{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:11:00Z","timestamp":1789042260507,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","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\/978-3-032-37020-4_5","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:27:16Z","timestamp":1789039636000},"page":"77-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale Representation Alignment for\u00a0Visual Autoregressive Modeling with\u00a0Mixture of\u00a0Experts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2424-4388","authenticated-orcid":false,"given":"Nuoyan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8740-7927","authenticated-orcid":false,"given":"Zhijun","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-8424","authenticated-orcid":false,"given":"Kun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1435-489X","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-8235","authenticated-orcid":false,"given":"Xinghao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"5_CR2","unstructured":"Alaparthi, S., Mishra, M.: Bidirectional encoder representations from transformers (bert): a sentiment analysis odyssey. arXiv preprint arXiv:2007.01127(2020)"},{"key":"5_CR3","unstructured":"Bachmann, R., et al.: Flextok: resampling images into 1d token sequences of flexible length. In: Forty-second International Conference on Machine Learning (2025)"},{"key":"5_CR4","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"5_CR5","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":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Softvq-vae: efficient 1-dimensional continuous tokenizer. In: Proceedings of the Computer Vision and Pattern Recognition Conferenc,. pp. 28358\u201328370 (2025)","DOI":"10.1109\/CVPR52734.2025.02641"},{"key":"5_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PmLR (2020)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, X., Fang, G., Wang, X.: Collaborative decoding makes visual auto-regressive modeling efficient. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23334\u201323344 (2025)","DOI":"10.1109\/CVPR52734.2025.02173"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR10","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR11","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":"5_CR12","doi-asserted-by":"crossref","unstructured":"Esteves, C., Suhail, M., Makadia, A.: Spectral image tokenizer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17181\u201317190 (2025)","DOI":"10.1109\/ICCV51701.2025.01596"},{"issue":"120","key":"5_CR13","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(120), 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR14","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Guo, H., et al.: Fastvar: linear visual autoregressive modeling via cached token pruning. arXiv preprint arXiv:2503.23367 (2025)","DOI":"10.1109\/ICCV51701.2025.01767"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Infinity: scaling bitwise autoregressive modeling for high-resolution image synthesis. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15733\u201315744 (2025)","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"5_CR19","unstructured":"Henighan, T., et al.: Scaling laws for autoregressive generative modeling. arXiv preprint arXiv:2010.14701 (2020)"},{"key":"5_CR20","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."},{"issue":"47","key":"5_CR21","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(47), 1\u201333 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Hu, T., et al.: Improving autoregressive visual generation with cluster-oriented token prediction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9351\u20139360 (2025)","DOI":"10.1109\/CVPR52734.2025.00873"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, W., Zheng, W., Duan, Y., Zhou, J., Lu, J.: Spectralar: spectral autoregressive visual generation. arXiv preprint arXiv:2506.10962 (2025)","DOI":"10.1109\/ICCV51701.2025.01470"},{"key":"5_CR24","unstructured":"Huang, Z., et al.: Nfig: autoregressive image generation with next-frequency prediction. arXiv preprint arXiv:2503.07076 (2025)"},{"issue":"1","key":"5_CR25","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"5_CR26","unstructured":"Jia, M., et al.: Mgvq: could vq-vae beat vae? A generalizable tokenizer with multi-group quantization. arXiv preprint arXiv:2507.07997 (2025)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Jiao, S., et al.: Flexvar: flexible visual autoregressive modeling without residual prediction. arXiv preprint arXiv:2502.20313 (2025)","DOI":"10.52202\/085713-0302"},{"key":"5_CR28","unstructured":"Jin, P., Zhu, B., Yuan, L., Yan, S.: Moe++: accelerating mixture-of-experts methods with zero-computation experts. arXiv preprint arXiv:2410.07348 (2024)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"5_CR30","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"5_CR31","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11523\u201311532 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"5_CR33","unstructured":"Lepikhin, D., et al.: Gshard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"5_CR34","unstructured":"Li, T., Katabi, D., He, K.: Self-conditioned image generation via generating representations. CoRR (2023)"},{"key":"5_CR35","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":"5_CR36","unstructured":"Li, X., et al.: Imagefolder: autoregressive image generation with folded tokens. arXiv preprint arXiv:2410.01756 (2024)"},{"key":"5_CR37","unstructured":"Liu, W., Zhuo, L., Xin, Y., Xia, S., Gao, P., Yue, X.: Customize your visual autoregressive recipe with set autoregressive modeling. arXiv preprint arXiv:2410.10511 (2024)"},{"key":"5_CR38","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR39","unstructured":"Pang, Y., et\u00a0al.: Next patch prediction for autoregressive visual generation. arXiv preprint arXiv:2412.15321 (2024)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Pang, Z., et al.: Randar: decoder-only autoregressive visual generation in random orders. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 45\u201355 (2025)","DOI":"10.1109\/CVPR52734.2025.00014"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: 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":"5_CR42","doi-asserted-by":"crossref","unstructured":"Ren, S., Yu, Q., He, J., Shen, X., Yuille, A., Chen, L.C.: Beyond next-token: next-x prediction for autoregressive visual generation. arXiv preprint arXiv:2502.20388 (2025)","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: scaling stylegan to large diverse datasets. In: ACM SIGGRAPH 2022 Conference, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"5_CR45","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"5_CR46","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"5_CR47","unstructured":"Team, C.: Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818 (2024)"},{"key":"5_CR48","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"5_CR49","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":"5_CR50","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"5_CR51","unstructured":"Van Den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756. PMLR (2016)"},{"key":"5_CR52","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR53","unstructured":"Wang, X., et\u00a0al.: Emu3: next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)"},{"key":"5_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Parallelized autoregressive visual generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12955\u201312965 (2025)","DOI":"10.1109\/CVPR52734.2025.01209"},{"key":"5_CR55","unstructured":"Weber, M., et al.: Maskbit: embedding-free image generation via bit tokens. arXiv preprint arXiv:2409.16211 (2024)"},{"key":"5_CR56","unstructured":"Xie, J., et al.: Show-o: one single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528 (2024)"},{"key":"5_CR57","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: Simmim: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Yao, J., Yang, B., Wang, X.: Reconstruction vs. generation: taming optimization dilemma in latent diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15703\u201315712 (2025)","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"5_CR59","doi-asserted-by":"crossref","unstructured":"Yu, H., Luo, H., Yuan, H., Rong, Y., Zhao, F.: Frequency autoregressive image generation with continuous tokens. arXiv preprint arXiv:2503.05305 (2025)","DOI":"10.52202\/085713-1907"},{"key":"5_CR60","doi-asserted-by":"crossref","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Randomized autoregressive visual generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18431\u201318441 (2025)","DOI":"10.1109\/ICCV51701.2025.01713"},{"key":"5_CR61","doi-asserted-by":"publisher","first-page":"128940","DOI":"10.52202\/079017-4096","volume":"37","author":"Q Yu","year":"2024","unstructured":"Yu, Q., et al.: An image is worth 32 tokens for reconstruction and generation. Adv. Neural. Inf. Process. Syst. 37, 128940\u2013128966 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR62","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. arXiv preprint arXiv:2410.06940 (2024)"},{"key":"5_CR63","unstructured":"Zhang, J., Long, W., Han, M., You, W., Gu, S.: Mvar: visual autoregressive modeling with scale and spatial markovian conditioning. arXiv preprint arXiv:2505.12742 (2025)"},{"key":"5_CR64","doi-asserted-by":"publisher","first-page":"7103","DOI":"10.52202\/068431-0515","volume":"35","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y., et al.: Mixture-of-experts with expert choice routing. Adv. Neural. Inf. Process. Syst. 35, 7103\u20137114 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR65","unstructured":"Zhuang, X., et al.: Vargpt: unified understanding and generation in a visual autoregressive multimodal large language model. arXiv preprint arXiv:2501.12327 (2025)"},{"key":"5_CR66","unstructured":"Zuo, S., et al.: Taming sparsely activated transformer with stochastic experts. arXiv preprint arXiv:2110.04260 (2021)"}],"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\/978-3-032-37020-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:27:42Z","timestamp":1789039662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_5","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":"11 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"}}]}}