{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:06:26Z","timestamp":1789038386296,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373618","type":"print"},{"value":"9783032373625","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\/978-3-032-37362-5_11","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:12:36Z","timestamp":1789035156000},"page":"201-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SynVAR: Synergizing Spatial and\u00a0Semantic Alignment in\u00a0Visual Autoregressive Model"],"prefix":"10.1007","author":[{"given":"Zhennan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxing","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kepan","family":"Nan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zili","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"11_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"11_CR2","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: Fusing diffusion paths for controlled image generation (2023)"},{"key":"11_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR4","unstructured":"Chang, H., et al.: Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"11_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"},{"issue":"4","key":"11_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer VVision, pp. 5343\u20135353 (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gao, R., Xiang, T.Z., Lin, F.: Diffusion model for camouflaged object detection. In: ECAI 2023, pp. 445\u2013452. IOS Press (2023)","DOI":"10.3233\/FAIA230302"},{"key":"11_CR9","unstructured":"Chen, Z., et al.: Region-aware text-to-image generation via hard binding and soft refinement. arXiv preprint arXiv:2411.06558 (2024)"},{"key":"11_CR10","unstructured":"Chen, Z., et al.: L2P: Unlocking latent potential for pixel generation. arXiv preprint arXiv:2605.12013 (2026)"},{"key":"11_CR11","unstructured":"Chen, Z., et al.: DiP: Taming diffusion models in pixel space. arXiv preprint arXiv:2511.18822 (2025)"},{"key":"11_CR12","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization. arXiv preprint arXiv:2412.14169 (2024)"},{"key":"11_CR13","unstructured":"Du, N., et al.: TextCrafter: Accurately rendering multiple texts in complex visual scenes. arXiv preprint arXiv:2503.23461 (2025)"},{"key":"11_CR14","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":"11_CR15","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":"11_CR16","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":"11_CR17","doi-asserted-by":"crossref","unstructured":"Guo, X., Liu, J., Cui, M., Li, J., Yang, H., Huang, D.: InitNO: boosting text-to-image diffusion models via initial noise optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9380\u20139389 (2024)","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis. arXiv preprint arXiv:2412.04431 (2024)","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"11_CR19","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":"11_CR20","doi-asserted-by":"publisher","first-page":"78723","DOI":"10.52202\/075280-3443","volume":"36","author":"K Huang","year":"2023","unstructured":"Huang, K., Sun, K., Xie, E., Li, Z., Liu, X.: T2I-CompBench: a comprehensive benchmark for open-world compositional text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 78723\u201378747 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7701\u20137711 (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"11_CR22","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":"11_CR23","unstructured":"Ma, X., et al.: STAR: Scale-wise text-to-image generation via auto-regressive representations. arXiv preprint arXiv:2406.10797 (2024)"},{"key":"11_CR24","unstructured":"Nan, K., et al.: OpenVid-1M: A large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371 (2024)"},{"key":"11_CR25","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":"11_CR26","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"11_CR27","unstructured":"Razavi, A., Van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"11_CR28","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR29","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"11_CR30","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"11_CR31","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":"11_CR32","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"11_CR33","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"11_CR34","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"11_CR35","unstructured":"Voronov, A., Kuznedelev, D., Khoroshikh, M., Khrulkov, V., Baranchuk, D.: Switti: Designing scale-wise transformers for text-to-image synthesis. arXiv preprint arXiv:2412.01819 (2024)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Training-free text-guided image editing with visual autoregressive model. arXiv preprint arXiv:2503.23897 (2025)","DOI":"10.1109\/ICCV51701.2025.01633"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: BoxDiff: text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7452\u20137461 (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"11_CR38","unstructured":"Yang, L., Yu, Z., Meng, C., Xu, M., Ermon, S., Cui, B.: Mastering text-to-image diffusion: recaptioning, planning, and generating with multimodal LLMs. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: A survey on vision-language models for multimodal federated learning tasks. Authorea Preprints (2025)","DOI":"10.36227\/techrxiv.175624545.56457516\/v1"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: D 4-VTON: dynamic semantics disentangling for differential diffusion based virtual try-on. In: European Conference on Computer Vision, pp. 36\u201352. Springer (2024)","DOI":"10.1007\/978-3-031-72952-2_3"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: OmniVTON: training-free universal virtual try-on. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16702\u201316711 (2025)","DOI":"10.1109\/ICCV51701.2025.01551"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, C., Cai, W., Dong, C., Hu, C.: Wavelet-based fourier information interaction with frequency diffusion adjustment for underwater image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00791"},{"key":"11_CR43","unstructured":"Zhao, C., et al.: LUVE: latent-cascaded ultra-high-resolution video generation with dual frequency experts. In: Forty-third International Conference on Machine Learning (2026). https:\/\/openreview.net\/forum?id=FjZF2l8ZZF"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, C., Dong, C., Cai, W., Wang, Y.: Learning a physical-aware diffusion model based on transformer for underwater image enhancement. IEEE Trans. Geosci. Remote Sens. (2026)","DOI":"10.1109\/TGRS.2026.3660483"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: From zero to detail: a progressive spectral decoupling paradigm for UHD image restoration with new benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201318 (2026)","DOI":"10.1109\/TPAMI.2026.3691530"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, D., Li, M., Yang, Z., Yang, Y.: DreamRenderer: Taming multi-instance attribute control in large-scale text-to-image models. arXiv preprint arXiv:2503.12885 (2025)","DOI":"10.1109\/ICCV51701.2025.01552"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, D., Li, Y., Ma, F., Zhang, X., Yang, Y.: MIGC: multi-instance generation controller for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6818\u20136828 (2024)","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"11_CR48","unstructured":"Zhou, D., Xie, J., Yang, Z., Yang, Y.: 3DIS: Depth-driven decoupled instance synthesis for text-to-image generation. arXiv preprint arXiv:2410.12669 (2024)"},{"key":"11_CR49","unstructured":"Zhuang, X., et al.: VARGPT: unified understanding and generation in a visual autoregressive multimodal large language model. arXiv preprint arXiv:2501.12327 (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\/978-3-032-37362-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:12:50Z","timestamp":1789035170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37362-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373618","9783032373625"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37362-5_11","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"}}]}}