{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:43Z","timestamp":1781538883586,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810585","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1861-1869","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["InterFold: Learning Interpretable Diffusion Manifolds Beyond Binary Samples"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0455-8441","authenticated-orcid":false,"given":"Alexander Vincent","family":"Lewi","sequence":"first","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7081-6316","authenticated-orcid":false,"given":"Rainer","family":"Tan","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447648"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Rameen Abdal Yipeng Qin and Peter Wonka. 2020. Image2StyleGAN++: How to Edit the Embedded Images?IEEE Transactions on Pattern Analysis and Machine Intelligence (2020).","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"e_1_3_3_1_5_2","unstructured":"Manuel Brack Felix Friedrich Dominik Hintersdorf Lukas Struppek Patrick Schramowski and Kristian Kersting. 2023. SEGA: Instructing Diffusion using Semantic Dimensions. arxiv:https:\/\/arXiv.org\/abs\/2311.16375\u00a0[cs.CV]"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei\u00a0A. Efros. 2023. InstructPix2Pix: Learning to Follow Image Editing Instructions. arxiv:https:\/\/arXiv.org\/abs\/2211.09800\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.09800","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02285"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Jiankang Deng Jia Guo Jing Yang Niannan Xue Irene Kotsia and Stefanos Zafeiriou. 2022. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 10 (Oct. 2022) 5962\u20135979. 10.1109\/tpami.2021.3087709","DOI":"10.1109\/tpami.2021.3087709"},{"key":"e_1_3_3_1_9_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st 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, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 503, 28\u00a0pages."},{"key":"e_1_3_3_1_10_2","unstructured":"Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit\u00a0H. Bermano Gal Chechik and Daniel Cohen\u2011Or. 2022. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. arxiv:https:\/\/arXiv.org\/abs\/2208.01618\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2208.01618"},{"key":"e_1_3_3_1_11_2","unstructured":"Rohit Gandikota Joanna Materzynska Tingrui Zhou Antonio Torralba and David Bau. 2023. Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2311.12092\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.12092"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581912"},{"key":"e_1_3_3_1_13_2","first-page":"9841","volume-title":"Advances in Neural Information Processing Systems","author":"H\u00e4rk\u00f6nen Erik","year":"2020","unstructured":"Erik H\u00e4rk\u00f6nen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls via Principal Component Analysis. In Advances in Neural Information Processing Systems , Vol.\u00a033. 9841\u20139850."},{"key":"e_1_3_3_1_14_2","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:https:\/\/arXiv.org\/abs\/2208.01626\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2208.01626"},{"key":"e_1_3_3_1_15_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_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_3_1_16_2","unstructured":"Edward\u00a0J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.LG]"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00507"},{"key":"e_1_3_3_1_18_2","unstructured":"Tero Karras Timo Aila Samuli Laine and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality Stability and Variation. arxiv:https:\/\/arXiv.org\/abs\/1710.10196\u00a0[cs.NE] https:\/\/arxiv.org\/abs\/1710.10196"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Bahjat Kawar Shiran Zada Oran Lang Omer Tov Huiwen Chang Tali Dekel Inbar Mosseri and Michal Irani. 2023. Imagic: Text-Based Real Image Editing with Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2210.09276\u00a0[cs.CV]","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_1_21_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kwon Mingi","year":"2023","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2023. Diffusion Models Already Have A Semantic Latent Space. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pd1P2eUBVfq"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01141"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00213"},{"key":"e_1_3_3_1_24_2","unstructured":"Xian Li and Percy Liang. 2021. Prefix-Tuning: Optimizing Continuous Prompts for Generation. arxiv:https:\/\/arXiv.org\/abs\/2101.00190\u00a0[cs.LG]"},{"key":"e_1_3_3_1_25_2","unstructured":"Zixiang Li Yue Song Renshuai Tao Xiaohong Jia Yao Zhao and Wei Wang. 2024. Unsupervised Region-Based Image Editing of Denoising Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2412.12912\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.12912"},{"key":"e_1_3_3_1_26_2","volume-title":"Advances in Neural Information Processing Systems","author":"Ling Huan","year":"2021","unstructured":"Huan Ling, Karsten Kreis, Daiqing Li, Seung\u00a0Wook Kim, Antonio Torralba, and Sanja Fidler. 2021. EditGAN: High-Precision Semantic Image Editing. In Advances in Neural Information Processing Systems , Vol.\u00a034."},{"key":"e_1_3_3_1_27_2","unstructured":"Ziwei Liu Ping Luo Xiaogang Wang and Xiaoou Tang. 2015. Deep Learning Face Attributes in the Wild. arxiv:https:\/\/arXiv.org\/abs\/1411.7766\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1411.7766"},{"key":"e_1_3_3_1_28_2","unstructured":"Ron Mokady Amir Hertz Jay Tenenbaum Kfir Aberman and Daniel Cohen-Or. 2022. Null-text Inversion for Editing Real Images using Guided Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2211.09794\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.09794"},{"key":"e_1_3_3_1_29_2","unstructured":"Yong-Hyun Park Mingi Kwon Junghyo Jo and Youngjung Uh. 2023. Unsupervised Discovery of Semantic Latent Directions in Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2302.12232\u00a0[cs.CV]"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_1_31_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya 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. arxiv:https:\/\/arXiv.org\/abs\/2103.00020\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_34_2","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2023. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. arxiv:https:\/\/arXiv.org\/abs\/2208.12242\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2208.12242"},{"key":"e_1_3_3_1_35_2","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Wei Wei Tingbo Hou Yael Pritch Neal Wadhwa Michael Rubinstein and Kfir Aberman. 2023. HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models. arxiv:https:\/\/arXiv.org\/abs\/2307.06949\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2307.06949"},{"key":"e_1_3_3_1_36_2","unstructured":"Ludovica Schaerf Andrea Alfarano Fabrizio Silvestri and Leonardo Impett. 2025. Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2501.14524\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2501.14524"},{"key":"e_1_3_3_1_37_2","volume-title":"seeprettyface","year":"2025","unstructured":"seeprettyface. 2025. seeprettyface. http:\/\/www.seeprettyface.com\/"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"e_1_3_3_1_39_2","volume-title":"Asian Conference on Computer Vision (ACCV)","author":"Tan Jiangtong","year":"2024","unstructured":"Jiangtong Tan, Hu Yu, Jie Huang, Zizheng Yang, and Feng Zhao. 2024. DiffLoss: Unleashing Diffusion Model as Constraint for Training Image Restoration Network. In Asian Conference on Computer Vision (ACCV). https:\/\/github.com\/JosephTiTan\/DiffLoss"},{"key":"e_1_3_3_1_40_2","unstructured":"Zihao Wang Lin Gui Jeffrey Negrea and Victor Veitch. 2023. Concept Algebra for (Score-Based) Text-Controlled Generative Models. arxiv:https:\/\/arXiv.org\/abs\/2302.03693\u00a0[cs.CV]"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01200"},{"key":"e_1_3_3_1_43_2","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. IP-Adapter: Text-to-Image Diffusion Models are Zero-Shot Segmenters. arxiv:https:\/\/arXiv.org\/abs\/2308.06721\u00a0[cs.CV]"},{"key":"e_1_3_3_1_44_2","unstructured":"Lun Zhang Tianxiang Zhang Chen Gao Xiaodong Cun Xuan Wang Chun Yuan Errui Ding and Chang Zhou. 2023. Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2310.09912\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2310.09912"},{"key":"e_1_3_3_1_45_2","unstructured":"Richard Zhang Phillip Isola Alexei\u00a0A. Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. arxiv:https:\/\/arXiv.org\/abs\/1801.03924\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1801.03924"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:06:45Z","timestamp":1781536005000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":44,"alternative-id":["10.1145\/3805622.3810585","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810585","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}