{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:04:51Z","timestamp":1789715091315,"version":"4.0.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","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\/978-3-032-37174-4_35","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:00:41Z","timestamp":1789714841000},"page":"604-620","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Drift-AR: Single-Step Visual Autoregressive Generation via\u00a0Anti-symmetric Drifting"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Zou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingde","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"35_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"35_CR2","unstructured":"Anil, R., et al.: PaLM 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"35_CR3","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. arXiv preprint arXiv:2210.09461 (2022)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4599\u20134603 (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"35_CR5","unstructured":"Deng, M., Li, H., Li, T., Du, Y., He, K.: Generative modeling via drifting. arXiv preprint arXiv:2602.04770 (2026)"},{"key":"35_CR6","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":"35_CR7","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. arXiv preprint arXiv:2305.10924 (2023)","DOI":"10.52202\/075280-0731"},{"key":"35_CR8","doi-asserted-by":"publisher","first-page":"52132","DOI":"10.52202\/075280-2270","volume":"36","author":"D Ghosh","year":"2023","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: an object-focused framework for evaluating text-to-image alignment. Adv. Neural. Inf. Process. Syst. 36, 52132\u201352152 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR9","first-page":"6626","volume":"30","author":"M Heusel","year":"2017","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. Adv. Neural. Inf. Process. Syst. 30, 6626\u20136637 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR10","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":"35_CR11","unstructured":"Leviathan, Y., Kalman, M., Matias, Y.: Fast inference from transformers via speculative decoding. arXiv preprint arXiv:2211.17192 (2023)"},{"key":"35_CR12","unstructured":"Li, D., Kamko, A., Akhgari, E., Sabet, A., Xu, L., Doshi, S.: Playground v2.5: three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245 (2024)"},{"key":"35_CR13","doi-asserted-by":"publisher","first-page":"56424","DOI":"10.52202\/079017-1797","volume":"37","author":"T Li","year":"2024","unstructured":"Li, T., Tian, Y., Li, H., Deng, M., He, K.: Autoregressive image generation without vector quantization. Adv. Neural. Inf. Process. Syst. 37, 56424\u201356445 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Wei, F., Zhang, C., Zhang, H.: EAGLE-2: faster inference of language models with dynamic draft trees. arXiv preprint arXiv:2406.16858 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.422"},{"key":"35_CR15","unstructured":"Li, Y., Wei, F., Zhang, C., Zhang, H.: EAGLE: speculative sampling requires rethinking feature uncertainty. arXiv preprint arXiv:2401.15077 (2024)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Wei, F., Zhang, C., Zhang, H.: EAGLE-3: scaling up inference acceleration of large language models via training-time test. arXiv preprint arXiv:2503.01840 (2025)","DOI":"10.52202\/085713-4562"},{"key":"35_CR17","unstructured":"Lin, S., Wang, A., Yang, X.: SDXL-lightning: progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"35_CR18","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"35_CR19","unstructured":"Liu, D., et al.: Lumina-mGPT: illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining. arXiv preprint arXiv:2408.02657 (2024)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: International Conference on Learning Representations, pp. 1\u201333 (2023)","DOI":"10.1109\/ICVISP64524.2024.10959352"},{"key":"35_CR21","unstructured":"Lou, J., et al.: Token caching for diffusion transformer acceleration. arXiv preprint arXiv:2409.18523 (2024)"},{"key":"35_CR22","unstructured":"Ren, S., Yu, Q., He, J., Shen, X., Yuille, A., Chen, L.C.: FlowAR: scale-wise autoregressive image generation meets flow matching. arXiv preprint arXiv:2412.15205 (2024)"},{"key":"35_CR23","first-page":"2234","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29, 2234\u20132242 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR24","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Shang, Y., Yuan, Z., Xie, B., Wu, B., Yan, Y.: Post-training quantization on diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1972\u20131981 (2023)","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"35_CR26","doi-asserted-by":"publisher","first-page":"48686","DOI":"10.52202\/075280-2113","volume":"36","author":"J So","year":"2023","unstructured":"So, J., Lee, J., Ahn, D., Kim, H., Park, E.: Temporal dynamic quantization for diffusion models. Adv. Neural. Inf. Process. Syst. 36, 48686\u201348698 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR27","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132264. PMLR (2015)"},{"key":"35_CR28","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: International Conference on Machine Learning, pp. 32211\u201332252. PMLR (2023)"},{"key":"35_CR29","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"35_CR30","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"35_CR31","unstructured":"Team, N., et al.: NextStep-1: toward autoregressive image generation with continuous tokens at scale. arXiv preprint arXiv:2508.10711 (2025)"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"84839","DOI":"10.52202\/079017-2694","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."},{"key":"35_CR33","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"35_CR34","first-page":"6306","volume":"30","author":"A Van Den Oord","year":"2017","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Adv. Neural. Inf. Process. Syst. 30, 6306\u20136315 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR35","unstructured":"Wang, Y., et al.: Parallelized autoregressive visual generation. arXiv preprint arXiv:2412.15119 (2024)"},{"key":"35_CR36","unstructured":"Wang, Z., Zhang, R., Ding, K., Yang, Q., Li, F., Xiang, S.: Continuous speculative decoding for autoregressive image generation. arXiv preprint arXiv:2411.11925 (2024)"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Yan, F., et al.: LazyMAR: accelerating masked autoregressive models via feature caching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15552\u201315561 (2025)","DOI":"10.1109\/ICCV51701.2025.01443"},{"key":"35_CR38","doi-asserted-by":"publisher","first-page":"47455","DOI":"10.52202\/079017-1505","volume":"37","author":"T Yin","year":"2024","unstructured":"Yin, T., et al.: Improved distribution matching distillation for fast image synthesis. Adv. Neural. Inf. Process. Syst. 37, 47455\u201347487 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR39","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6613\u20136623 (2024)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: DiTFastAttn: attention compression for diffusion transformer models. arXiv preprint arXiv:2406.08552 (2024)","DOI":"10.52202\/079017-0037"},{"key":"35_CR41","unstructured":"Zhang, D., Li, S., Chen, C., Xie, Q., Lu, H.: Laptop-diff: layer pruning and normalized distillation for compressing diffusion models. arXiv preprint arXiv:2404.11098 (2024)"},{"key":"35_CR42","unstructured":"Zhen, D., et al.: Marrying autoregressive transformer and diffusion with multi-reference autoregression. arXiv preprint arXiv:2506.09482 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:00:56Z","timestamp":1789714856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_35","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":"19 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}