{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T04:41:06Z","timestamp":1770698466238,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-6957-1_19","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:45:56Z","timestamp":1770633956000},"page":"262-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Token-Based Multi-condition Autoregressive Diffusion for\u00a0Lung CT Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7715-4272","authenticated-orcid":false,"given":"Bo","family":"Wu","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"issue":"1","key":"19_CR1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.imed.2022.07.002","volume":"3","author":"K He","year":"2023","unstructured":"He, K., et al.: Transformers in medical image analysis. Intell. Med. 3(1), 59\u201378 (2023)","journal-title":"Intell. Med."},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Kaissis, G. A., Makowski, M. R., R\u00fcckert, D., Braren, R. F.: Secure, privacy-preserving and federated machine learning in medical imaging. Nature Mach. Intell., 2(6),305\u2013311 (2020)","DOI":"10.1038\/s42256-020-0186-1"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Zech, J. R., et al.: Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS medicine, 15(11),e1002683 (2018)","DOI":"10.1371\/journal.pmed.1002683"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Khosravi, B., et al. Creating high fidelity synthetic pelvis radiographs using generative adversarial networks: unlocking the potential of deep learning models without patient privacy concerns. J. Arthroplasty, 38(10),2037\u20132043 (2023)","DOI":"10.1016\/j.arth.2022.12.013"},{"issue":"3","key":"19_CR5","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1364\/BOE.449796","volume":"13","author":"M Gan","year":"2022","unstructured":"Gan, M., Wang, C.: Esophageal optical coherence tomography image synthesis using an adversarially learned variational autoencoder. Biomed. Opt. Express 13(3), 1188\u20131201 (2022)","journal-title":"Biomed. Opt. Express"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Khader, F., et\u00a0al.: Denoising diffusion probabilistic models for 3d medical image generation. Sci. Rep., 13(1), 7303 (2023)","DOI":"10.1038\/s41598-023-34341-2"},{"key":"19_CR7","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR8","unstructured":"Bayat, R.: A study on sample diversity in generative models: Gans vs. diffusion models (2023)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Wolleb, J., Bieder, F., Sandk\u00fchler, R., Cattin, P.C.: Diffusion models for medical anomaly detection. In: International Conference on Medical image computing and computer-assisted intervention, pp. 35\u201345. Springer (2022)","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"19_CR10","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"19_CR11","unstructured":"Menick, J., Kalchbrenner, N.: Generating high fidelity images with subscale pixel networks and multidimensional upscaling. arXiv preprint arXiv:1812.01608 (2018)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Go, S., Ji, Y., Park, S. J., Lee, S.: Generation of structurally realistic retinal fundus images with diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2335\u20132344 (2024)","DOI":"10.1109\/CVPRW63382.2024.00239"},{"key":"19_CR13","unstructured":"Song, Y., et al.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"19_CR14","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"19_CR15","first-page":"5775","volume":"35","author":"L Cheng","year":"2022","unstructured":"Cheng, L., et al.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR16","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International conference on machine learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"19_CR17","unstructured":"Razavi, A., den Oord, A.V., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"19_CR19","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2),3 (2022)"},{"key":"19_CR20","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst., 35, 36479\u201336494 (2022)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Pan, K., et al.: Generative multimodal pretraining with discrete diffusion timestep tokens. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26136\u201326146 (2025)","DOI":"10.1109\/CVPR52734.2025.02434"},{"key":"19_CR22","unstructured":"Lipman, Y., TQ Chen, R., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"19_CR23","unstructured":"Deng, C., Zhu, D., Li, K., Guang, S., Fan, H.: Causal diffusion transformers for generative modeling. arXiv preprint arXiv:2412.12095 (2024)"},{"key":"19_CR24","unstructured":"Gu, J., et al.: Denoising autoregressive transformers for scalable text-to-image generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"19_CR25","unstructured":"Pan, X., et\u00a0al.: Transfer between modalities with metaqueries. arXiv preprint arXiv:2504.06256 (2025)"},{"key":"19_CR26","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., et al.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"William Peebles and Saining Xie. Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4195\u20134205, 2023","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W. T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"19_CR30","first-page":"84839","volume":"37","author":"K Tian","year":"2024","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling:scalable image generation via next-scale prediction. Adv. Neural. Inf. Process. Syst. 37, 84839\u201384865 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:46:13Z","timestamp":1770633973000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}