{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:50Z","timestamp":1776931190872,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572458"],"award-info":[{"award-number":["62572458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Science and Technology Plan Project","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763820","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-5455","authenticated-orcid":false,"given":"Yu","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2018-5135","authenticated-orcid":false,"given":"You","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-8148","authenticated-orcid":false,"given":"Lin","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5803-2185","authenticated-orcid":false,"given":"Oliver","family":"Deussen","sequence":"additional","affiliation":[{"name":"University of Konstanz, Konstanz, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1681-3263","authenticated-orcid":false,"given":"Hongbin","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3622-2735","authenticated-orcid":false,"given":"Jintao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6699-2944","authenticated-orcid":false,"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng-Kung University, Tainan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"e_1_3_3_2_4_1","unstructured":"blackforestlabs.ai. 2024. FLUX offering state-of-the-art performance image generation. https:\/\/blackforestlabs.ai\/. Accessed: 2024-10-07."},{"key":"e_1_3_3_2_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_6_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen Junsong","year":"2024","unstructured":"Junsong Chen, Jincheng YU, Chongjian GE, Lewei Yao, Enze Xie, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024c. PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eAKmQPe3m1"},{"key":"e_1_3_3_2_7_1","unstructured":"Tianqi Chen Yongfei Liu Zhendong Wang Jianbo Yuan Quanzeng You Hongxia Yang and Mingyuan Zhou. 2023. Improving in-context learning in diffusion models with visual context-modulated prompts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.01408 (2023)."},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Xi Chen Yutong Feng Mengting Chen Yiyang Wang Shilong Zhang Yu Liu Yujun Shen and Hengshuang Zhao. 2024a. Zero-shot image editing with reference imitation. Advances in Neural Information Processing Systems 37 (2024) 84010\u201384032.","DOI":"10.52202\/079017-2669"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01166"},{"key":"e_1_3_3_2_11_1","unstructured":"Jooyoung Choi Yunjey Choi Yunji Kim Junho Kim and Sungroh Yoon. 2023. Custom-edit: Text-guided image editing with customized diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.15779 (2023)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687612"},{"key":"e_1_3_3_2_13_1","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_14_1","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Jingyuan Ma Rui Li Heming Xia Jingjing Xu Zhiyong Wu Tianyu Liu et\u00a0al. 2022. A survey on in-context learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.00234 (2022)."},{"key":"e_1_3_3_2_15_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\u00a0al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_2_16_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit\u00a0Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2023. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_17_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gandelsman Yossi","year":"2024","unstructured":"Yossi Gandelsman, Alexei\u00a0A Efros, and Jacob Steinhardt. 2024. Interpreting CLIP\u2019s Image Representation via Text-Based Decomposition. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_18_1","unstructured":"Jing Gu Yilin Wang Nanxuan Zhao Tsu-Jui Fu Wei Xiong Qing Liu Zhifei Zhang He Zhang Jianming Zhang HyunJoon Jung et\u00a0al. 2024a. Photoswap: Personalized subject swapping in images. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_19_1","first-page":"402","volume-title":"European Conference on Computer Vision","author":"Gu Jing","year":"2024","unstructured":"Jing Gu, Nanxuan Zhao, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Yilin Wang, and Xin\u00a0Eric Wang. 2024b. SwapAnything: Enabling Arbitrary Object Swapping in Personalized Image Editing. In European Conference on Computer Vision. 402\u2013418."},{"key":"e_1_3_3_2_20_1","unstructured":"Runze He Kai Ma Linjiang Huang Shaofei Huang Jialin Gao Xiaoming Wei Jiao Dai Jizhong Han and Si Liu. 2024. Freeedit: Mask-free reference-based image editing with multi-modal instruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.18071 (2024)."},{"key":"e_1_3_3_2_21_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-or. 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_3_2_23_1","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 30 (2017)."},{"key":"e_1_3_3_2_24_1","unstructured":"Lianghua Huang Wei Wang Zhi-Fan Wu Yupeng Shi Huanzhang Dou Chen Liang Yutong Feng Yu Liu and Jingren Zhou. 2024. In-context lora for diffusion transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.23775 (2024)."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_27_1","first-page":"233","volume-title":"European Conference on Computer Vision","author":"Li Pengzhi","year":"2024","unstructured":"Pengzhi Li, Qiang Nie, Ying Chen, Xi Jiang, Kai Wu, Yuhuan Lin, Yong Liu, Jinlong Peng, Chengjie Wang, and Feng Zheng. 2024. Tuning-free image customization with image and text guidance. In European Conference on Computer Vision. Springer, 233\u2013250."},{"key":"e_1_3_3_2_28_1","unstructured":"Tianle Li Max Ku Cong Wei and Wenhu Chen. 2023. DreamEdit: Subject-driven Image Editing. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_22"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_35_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell Dustin","year":"2024","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2024. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_36_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. (2019)."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_2_39_1","unstructured":"Chaehun Shin Jooyoung Choi Heeseung Kim and Sungroh Yoon. 2024. Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15466 (2024)."},{"key":"e_1_3_3_2_40_1","unstructured":"Wensong Song Hong Jiang Zongxing Yang Ruijie Quan and Yi Yang. 2025. Insert Anything: Image Insertion via In-Context Editing in DiT. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.15009 (2025)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"crossref","unstructured":"Yoad Tewel Omri Kaduri Rinon Gal Yoni Kasten Lior Wolf Gal Chechik and Yuval Atzmon. 2024. Training-free consistent text-to-image generation. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201318.","DOI":"10.1145\/3658157"},{"key":"e_1_3_3_2_44_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"e_1_3_3_2_47_1","unstructured":"Zhendong Wang Yifan Jiang Yadong Lu Pengcheng He Weizhu Chen Zhangyang Wang Mingyuan Zhou et\u00a0al. 2023a. In-context learning unlocked for diffusion models. Advances in Neural Information Processing Systems 36 (2023) 8542\u20138562."},{"key":"e_1_3_3_2_48_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et\u00a0al. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"e_1_3_3_2_50_1","unstructured":"Daniel Winter Asaf Shul Matan Cohen Dana Berman Yael Pritch Alex Rav-Acha and Yedid Hoshen. 2024b. ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.08645 (2024)."},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"crossref","unstructured":"Yu Xu Fan Tang Juan Cao Yuxin Zhang Oliver Deussen Weiming Dong Jintao Li and Tong-Yee Lee. 2025. B4M: Breaking Low-Rank Adapter for Making Content-Style Customization. ACM Transactions on Graphics 44 2 (2025) 1\u201317.","DOI":"10.1145\/3728461"},{"key":"e_1_3_3_2_53_1","unstructured":"Yu Xu Fan Tang Juan Cao Yuxin Zhang Xiaoyu Kong Jintao Li Oliver Deussen and Tong-Yee Lee. 2024. HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15034 (2024)."},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_3_2_55_1","unstructured":"Yongsheng Yu Ziyun Zeng Haitian Zheng and Jiebo Luo. 2025. OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.08677 (2025)."},{"key":"e_1_3_3_2_56_1","unstructured":"Yuchen Zeng Wonjun Kang Yicong Chen Hyung\u00a0Il Koo and Kangwook Lee. 2024. Can MLLMs Perform Text-to-Image In-Context Learning? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01293 (2024)."},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730670"},{"key":"e_1_3_3_2_58_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhu Chenyang","year":"2024","unstructured":"Chenyang Zhu, Kai Li, Yue Ma, Longxiang Tang, Chengyu Fang, Chubin Chen, Qifeng Chen, and Xiu Li. 2024. InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences. In The Thirteenth International Conference on Learning Representations."}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:28:07Z","timestamp":1765250887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763820"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":57,"alternative-id":["10.1145\/3757377.3763820","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763820","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}