{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T13:33:39Z","timestamp":1770384819564,"version":"3.49.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"name":"the Pioneer R&D Program of Zhejiang","award":["2024C01035"],"award-info":[{"award-number":["2024C01035"]}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["226-2024-00049"],"award-info":[{"award-number":["226-2024-00049"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["226-2024-00145"],"award-info":[{"award-number":["226-2024-00145"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10994-025-06743-y","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T15:59:52Z","timestamp":1738857592000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CaCOM: customizing text-to-image diffusion models in the wild via continual active selection"],"prefix":"10.1007","volume":"114","author":[{"given":"Jianan","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"6743_CR1","doi-asserted-by":"crossref","unstructured":"Alemohammad, S., Casco-Rodriguez, J., Luzi, L., Humayun, A.I., Babaei, H., LeJeune, D., Siahkoohi, A., & Baraniuk, R.G. (2023). Self-consuming generative models go mad. arXiv preprint arXiv:2307.01850","DOI":"10.52591\/lxai202312101"},{"key":"6743_CR2","unstructured":"Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., & Agarwal, A. (2019). Deep batch active learning by diverse, uncertain gradient lower bounds. CoRR arXiv:abs\/1906.03671"},{"issue":"3","key":"6743_CR3","first-page":"8","volume":"2","author":"J Betker","year":"2023","unstructured":"Betker, J., Goh, G., Jing, L., Brooks, T., Wang, J., Li, L., Ouyang, L., Zhuang, J., Lee, J., Guo, Y., et al. (2023). Improving image generation with better captions. Computer Science, 2(3), 8.","journal-title":"Computer Science"},{"key":"6743_CR4","unstructured":"Borji, A. (2022). Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2. arXiv preprint arXiv:2210.00586"},{"key":"6743_CR5","unstructured":"Budzinski, M., et al. (2023). Machine learning approaches for computing information value and information density"},{"key":"6743_CR6","doi-asserted-by":"crossref","unstructured":"Cai, W., & Wei, Z. (2019) Diversity-generated image inpainting with style extraction. arXiv preprint arXiv:1912.01834","DOI":"10.20944\/preprints201912.0028.v1"},{"key":"6743_CR7","unstructured":"Chen, J., Wang, Y., Wang, P., Chen, X., Zhang, Z., Lei, Z., & Li, Q. (2023). Diffusepast: Diffusion-based generative replay for class incremental semantic segmentation. arXiv preprint arXiv:2308.01127"},{"key":"6743_CR8","unstructured":"Ding, Y., Liu, L., Tian, C., Yang, J., & Ding, H. (2022). Don\u2019t stop learning: Towards continual learning for the clip model. arXiv preprint arXiv:2207.09248"},{"key":"6743_CR9","doi-asserted-by":"crossref","unstructured":"Douillard, A., Cord, M., Ollion, C., Robert, T., & Valle, E. (2020). Podnet: Pooled outputs distillation for small-tasks incremental learning. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX 16 (pp. 86\u2013102). Springer","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"6743_CR10","doi-asserted-by":"crossref","unstructured":"Dranoshchuk, A., & Veselov, A. (2019). About perceptual quality estimation for image compression. In 2019 wave electronics and its application in information and telecommunication systems (WECONF) (pp. 1\u20134). IEEE","DOI":"10.1109\/WECONF.2019.8840116"},{"key":"6743_CR11","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., & Cohen-or, D. (2022). An image is worth one word: Personalizing text-to-image generation using textual inversion. In The eleventh international conference on learning representations."},{"issue":"1","key":"6743_CR12","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K. M., Rasch, M. J., Sch\u00f6lkopf, B., & Smola, A. (2012). A kernel two-sample test. The Journal of Machine Learning Research, 13(1), 723\u2013773.","journal-title":"The Journal of Machine Learning Research"},{"key":"6743_CR13","doi-asserted-by":"crossref","unstructured":"Hong, S., Lee, G., Jang, W., & Kim, S. (2023). Improving sample quality of diffusion models using self-attention guidance. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7462\u20137471).","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"6743_CR14","unstructured":"Hu, E.J., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al. (2021). Lora: Low-rank adaptation of large language models. In International conference on learning representations."},{"key":"6743_CR15","unstructured":"Iyer, R., Khargoankar, N., Bilmes, J., & Asanani, H. (2021). Submodular combinatorial information measures with applications in machine learning. In Algorithmic learning theory (pp. 722\u2013754). PMLR"},{"key":"6743_CR16","first-page":"31796","volume":"35","author":"A Karanam","year":"2022","unstructured":"Karanam, A., Killamsetty, K., Kokel, H., & Iyer, R. (2022). Orient: Submodular mutual information measures for data subset selection under distribution shift. Advances in Neural Information Processing Systems, 35, 31796\u201331808.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6743_CR17","doi-asserted-by":"crossref","unstructured":"Kaushal, V., Kothawade, S., Ramakrishnan, G., Bilmes, J., & Iyer, R. (2021). Prism: A unified framework of parameterized submodular information measures for targeted data subset selection and summarization. arXiv preprint arXiv:2103.00128","DOI":"10.1609\/aaai.v36i9.21264"},{"key":"6743_CR18","unstructured":"Kettunen, M., H\u00e4rk\u00f6nen, E., & Lehtinen, J. (2019). E-lpips: robust perceptual image similarity via random transformation ensembles. arXiv preprint arXiv:1906.03973"},{"key":"6743_CR19","doi-asserted-by":"crossref","unstructured":"Kim, Y., & Shin, B. (2022). In defense of core-set: A density-aware core-set selection for active learning. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (pp. 804\u2013812).","DOI":"10.1145\/3534678.3539476"},{"key":"6743_CR20","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.-H., Ha, J.-W., & Zhu, J.-Y. (2023). Dense text-to-image generation with attention modulation. arXiv preprint arXiv:2308.12964","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"6743_CR21","doi-asserted-by":"crossref","unstructured":"Kim, K., Park, D., Kim, K.I., & Chun, S.Y. (2021). Task-aware variational adversarial active learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8166\u20138175).","DOI":"10.1109\/CVPR46437.2021.00807"},{"issue":"13","key":"6743_CR22","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017). Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13), 3521\u20133526.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"6743_CR23","first-page":"18685","volume":"34","author":"S Kothawade","year":"2021","unstructured":"Kothawade, S., Beck, N., Killamsetty, K., & Iyer, R. (2021). Similar: Submodular information measures based active learning in realistic scenarios. Advances in Neural Information Processing Systems, 34, 18685\u201318697.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6743_CR24","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J.-Y. (2023). Multi-concept customization of text-to-image diffusion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1931\u20131941).","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"6743_CR25","doi-asserted-by":"crossref","unstructured":"Li, D., Chen, Z., Cho, E., Hao, J., Liu, X., Xing, F., Guo, C., & Liu, Y. (2022). Overcoming catastrophic forgetting during domain adaptation of seq2seq language generation. In Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 5441\u20135454).","DOI":"10.18653\/v1\/2022.naacl-main.398"},{"key":"6743_CR26","unstructured":"Li, X., Zhou, Y., Wu, T., Socher, R., & Xiong, C. (2019). Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting. In International conference on machine learning (pp. 3925\u20133934). PMLR"},{"key":"6743_CR27","doi-asserted-by":"crossref","unstructured":"Liu, H., Wan, Z., Huang, W., Song, Y., Han, X., & Liao, J. (2021). Pd-gan: Probabilistic diverse gan for image inpainting. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9371\u20139381).","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"6743_CR28","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, J., Chen, C., & Lu, H. (2023). Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning. arXiv preprint arXiv:2307.11410","DOI":"10.1145\/3641519.3657469"},{"key":"6743_CR29","doi-asserted-by":"crossref","unstructured":"Mai, X., Avestimehr, S., Ortega, A., & Soltanolkotabi, M. (2022). On the effectiveness of active learning by uncertainty sampling in classification of high-dimensional gaussian mixture data. In ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4238\u20134242). IEEE","DOI":"10.1109\/ICASSP43922.2022.9747685"},{"key":"6743_CR30","doi-asserted-by":"crossref","unstructured":"Miyata, T. (2023). Training of perceptual image denoising network with weighted sum of iqa methods. In 2023 IEEE 20th consumer communications & networking conference (CCNC) (pp. 658\u2013659). IEEE","DOI":"10.1109\/CCNC51644.2023.10059768"},{"key":"6743_CR31","doi-asserted-by":"crossref","unstructured":"Oppenlaender, J. (2023). The cultivated practices of text-to-image generation. arXiv preprint arXiv:2306.11393","DOI":"10.1007\/978-3-031-66528-8_14"},{"key":"6743_CR32","doi-asserted-by":"crossref","unstructured":"Peng, J., Liu, D., Xu, S., & Li, H. (2021). Generating diverse structure for image inpainting with hierarchical vq-vae. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10775\u201310784).","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"6743_CR33","first-page":"16131","volume":"34","author":"Q Pham","year":"2021","unstructured":"Pham, Q., Liu, C., & Hoi, S. (2021). Dualnet: Continual learning, fast and slow. Advances in Neural Information Processing Systems, 34, 16131\u201316144.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6743_CR34","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., & Rombach, R. (2023). Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952"},{"key":"6743_CR35","unstructured":"Qin, C., Zhang, S., Yu, N., Feng, Y., Yang, X., Zhou, Y., Wang, H., Niebles, J.C., Xiong, C., Savarese, S., et al. (2023) Unicontrol: A unified diffusion model for controllable visual generation in the wild. arXiv preprint arXiv:2305.11147"},{"key":"6743_CR36","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021). Learning transferable visual models from natural language supervision. In International conference on machine learning (pp. 8748\u20138763). PMLR"},{"issue":"9","key":"6743_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3472291","volume":"54","author":"P Ren","year":"2021","unstructured":"Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Gupta, B. B., Chen, X., & Wang, X. (2021). A survey of deep active learning. ACM Computing Surveys (CSUR), 54(9), 1\u201340.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"6743_CR38","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10684\u201310695).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6743_CR39","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). 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).","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"6743_CR40","unstructured":"Sahak, H., Watson, D., Saharia, C., & Fleet, D. (2023). Denoising diffusion probabilistic models for robust image super-resolution in the wild. arXiv preprint arXiv:2302.07864"},{"key":"6743_CR41","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35, 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6743_CR42","unstructured":"Sener, O., & Savarese, S. (2018). Active learning for convolutional neural networks: A core-set approach. In International conference on learning representations."},{"key":"6743_CR43","unstructured":"Settles, B. (2009). Active learning literature survey."},{"key":"6743_CR44","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., & Jung, H.J. (2023). Instantbooth: Personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"6743_CR45","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1613\/jair.1.13689","volume":"74","author":"G Skantze","year":"2022","unstructured":"Skantze, G., & Willemsen, B. (2022). Collie: Continual learning of language grounding from language-image embeddings. Journal of Artificial Intelligence Research, 74, 1201\u20131223.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6743_CR46","doi-asserted-by":"crossref","unstructured":"Smith, J., Hsu, Y.-C., Balloch, J., Shen, Y., Jin, H., & Kira, Z. (2021). Always be dreaming: A new approach for data-free class-incremental learning. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9374\u20139384).","DOI":"10.1109\/ICCV48922.2021.00924"},{"key":"6743_CR47","unstructured":"Smith, J.S., Hsu, Y.-C., Zhang, L., Hua, T., Kira, Z., Shen, Y., & Jin, H. (2023). Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027"},{"key":"6743_CR48","unstructured":"Sun, G., Liang, W., Dong, J., Li, J., Ding, Z., & Cong, Y. (2023). Create your world: Lifelong text-to-image diffusion. arXiv preprint arXiv:2309.04430"},{"key":"6743_CR49","doi-asserted-by":"crossref","unstructured":"Valipour, M., Rezagholizadeh, M., Kobyzev, I., & Ghodsi, A. (2023). Dylora: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation. In Proceedings of the 17th conference of the European chapter of the association for computational linguistics (pp. 3266\u20133279).","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"6743_CR50","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., Mac\u00a0Aodha, O., Song, Y., Cui, Y., Sun, C., Shepard, A., Adam, H., Perona, P., & Belongie, S. (2018). The inaturalist species classification and detection dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8769\u20138778).","DOI":"10.1109\/CVPR.2018.00914"},{"issue":"1","key":"6743_CR51","doi-asserted-by":"publisher","first-page":"4069","DOI":"10.1038\/s41467-020-17866-2","volume":"11","author":"GM Ven","year":"2020","unstructured":"Ven, G. M., Siegelmann, H. T., & Tolias, A. S. (2020). Brain-inspired replay for continual learning with artificial neural networks. Nature Communications, 11(1), 4069.","journal-title":"Nature Communications"},{"key":"6743_CR52","unstructured":"Wang, L., Zhang, X., Su, H., & Zhu, J. (2023). A comprehensive survey of continual learning: Theory, method and application. arXiv preprint arXiv:2302.00487"},{"key":"6743_CR53","doi-asserted-by":"publisher","first-page":"8566","DOI":"10.1609\/aaai.v36i8.20834","volume":"36","author":"T Wang","year":"2022","unstructured":"Wang, T., Li, X., Yang, P., Hu, G., Zeng, X., Huang, S., Xu, C.-Z., & Xu, M. (2022). Boosting active learning via improving test performance. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 8566\u20138574.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6743_CR54","doi-asserted-by":"crossref","unstructured":"Wu, J., Chen, J., & Huang, D. (2022). Entropy-based active learning for object detection with progressive diversity constraint. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9397\u20139406).","DOI":"10.1109\/CVPR52688.2022.00918"},{"key":"6743_CR55","unstructured":"Yang, J., Wang, H., Xiao, R., Wu, S., Chen, G., & Zhao, J. (2023). Controllable textual inversion for personalized text-to-image generation. arXiv preprint arXiv:2304.05265"},{"key":"6743_CR56","unstructured":"Yeh, S.-Y., Hsieh, Y.-G., Gao, Z., Yang, B.B., Oh, G., & Gong, Y. (2023). Navigating text-to-image customization: From lycoris fine-tuning to model evaluation. arXiv preprint arXiv:2309.14859"},{"key":"6743_CR57","unstructured":"Zajac, M., Deja, K., Kuzina, A., Tomczak, J.M., Trzci\u0144ski, T., Shkurti, F., & Mi\u0142o\u015b, P. (2023). Exploring continual learning of diffusion models. arXiv preprint arXiv:2303.15342"},{"key":"6743_CR58","doi-asserted-by":"publisher","unstructured":"Zameshina, M., Teytaud, O., & Najman, L. (2023). Diverse diffusion: Enhancing image diversity in text-to-image generation. CoRR https:\/\/doi.org\/10.48550\/ARXIV.2310.12583arXiv:abs\/2310.12583","DOI":"10.48550\/ARXIV.2310.12583"},{"key":"6743_CR59","unstructured":"Zhang, X., Zhao, W., Lu, X., & Chien, J. (2023). Text2layer: Layered image generation using latent diffusion model. arXiv preprint arXiv:2307.09781"},{"key":"6743_CR60","doi-asserted-by":"crossref","unstructured":"Zhong, S., Huang, Z., Wen, W., Qin, J., & Lin, L. (2023). Sur-adapter: Enhancing text-to-image pre-trained diffusion models with large language models. In Proceedings of the 31st ACM international conference on multimedia (pp. 567\u2013578).","DOI":"10.1145\/3581783.3611863"},{"issue":"9","key":"6743_CR61","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"key":"6743_CR62","unstructured":"Zhu, Y., Wu, Y., Deng, Z., Russakovsky, O., & Yan, Y. (2023). Unseen image synthesis with diffusion models. arXiv preprint arXiv:2310.09213"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06743-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06743-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06743-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:02:51Z","timestamp":1770339771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06743-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["6743"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06743-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"69"}}