{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:37:57Z","timestamp":1783183077458,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771013","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["EliGen: Entity-Level Controlled Image Generation with Regional Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4004-617X","authenticated-orcid":false,"given":"Hong","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University, hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-8240","authenticated-orcid":false,"given":"Zhongjie","family":"Duan","sequence":"additional","affiliation":[{"name":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8150-4168","authenticated-orcid":false,"given":"Xingjun","family":"Wang","sequence":"additional","affiliation":[{"name":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7358-819X","authenticated-orcid":false,"given":"Yingda","family":"Chen","sequence":"additional","affiliation":[{"name":"ModelScope Team, Alibaba Group Inc., hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0043-4904","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. Multidiffusion: Fusing diffusion paths for controlled image generation. (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"e_1_3_3_2_4_2","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.03206 (2024)."},{"key":"e_1_3_3_2_5_2","first-page":"6840","volume-title":"Advances in Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems , H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.), Vol.\u00a033. Curran Associates, Inc., 6840\u20136851. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_3_2_6_2","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.12598 (2022)."},{"key":"e_1_3_3_2_7_2","unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et\u00a0al. 2024. CogVLM2: Visual Language Models for Image and Video Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.16500 (2024)."},{"key":"e_1_3_3_2_8_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685 (2021)."},{"key":"e_1_3_3_2_9_2","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_10_2","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_11_2","unstructured":"Tero Karras Miika Aittala Timo Aila and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems 35 (2022) 26565\u201326577."},{"key":"e_1_3_3_2_12_2","unstructured":"Rahima Khanam and Muhammad Hussain. 2024. YOLOv11: An Overview of the Key Architectural Enhancements. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.17725 (2024)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"e_1_3_3_2_14_2","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."},{"key":"e_1_3_3_2_15_2","unstructured":"Black\u00a0Forest Labs. 2024. FLUX. https:\/\/blackforestlabs.ai\/announcing-black-forest-labs."},{"key":"e_1_3_3_2_16_2","unstructured":"LAION. 2022. LAION-Aesthetics V2. https:\/\/github.com\/christophschuhmann\/improved-aesthetic-predictor."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_3_2_18_2","unstructured":"Zhimin Li Jianwei Zhang Qin Lin Jiangfeng Xiong Yanxin Long Xinchi Deng Yingfang Zhang Xingchao Liu Minbin Huang Zedong Xiao et\u00a0al. 2024. Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding. arXiv e-prints (2024)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_2_20_2","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Qing Jiang Chunyuan Li Jianwei Yang Hang Su et\u00a0al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.05499 (2023)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28204"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_23_2","unstructured":"Chong Mou Xintao Wang Liangbin Xie Yanze Wu Jian Zhang Zhongang Qi Ying Shan and Xiaohu Qie. 2023. T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.08453 (2023)."},{"key":"e_1_3_3_2_24_2","unstructured":"William Peebles and Saining Xie. 2022. Scalable Diffusion Models with Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.09748 (2022)."},{"key":"e_1_3_3_2_25_2","volume-title":"ICLR","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 ICLR."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01233"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_2_31_2","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. ArXiv abs\/2010.02502 (2021)."},{"key":"e_1_3_3_2_32_2","unstructured":"InstantX Team. 2024. InstantX FLUX.1-dev IP-Adapter Page."},{"key":"e_1_3_3_2_33_2","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et\u00a0al. 2024. Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12191 (2024)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"e_1_3_3_2_35_2","unstructured":"Zijie\u00a0J. Wang Evan Montoya David Munechika Haoyang Yang Benjamin Hoover and Duen\u00a0Horng Chau. 2022. DiffusionDB: A Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models. arXiv:https:\/\/arXiv.org\/abs\/2210.14896 [cs] (2022). https:\/\/arxiv.org\/abs\/2210.14896"},{"key":"e_1_3_3_2_36_2","unstructured":"Yinwei Wu Xianpan Zhou Bing Ma Xuefeng Su Kai Ma and Xinchao Wang. 2024. Ifadapter: Instance feature control for grounded text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.08240 (2024)."},{"key":"e_1_3_3_2_37_2","unstructured":"Jiayu Xiao Henglei Lv Liang Li Shuhui Wang and Qingming Huang. 2023. R&b: Region and boundary aware zero-shot grounded text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.08872 (2023)."},{"key":"e_1_3_3_2_38_2","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06721 (2023)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00766"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:07:45Z","timestamp":1765008465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771013"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":41,"alternative-id":["10.1145\/3743093.3771013","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771013","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}