{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:15:39Z","timestamp":1772828139679,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758301","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"13391-13397","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0479-9343","authenticated-orcid":false,"given":"Chenglin","family":"Wang","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9883-5621","authenticated-orcid":false,"given":"Yucheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8715-9718","authenticated-orcid":false,"given":"Qianning","family":"Wang","sequence":"additional","affiliation":[{"name":"Auckland University of Technology, Auckland, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2973-7682","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6297-4423","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al., 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)."},{"key":"e_1_3_2_1_2_1","unstructured":"Jacob Austin Daniel D. Johnson Jonathan Ho Daniel Tarlow and Rianne van den Berg. 2021. Structured Denoising Diffusion Models in Discrete State-Spaces. In NeurIPS."},{"key":"e_1_3_2_1_3_1","volume-title":"HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing. arXiv preprint arXiv:2412.04280","author":"Bai Jinbin","year":"2024","unstructured":"Jinbin Bai, Wei Chow, Ling Yang, Xiangtai Li, Juncheng Li, Hanwang Zhang, and Shuicheng Yan. 2024. HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing. arXiv preprint arXiv:2412.04280 (2024)."},{"key":"e_1_3_2_1_4_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_6_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 Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia. 3342-3351","author":"Chakrabarty Goirik","unstructured":"Goirik Chakrabarty, Aditya Chandrasekar, Ramya Hebbalaguppe, and Prathosh AP. 2024. Lomoe: Localized multi-object editing via multi-diffusion. In Proceedings of the 32nd ACM International Conference on Multimedia. 3342-3351."},{"key":"e_1_3_2_1_8_1","volume-title":"Forty-first international conference on machine learning.","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al., 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_2_1_9_1","volume-title":"Got: Unleashing reasoning capability of multimodal large language model for visual generation and editing. arXiv preprint arXiv:2503.10639","author":"Fang Rongyao","year":"2025","unstructured":"Rongyao Fang, Chengqi Duan, Kun Wang, Linjiang Huang, Hao Li, Shilin Yan, Hao Tian, Xingyu Zeng, Rui Zhao, Jifeng Dai, et al., 2025. Got: Unleashing reasoning capability of multimodal large language model for visual generation and editing. arXiv preprint arXiv:2503.10639 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Yinfei Yang, and Zhe Gan.","author":"Fu Tsu-Jui","year":"2024","unstructured":"Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, and Zhe Gan. 2024. Guiding Instruction-based Image Editing via Multimodal Large Language Models. In ICLR, ."},{"key":"e_1_3_2_1_11_1","volume-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing. arXiv preprint arXiv:2405.04007","author":"Ge Yuying","year":"2024","unstructured":"Yuying Ge, Sijie Zhao, Chen Li, Yixiao Ge, and Ying Shan. 2024a. Seed-data-edit technical report: A hybrid dataset for instructional image editing. arXiv preprint arXiv:2405.04007 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Making LLaMA SEE and Draw with SEED Tokenizer. In ICLR","author":"Ge Yuying","year":"2024","unstructured":"Yuying Ge, Sijie Zhao, Ziyun Zeng, Yixiao Ge, Chen Li, Xintao Wang, and Ying Shan. 2024b. Making LLaMA SEE and Draw with SEED Tokenizer. In ICLR 2024."},{"key":"e_1_3_2_1_13_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. 2025. 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_14_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS 2020."},{"key":"e_1_3_2_1_16_1","first-page":"22569","article-title":"ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping","volume":"37","author":"Huang Mingzhen","year":"2024","unstructured":"Mingzhen Huang, Jialing Cai, Shan Jia, Vishnu Lokhande, and Siwei Lyu. 2024a. ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping. Advances in Neural Information Processing Systems, Vol. 37 (2024), 22569-22595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"e_1_3_2_1_18_1","first-page":"740","article-title":"Microsoft coco: Common objects in context","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 ECCV. 740-755.","journal-title":"ECCV."},{"key":"e_1_3_2_1_19_1","unstructured":"Shiyu Liu Yucheng Han Peng Xing Fukun Yin Rui Wang Wei Cheng Jiaqi Liao Yingming Wang Honghao Fu Chunrui Han et al. 2025. Step1X-Edit: A Practical Framework for General Image Editing. arXiv preprint arXiv:2504.17761 (2025)."},{"key":"e_1_3_2_1_20_1","unstructured":"Yiwei Ma Jiayi Ji Ke Ye Weihuang Lin Zhibin Wang Yonghan Zheng Qiang Zhou Xiaoshuai Sun and Rongrong Ji. 2024. I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing. In NeurIPS."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_23_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, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"e_1_3_2_1_27_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_28_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_29_1","volume-title":"Diffusion model with representation alignment for protein inverse folding. arXiv preprint arXiv:2412.09380","author":"Wang Chenglin","year":"2024","unstructured":"Chenglin Wang, Yucheng Zhou, Zijie Zhai, Jianbing Shen, and Kai Zhang. 2024. Diffusion model with representation alignment for protein inverse folding. arXiv preprint arXiv:2412.09380 (2024)."},{"key":"e_1_3_2_1_30_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_31_1","volume-title":"Omnigen: Unified image generation. arXiv preprint arXiv:2409.11340","author":"Xiao Shitao","year":"2024","unstructured":"Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, and Zheng Liu. 2024. Omnigen: Unified image generation. arXiv preprint arXiv:2409.11340 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark. arXiv preprint arXiv:2504.13143","author":"Yang Siwei","year":"2025","unstructured":"Siwei Yang, Mude Hui, Bingchen Zhao, Yuyin Zhou, Nataniel Ruiz, and Cihang Xie. 2025. Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark. arXiv preprint arXiv:2504.13143 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Object-aware inversion and reassembly for image editing. arXiv preprint arXiv:2310.12149","author":"Yang Zhen","year":"2023","unstructured":"Zhen Yang, Ganggui Ding, Wen Wang, Hao Chen, Bohan Zhuang, and Chunhua Shen. 2023. Object-aware inversion and reassembly for image editing. arXiv preprint arXiv:2310.12149 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738","author":"Yu Qifan","year":"2024","unstructured":"Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. 2024. AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_36_1","first-page":"31428","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","volume":"36","author":"Zhang Kai","year":"2023","unstructured":"Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. 2023. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems, Vol. 36 (2023), 31428-31449.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer. arXiv preprint arXiv:2504.20690","author":"Zhang Zechuan","year":"2025","unstructured":"Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, and Yi Yang. 2025. In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer. arXiv preprint arXiv:2504.20690 (2025)."},{"key":"e_1_3_2_1_38_1","first-page":"3058","article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","volume":"37","author":"Zhao Haozhe","year":"2024","unstructured":"Haozhe Zhao, Xiaojian Shawn Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, and Baobao Chang. 2024. Ultraedit: Instruction-based fine-grained image editing at scale. Advances in Neural Information Processing Systems, Vol. 37 (2024), 3058-3093.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Yucheng Zhou Xiang Li Qianning Wang and Jianbing Shen. 2024. Visual in-context learning for large vision-language models. arXiv preprint arXiv:2402.11574","DOI":"10.18653\/v1\/2024.findings-acl.940"}],"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\/3746027.3758301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:03Z","timestamp":1765309503000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.1145\/3746027.3758301","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758301","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"}}]}}