{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T06:07:05Z","timestamp":1777183625018,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":94,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62401365, 62225112, 62271312, 62132006, U24A20220"],"award-info":[{"award-number":["62401365, 62225112, 62271312, 62132006, U24A20220"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411, 2025M773473"],"award-info":[{"award-number":["BX20250411, 2025M773473"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"STCSM","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755294","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"6908-6917","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7834-6179","authenticated-orcid":false,"given":"Zitong","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9627-9562","authenticated-orcid":false,"given":"Bingnan","family":"Liu","sequence":"additional","affiliation":[{"name":"UESTC, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8136-1187","authenticated-orcid":false,"given":"Guangji","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9890-2698","authenticated-orcid":false,"given":"Jiarui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1300-7401","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2428-0326","authenticated-orcid":false,"given":"Shiqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3415-6201","authenticated-orcid":false,"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"UESTC, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3206","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/CVPR.2018.00182"},{"key":"e_1_3_2_1_2_1","volume-title":"Customizable Models. Meta AI Blog (20","author":"Meta AI","year":"2024","unstructured":"AI Meta. 2024. Llama 3.2: Revolutionizing Edge AI and Vision with Open, Customizable Models. Meta AI Blog (20 December 2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song et al. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"e_1_3_2_1_5_1","volume-title":"Daniela Massiceti, Maziar Sanjabi, et al.","author":"Basu Samyadeep","year":"2023","unstructured":"Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, et al., 2023. EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods. arXiv preprint arXiv:2310.02426 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00416"},{"key":"e_1_3_2_1_11_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian et al. 2025. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv preprint arXiv:2412.05271 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, et al., 2024b. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24185-24198."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, et al., 2024c. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24185-24198."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the British Machine Vision Conference (BMVC).","author":"Jiaying Liu Chen Wei Wenhan Yang","year":"2018","unstructured":"Wenhan Yang Jiaying Liu Chen Wei, Wenjing Wang. 2018. Deep Retinex Decomposition for Low-Light Enhancement. In Proceedings of the British Machine Vision Conference (BMVC)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2318984.2319918"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML).","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, et al., 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2691802"},{"key":"e_1_3_2_1_19_1","volume-title":"ReNoise: Real Image Inversion Through Iterative Noising. arXiv preprint arXiv:2403.14602","author":"Garibi Daniel","year":"2024","unstructured":"Daniel Garibi, Or Patashnik, Andrey Voynov, Hadar Averbuch-Elor, and Daniel Cohen-Or. 2024. ReNoise: Real Image Inversion Through Iterative Noising. arXiv preprint arXiv:2403.14602 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_6"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the conference on Asia-Pacific Signal and Information Processing Association (APSIPA). 1-6.","author":"Gu K.","unstructured":"K. Gu, G. Zhai, X. Yang, and W. Zhang. 2012. An improved full-reference image quality metric based on structure compensation. In Proceedings of the conference on Asia-Pacific Signal and Information Processing Association (APSIPA). 1-6."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_2_1_24_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A Reference-Free Evaluation Metric for Image Captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_25_1","unstructured":"Yi Huang Jiancheng Huang Yifan Liu Mingfu Yan Jiaxi Lv Jianzhuang Liu et al. 2024. Diffusion Model-Based Image Editing: A Survey. IEEE transactions on pattern analysis and machine intelligence (TPAMI) Vol. PP (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"e_1_3_2_1_27_1","unstructured":"Mude Hui Siwei Yang Bingchen Zhao Yichun Shi Heng Wang Peng Wang et al. 2024. HQ-Edit: A High-Quality Dataset for Instruction-Based Image Editing. arXiv preprint arXiv:2404.09990 (2024)."},{"key":"e_1_3_2_1_28_1","unstructured":"International Telecommunication Union (ITU). 2012. Methodology for the Subjective Assessment of the Quality of Television Pictures. Technical Report Rec. ITU-R BT.500-13. International Telecommunication Union (ITU)."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Ju Xuan","year":"2024","unstructured":"Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, and Qiang Xu. 2024. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_32_1","first-page":"36652","article-title":"Pick-a-Pic","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. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS). 36652-36663.","journal-title":"In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01268"},{"key":"e_1_3_2_1_34_1","volume-title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models. arXiv preprint arXiv:2412.08629","author":"Kulikov Vladimir","year":"2024","unstructured":"Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, and Tomer Michaeli. 2024. FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models. arXiv preprint arXiv:2412.08629 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Kwon Mingi","year":"2023","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2023. Diffusion Models Already Have a Semantic Latent Space. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00123"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"e_1_3_2_1_38_1","unstructured":"Feng Li Renrui Zhang Hao Zhang Yuanhan Zhang Bo Li Wei Li et al. 2024c. LLaVA-Next-Interleave: Tackling Multi-Image Video and 3D in Large Multimodal Models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In Proceedings of the International Conference on Machine Learning (ICML). 12888-12900."},{"key":"e_1_3_2_1_40_1","volume-title":"Instructany2pix: Flexible Visual Editing via Multimodal Instruction Following. arXiv preprint arXiv:2312.06738","author":"Li Shufan","year":"2023","unstructured":"Shufan Li, Harkanwar Singh, and Aditya Grover. 2023a. Instructany2pix: Flexible Visual Editing via Multimodal Instruction Following. arXiv preprint arXiv:2312.06738 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Zone: Zero-Shot Instruction-Guided Local Editing. arXiv preprint arXiv:2312.16794","author":"Li Shanglin","year":"2023","unstructured":"Shanglin Li, Bohan Zeng, Yutang Feng, Sicheng Gao, Xuhui Liu, Jiaming Liu, et al., 2023b. Zone: Zero-Shot Instruction-Guided Local Editing. arXiv preprint arXiv:2312.16794 (2023)."},{"key":"e_1_3_2_1_42_1","unstructured":"Yuheng Li Haotian Liu Mu Cai Yijun Li Eli Shechtman Zhe Lin et al. 2024b. Removing Distributional Discrepancies in Captions Improves Image-Text Alignment. arXiv preprint arXiv:2410.00905 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Improved Baselines with Visual Instruction Tuning. arXiv preprint arXiv:2310.03744","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. Improved Baselines with Visual Instruction Tuning. arXiv preprint arXiv:2310.03744 (2023)."},{"key":"e_1_3_2_1_44_1","first-page":"34892","article-title":"Visual Instruction Tuning","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual Instruction Tuning. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 36. 34892-34916.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_45_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu et al. 2024. DeepSeek-VL: Towards Real-World Vision-Language Understanding. arXiv preprint arXiv:2403.05525 Vol. 6 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurPIS).","author":"Ma Yiwei","year":"2024","unstructured":"Yiwei Ma, Jiayi Ji, Ke Ye, Weihuang Lin, Yonghan Zheng, Qiang Zhou, et al., 2024. I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing. In Proceedings of the Advances in Neural Information Processing Systems (NeurPIS)."},{"key":"e_1_3_2_1_47_1","volume-title":"ACE: Instruction-Based Image Creation and Editing via Context-Aware Content Filling. arXiv preprint arXiv:2501.02487","author":"Mao Chaojie","year":"2025","unstructured":"Chaojie Mao, Jingfeng Zhang, Yulin Pan, Zeyinzi Jiang, Zhen Han, Yu Liu, et al., 2025. ACE: Instruction-Based Image Creation and Editing via Context-Aware Content Filling. arXiv preprint arXiv:2501.02487 (2025)."},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the Asilomar Conference on Signals, Systems and Computers (ACSSC). 723-727","author":"Mittal Anish","unstructured":"Anish Mittal, Anush K. Moorthy, and Alan C. Bovik. 2011. Blind\/Referenceless Image Spatial Quality Evaluator. In Proceedings of the Asilomar Conference on Signals, Systems and Computers (ACSSC). 723-727."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_2_1_50_1","unstructured":"A. K. Moorthy and A. C. Bovik. 2009. A Modular Framework for Constructing Blind Universal Quality Indices. IEEE Signal Processing Letters (SPL) (2009)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2147325"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00878"},{"key":"e_1_3_2_1_54_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman et al. 2024. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Sdxl: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, et al., 2023. Sdxl: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML).","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, A. Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2191563"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859389"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_63_1","volume-title":"IE-Bench: Advancing the Measurement of Text-Driven Image Editing for Human Perception Alignment. arXiv preprint arXiv:2501.09927","author":"Sun Shangkun","year":"2025","unstructured":"Shangkun Sun, Bowen Qu, Xiaoyu Liang, Songlin Fan, and Wei Gao. 2025. IE-Bench: Advancing the Measurement of Text-Driven Image Editing for Human Perception Alignment. arXiv preprint arXiv:2501.09927 (2025)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS).","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, and Bharath Hariharan. 2023. Emergent Correspondence from Image Diffusion. In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_66_1","volume-title":"EDICT: Exact Diffusion Inversion via Coupled Transformations. arXiv preprint arXiv:2211.12446","author":"Wallace Bram","year":"2022","unstructured":"Bram Wallace, Akash Gokul, and Nikhil Naik. 2022. EDICT: Exact Diffusion Inversion via Coupled Transformations. arXiv preprint arXiv:2211.12446 (2022)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_68_1","first-page":"46","article-title":"AIGCIQA2023: A Large-Scale Image Quality Assessment Database for AI Generated Images: From the Perspectives of Quality, Authenticity and Correspondence","author":"Wang Jiarui","year":"2023","unstructured":"Jiarui Wang, Huiyu Duan, Jing Liu, Shi Chen, Xiongkuo Min, and Guangtao Zhai. 2023b. AIGCIQA2023: A Large-Scale Image Quality Assessment Database for AI Generated Images: From the Perspectives of Quality, Authenticity and Correspondence. In Proceedings of the CAAI International Conference on Artificial Intelligence (CICAI). 46-57.","journal-title":"Proceedings of the CAAI International Conference on Artificial Intelligence (CICAI)."},{"key":"e_1_3_2_1_69_1","volume-title":"Quality Assessment for AI Generated Images with Instruction Tuning","author":"Wang Jiarui","year":"2025","unstructured":"Jiarui Wang, Huiyu Duan, Guangtao Zhai, and Xiongkuo Min. 2025a. Quality Assessment for AI Generated Images with Instruction Tuning. IEEE Transactions on Multimedia (TMM) (2025)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00192"},{"key":"e_1_3_2_1_72_1","volume-title":"Taming Rectified Flow for Inversion and Editing. arXiv preprint arXiv:2411.04746","author":"Wang Jiangshan","year":"2024","unstructured":"Jiangshan Wang, Junfu Pu, Zhongang Qi, Jiayi Guo, Yue Ma, Nisha Huang, Yuxin Chen, Xiu Li, and Ying Shan. 2024b. Taming Rectified Flow for Inversion and Editing. arXiv preprint arXiv:2411.04746 (2024)."},{"key":"e_1_3_2_1_73_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai et al. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_76_1","first-page":"1398","volume-title":"Proceedings of the Asilomar Conference on Signals, Systems & Computers (ACSSC)","volume":"2","author":"Wang Z.","unstructured":"Z. Wang, E. P. Simoncelli, and A. C. Bovik. 2003. Multiscale structural similarity for image quality assessment. In Proceedings of the Asilomar Conference on Signals, Systems & Computers (ACSSC), Vol. 2. 1398-1402."},{"key":"e_1_3_2_1_77_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Chunyi Li Liang Liao et al. 2023b. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. arXiv preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_78_1","volume-title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023a. Human Preference Score: Better Aligning Text-to-Image Models with Human Preference. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_79_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai et al. 2024. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_80_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 15903-15935","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, et al., 2023. ImageReward: learning and evaluating human preferences for text-to-image generation. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 15903-15935."},{"key":"e_1_3_2_1_81_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9192-9201","author":"Xu Sihan","year":"2024","unstructured":"Sihan Xu, Yidong Huang, Jiayi Pan, Ziqiao Ma, and Joyce Chai. 2024. Inversion-Free Image Editing with Natural Language. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9192-9201."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"e_1_3_2_1_84_1","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_85_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Ye Jiabo","year":"2024","unstructured":"Jiabo Ye, Haiyang Xu, Haowei Liu, Anwen Hu, Ming Yan, Qi Qian, et al., 2024. mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multimodal Large Language Models. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"e_1_3_2_1_87_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurPIS).","author":"Zhang Kai","year":"2023","unstructured":"Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. 2023c. Magicbrush: A manually annotated dataset for instruction-guided image editing. In Proceedings of the Advances in Neural Information Processing Systems (NeurPIS)."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"e_1_3_2_1_89_1","unstructured":"Pan Zhang Xiaoyi Dong Bin Wang Yuhang Cao Chao Xu Linke Ouyang et al. 2023b. InternLM-XComposer: A Vision-Language Large Model for Advanced Text-Image Comprehension and Composition. arXiv preprint arXiv:2309.15112 (2023)."},{"key":"e_1_3_2_1_90_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Pengcheng He, Yu Cheng, Weizhu Chen, et al., 2023a. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_91_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Zhang R.","unstructured":"R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00316"},{"key":"e_1_3_2_1_94_1","volume-title":"Omnitextsuperscript2: Unifying Omnidirectional Image Generation and Editing in an Omni Model. arXiv preprint","author":"Yang Liu","unstructured":"Liu Yang, Huiyu Duan, Yucheng Zhu, Xiaohong Liu, Lu Liu, Zitong Xu, Guangji Ma, Xiongkuo Min, Guangtao Zhai, and Patrick Le Callet. 2025. Omnitextsuperscript2: Unifying Omnidirectional Image Generation and Editing in an Omni Model. arXiv preprint, Vol. arXiv:2504.11379."}],"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\/3746027.3755294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:41Z","timestamp":1765339721000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":94,"alternative-id":["10.1145\/3746027.3755294","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755294","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"}}]}}