2405.19298","author":"Zhu Hanwei","year":"2024","unstructured":"Hanwei Zhu, Haoning Wu, Yixuan Li, Zicheng Zhang, Baoliang Chen, Lingyu Zhu, Yuming Fang, Guangtao Zhai, Weisi Lin, and Shiqi Wang. 2024. Adaptive image quality assessment via teaching large multimodal model to compare. arXiv preprint arXiv:2405.19298 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:36Z","timestamp":1765340136000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":98,"alternative-id":["10.1145\/3746027.3754961","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754961","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}