{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:40:10Z","timestamp":1745696410806,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658114","type":"print"},{"value":"9789819658121","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-5812-1_17","type":"book-chapter","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:13:54Z","timestamp":1745694834000},"page":"316-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TAD: A Plug-and-Play Task Arithmetic Approach for\u00a0Augmenting Diffusion Models"],"prefix":"10.1007","author":[{"given":"Qingyi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruochen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishen","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Aghajanyan, A., Zettlemoyer, L., Gupta, S.: Intrinsic dimensionality explains the effectiveness of language model fine-tuning. arXiv preprint arXiv:2012.13255 (2020)","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"17_CR3","unstructured":"Cao, Y., et al.: A comprehensive survey of AI-generated content (AIGC): a history of generative AI from GAN to ChatGPT. arXiv preprint arXiv:2303.04226 (2023)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Masked image training for generalizable deep image denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1692\u20131703 (2023)","DOI":"10.1109\/CVPR52729.2023.00169"},{"key":"17_CR5","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. arXiv preprint arXiv:2303.07345 (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Orgad, H., Belinkov, Y., Materzy\u0144ska, J., Bau, D.: Unified concept editing in diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5111\u20135120 (2024)","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"17_CR9","unstructured":"Hu, E.J., et al.: LoRa: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR10","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22691\u201322702 (2023)","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"17_CR13","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14297\u201314306 (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"17_CR18","unstructured":"Ortiz-Jimenez, G., Favero, A., Frossard, P.: Task arithmetic in the tangent space: improved editing of pre-trained models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR19","unstructured":"Ortiz-Jim\u00e9nez, G., Modas, A., Moosavi-Dezfooli, S.M., Frossard, P.: What can linearized neural networks actually say about generalization? In: Advances in Neural Information Processing Systems (NeurIPS) (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/4b5deb9a14d66ab0acc3b8a2360cde7c-Paper.pdf"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"17_CR22","unstructured":"Qin, C., et\u00a0al.: Unicontrol: a unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147 (2023)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Shah, V., et al.: Ziplora: any subject in any style by effectively merging LoRAs. arXiv preprint arXiv:2311.13600 (2023)","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Sheynin, S., et al.: Emu edit: precise image editing via recognition and generation tasks. arXiv preprint arXiv:2311.10089 (2023)","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"17_CR27","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (2015)"},{"issue":"2","key":"17_CR28","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1162\/qjec.2009.124.2.469","volume":"124","author":"E Spolaore","year":"2009","unstructured":"Spolaore, E., Wacziarg, R.: The diffusion of development. Q. J. Econ. 124(2), 469\u2013529 (2009)","journal-title":"Q. J. Econ."},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Wang, S., et\u00a0al.: Imagen editor and editbench: advancing and evaluating text-guided image inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18359\u201318369 (2023)","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"17_CR31","unstructured":"Wu, J., Gan, W., Chen, Z., Wan, S., Lin, H.: Ai-generated content (AIGC): a survey. arXiv preprint arXiv:2304.06632 (2023)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: SmartBrush: text and shape guided object inpainting with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Xu, S.Z., Lai, Y.K.: Simultaneous multi-attribute image-to-image translation using parallel latent transform networks. In: Computer Graphics Forum, vol.\u00a039, pp. 531\u2013542. Wiley Online Library (2020)","DOI":"10.1111\/cgf.14165"},{"key":"17_CR34","unstructured":"Yang, Z., Ding, G., Wang, W., Chen, H., Zhuang, B., Shen, C.: Object-aware inversion and reassembly for image editing. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: ReCo: region-controlled text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14246\u201314255 (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"17_CR36","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Y\u00fcce, G., Ortiz-Jim\u00e9nez, G., Besbinar, B., Frossard, P.: A structured dictionary perspective on implicit neural representations. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01863"},{"key":"17_CR38","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion model in generative AI: a survey. arXiv preprint arXiv:2303.07909 (2023)"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17907\u201317917 (2022)","DOI":"10.1109\/CVPR52688.2022.01738"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5812-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:14:12Z","timestamp":1745694852000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5812-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658114","9789819658121"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5812-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}