{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:03:26Z","timestamp":1784466206318,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233779","type":"print"},{"value":"9789819233786","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3378-6_16","type":"book-chapter","created":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:00:50Z","timestamp":1784466050000},"page":"190-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DynamicVAR: Multimodal-Routing-Based Adaptive Visual Autoregressive Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3742-8375","authenticated-orcid":false,"given":"GuoChao","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-3742-8375","authenticated-orcid":false,"given":"Yong","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2869-6531","authenticated-orcid":false,"given":"XuDong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"16_CR1","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS 2020, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR 2022, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV 2023, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS 2022, vol. 35, pp. 36479\u201336494 (2022)","DOI":"10.52202\/068431-2643"},{"key":"16_CR5","unstructured":"Podell, D., et al.: SDXL: Improving latent diffusion models for high-resolution image synthesis (2023). arXiv preprint https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: PixArt-\u03a3: Weak-to-strong training of diffusion transformer for 4K text-to-image generation. In: ECCV 2024, pp. 74\u201391 (2024)","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"16_CR7","unstructured":"van den Oord, A., Vinyals, O.: Neural discrete representation learning. In: NeurIPS 2017, vol. 30, pp. 6306\u20136315 (2017)"},{"key":"16_CR8","first-page":"12873","volume":"2021","author":"P Esser","year":"2021","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR. 2021, 12873\u201312883 (2021)","journal-title":"In: CVPR"},{"key":"16_CR9","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN (2021). arXiv preprint https:\/\/arxiv.org\/abs\/2110.04627"},{"key":"16_CR10","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. In: ICML 2023, pp. 4056\u20134067 (2023)"},{"key":"16_CR11","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: llama for scalable image generation (2024). arXiv preprint https:\/\/arxiv.org\/abs\/2406.06525"},{"key":"16_CR12","unstructured":"Tang, H., et al.: HART: hybrid autoregressive transformer for visual generation (2024). arXiv preprint https:\/\/arxiv.org\/abs\/2410.10812"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Infinity: scaling bitwise autoregressive modeling for high-resolution image synthesis (2025). arXiv preprint","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"16_CR14","unstructured":"Chen, T., Zhang, R., Hinton, G.: Analog bits: generating discrete data using diffusion models with self-conditioning (2022). arXiv preprint https:\/\/arxiv.org\/abs\/2208.04202"},{"key":"16_CR15","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021, pp. 8748\u20138763 (2021)"},{"key":"16_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NeurIPS 2017, vol. 30, pp. 6626\u20136637 (2017)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: A large-scale hierarchical image database. In: CVPR 2009, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"16_CR18","unstructured":"Esser, P., et al.: Stable diffusion 3: Scaling rectified flow transformers for high-resolution image synthesis (2024). arXiv preprint https:\/\/arxiv.org\/abs\/2403.03206"},{"issue":"70","key":"16_CR19","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. 25(70), 1\u201353 (2024)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR20","volume-title":"CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deepfake Videos","author":"W Ahmad","year":"2025","unstructured":"Ahmad, W., Peng, Y.T., Chang, Y.H., Ganfure, G.O., Khan, S.: CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deepfake Videos. ACM Trans. Multimedia Comput. Commun. Appl. (2025)"},{"key":"16_CR21","unstructured":"Ryoo, M.S., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: TokenLearner: adaptive space-time tokenization for videos. In: NeurIPS 2021, pp. 2577\u20132589 (2021)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3378-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:00:52Z","timestamp":1784466052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3378-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"ISBN":["9789819233779","9789819233786"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3378-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"20 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}