{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:28Z","timestamp":1777656328940,"version":"3.51.4"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_17","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"302-319","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["AdaNAT: Exploring Adaptive Policy for\u00a0Token-Based Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6428-1456","authenticated-orcid":false,"given":"Zanlin","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0546-0885","authenticated-orcid":false,"given":"Renping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4850-8401","authenticated-orcid":false,"given":"Rui","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7004-939X","authenticated-orcid":false,"given":"Jiayi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9440-4198","authenticated-orcid":false,"given":"Jinyi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8276-3620","authenticated-orcid":false,"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"17_CR1","unstructured":"Bachman, P., Precup, D.: Data generation as sequential decision making. In: NeurIPS (2015)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bao, F., Li, C., Cao, Y., Zhu, J.: All are worth words: a ViT backbone for score-based diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"17_CR3","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. In: ICLR (2024)"},{"key":"17_CR4","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"17_CR5","unstructured":"Chang, H., et\u00a0al.: Muse: text-to-image generation via masked generative transformers. In: ICML (2023)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"17_CR7","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. JMLR 24, 1\u2013113 (2023)","journal-title":"JMLR"},{"key":"17_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. Google AI language. In: NAACL (2019)"},{"key":"17_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"17_CR10","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS (2021)"},{"key":"17_CR11","unstructured":"Du, N., et\u00a0al.: GLaM: efficient scaling of language models with mixture-of-experts. In: ICML (2022)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Fan, W.C., Chen, Y.C., Chen, D., Cheng, Y., Yuan, L., Wang, Y.C.F.: Frido: feature pyramid diffusion for complex scene image synthesis. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"17_CR14","unstructured":"Fan, Y., Lee, K.: Optimizing DDPM sampling with shortcut fine-tuning. arXiv preprint arXiv:2301.13362 (2023)"},{"key":"17_CR15","unstructured":"Fan, Y., et al.: Reinforcement learning for fine-tuning text-to-image diffusion models. In: NeurIPS (2023)"},{"key":"17_CR16","unstructured":"Ge, Y., Ge, Y., Zeng, Z., Wang, X., Shan, Y.: Planting a seed of vision in large language model. In: ICLR (2024)"},{"key":"17_CR17","unstructured":"Ge, Y., et al.: Making LLaMA see and draw with seed tokenizer. In: ICLR (2024)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Ghazvininejad, M., Levy, O., Liu, Y., Zettlemoyer, L.: Mask-predict: parallel decoding of conditional masked language models. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1633"},{"key":"17_CR19","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Gu, J., Kong, X.: Fully non-autoregressive neural machine translation: tricks of the trade. In: ACL (2021)","DOI":"10.18653\/v1\/2021.findings-acl.11"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"17_CR22","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)"},{"key":"17_CR23","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS Workshop (2021)"},{"key":"17_CR24","unstructured":"Hoffmann, J., et\u00a0al.: Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)"},{"key":"17_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"17_CR26","unstructured":"Kool, W., Van\u00a0Hoof, H., Welling, M.: Stochastic beams and where to find them: the Gumbel-Top-k trick for sampling sequences without replacement. In: ICML (2019)"},{"key":"17_CR27","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"17_CR28","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Draft-and-revise: effective image generation with contextual RQ-transformer. In: NeurIPS (2022)"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Lezama, J., Chang, H., Jiang, L., Essa, I.: Improved masked image generation with token-critic. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13683, pp. 70\u201386. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_5","DOI":"10.1007\/978-3-031-20050-2_5"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Li, T., Chang, H., Mishra, S., Zhang, H., Katabi, D., Krishnan, D.: MAGE: masked generative encoder to unify representation learning and image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"17_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"17_CR32","unstructured":"Liu, E., Ning, X., Yang, H., Wang, Y.: A unified sampling framework for solver searching of diffusion probabilistic models. In: ICLR (2024)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"17_CR34","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver: a fast ODE solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS (2022)"},{"key":"17_CR35","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"17_CR36","unstructured":"Mentzer, F., Minnen, D., Agustsson, E., Tschannen, M.: Finite scalar quantization: VQ-VAE made simple. In: ICLR (2023)"},{"key":"17_CR37","unstructured":"Mizrahi, D., et al.: 4M: massively multimodal masked modeling. In: NeurIPS (2023)"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Ni, Z., et al.: Revisiting non-autoregressive transformers for efficient image synthesis. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00669"},{"key":"17_CR39","unstructured":"Parmar, N., et al.: Image transformer. In: ICML (2018)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"17_CR41","unstructured":"Qian, S., Chang, H., Li, Y., Zhang, Z., Jia, J., Zhang, H.: StraIT: non-autoregressive generation with stratified image transformer. arXiv preprint arXiv:2303.00750 (2023)"},{"key":"17_CR42","unstructured":"Rae, J.W., et\u00a0al.: Scaling language models: methods, analysis & insights from training Gopher. arXiv preprint arXiv:2112.11446 (2021)"},{"key":"17_CR43","first-page":"5485","volume":"140","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 140, 5485\u20135551 (2020)","journal-title":"JMLR"},{"key":"17_CR44","unstructured":"Razavi, A., van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2 (2019)"},{"key":"17_CR45","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)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR46","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et\u00a0al.: ImageNet large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"17_CR49","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS (2016)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Sarmad, M., Lee, H.J., Kim, Y.M.: RL-GAN-Net: a reinforcement learning agent controlled GAN network for real-time point cloud shape completion. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00605"},{"key":"17_CR51","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"17_CR53","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-LM: training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)"},{"key":"17_CR54","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"17_CR55","unstructured":"Tian, C., et al.: ADDP: learning general representations for image recognition and generation with alternating denoising diffusion process. In: ICLR (2024)"},{"key":"17_CR56","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"17_CR57","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: IRGAN: a minimax game for unifying generative and discriminative information retrieval models. In: SIGIR (2017)","DOI":"10.1145\/3077136.3080786"},{"key":"17_CR59","unstructured":"Wang, T., et al.: What language model architecture and pretraining objective works best for zero-shot generalization? In: ICML (2022)"},{"key":"17_CR60","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, W., Wang, Y.F., Wang, W.Y.: No metrics are perfect: adversarial reward learning for visual storytelling. arXiv preprint arXiv:1804.09160 (2018)","DOI":"10.18653\/v1\/P18-1083"},{"key":"17_CR61","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. In: NeurIPS (2023)"},{"key":"17_CR62","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. In: TMLR (2022)"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"17_CR64","unstructured":"Yu, L., et\u00a0al.: Language model beats diffusion\u2013tokenizer is key to visual generation. In: ICLR (2024)"},{"key":"17_CR65","unstructured":"Yu, L., et\u00a0al.: Scaling autoregressive multi-modal models: pretraining and instruction tuning. arXiv preprint arXiv:2309.02591 (2023)"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Zhan, J., et\u00a0al.: AnyGPT: unified multimodal LLM with discrete sequence modeling. arXiv preprint arXiv:2402.12226 (2024)","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"17_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tzeng, E., Du, Y., Kislyuk, D.: Large-scale reinforcement learning for diffusion models. arXiv preprint arXiv:2401.12244 (2024)","DOI":"10.1007\/978-3-031-73036-8_1"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72640-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:31:14Z","timestamp":1732962674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}