{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:08:10Z","timestamp":1788988090356,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_30","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:28:19Z","timestamp":1788985699000},"page":"544-563","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViQ: Text-Aligned Visual Quantized Representations at\u00a0Any Resolution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6022-9302","authenticated-orcid":false,"given":"Xumin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6943-3085","authenticated-orcid":false,"given":"Zuyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3952-8753","authenticated-orcid":false,"given":"Yongming","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"30_CR1","unstructured":"Agarwal, N., et\u00a0al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"30_CR2","unstructured":"Chen, L., et\u00a0al.: Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330 (2024)"},{"key":"30_CR3","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling (2025). https:\/\/arxiv. org\/abs\/2412.05271"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, X., et\u00a0al.: Simplevqa: multimodal factuality evaluation for multimodal large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4637\u20134646 (2025)","DOI":"10.1109\/ICCV51701.2025.00441"},{"key":"30_CR6","unstructured":"Chiu, C.C., Qin, J., Zhang, Y., Yu, J., Wu, Y.: Self-supervised learning with random-projection quantizer for speech recognition. In: International Conference on Machine Learning, pp. 3915\u20133924. PMLR (2022)"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Dehghani, M., et al.: Patch n\u2019pack: Navit, a vision transformer for any aspect ratio and resolution. NeurIPS 36 (2024)","DOI":"10.52202\/075280-0106"},{"key":"30_CR8","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":"30_CR9","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A., Shankar, V.: Data filtering networks. arXiv preprint arXiv:2309.17425 (2023)"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Fini, E., et\u00a0al.: Multimodal autoregressive pre-training of large vision encoders. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9641\u20139654 (2025)","DOI":"10.1109\/CVPR52734.2025.00901"},{"key":"30_CR11","unstructured":"Gersho, A., Gray, R.M.: Vector quantization and signal compression, vol.\u00a0159. Springer Science & Business Media (2012)"},{"issue":"11","key":"30_CR12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"30_CR13","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-VL Technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: ECCV, pp. 235\u2013251. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"30_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2017). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Lauren\u00e7on, H., Tronchon, L., Cord, M., Sanh, V.: What matters when building vision-language models? arXiv preprint arXiv:2405.02246 (2024)","DOI":"10.52202\/079017-2789"},{"key":"30_CR17","unstructured":"Li, B., et\u00a0al.: LMMs-eval: Accelerating the development of large multimoal models (2024)"},{"key":"30_CR18","unstructured":"Li, B., et al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"30_CR19","unstructured":"Liu, H., et al.: Llava-next: improved reasoning, OCR, and world knowledge (2024)"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. NeurIPS 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"30_CR21","unstructured":"Liu, Y., et al.: On the hidden mystery of OCR in large multimodal models. arXiv preprint arXiv:2305.07895 (2023)"},{"key":"30_CR22","unstructured":"Liu, Z., Dong, Y., Liu, Z., Hu, W., Lu, J., Rao, Y.: Oryx MLLM: on-demand spatial-temporal understanding at arbitrary resolution. arXiv preprint arXiv:2409.12961 (2024)"},{"key":"30_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"30_CR24","unstructured":"Luo, Z., Shi, F., Ge, Y., Yang, Y., Wang, L., Shan, Y.: Open-magvit2: an open-source project toward democratizing auto-regressive visual generation. arXiv preprint arXiv:2409.04410 (2024)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Unitok: a unified tokenizer for visual generation and understanding. arXiv preprint arXiv:2502.20321 (2025)","DOI":"10.52202\/085713-4306"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: Infographicvqa. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"30_CR29","unstructured":"Mentzer, F., Minnen, D., Agustsson, E., Tschannen, M.: Finite scalar quantization: VQ-VAE made simple. In: The Twelfth International Conference on Learning Representations"},{"key":"30_CR30","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"30_CR31","unstructured":"QwenTeam: Qwen2-VL: To see the world more clearly. Wwen Blog (2024). https:\/\/qwenlm.github.io\/blog\/qwen2-vl\/"},{"key":"30_CR32","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Shi, F., Luo, Z., Ge, Y., Yang, Y., Shan, Y., Wang, L.: Scalable image tokenization with index backpropagation quantization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16037\u201316046 (2025)","DOI":"10.1109\/ICCV51701.2025.01488"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"30_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"30_CR36","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"30_CR37","unstructured":"Team, K., et al.: Kimi-VL Technical report. arXiv preprint arXiv:2504.07491 (2025)"},{"key":"30_CR38","unstructured":"Team, M.L.: Longcat-next: lexicalizing modalities as discrete tokens (2026). https:\/\/arxiv.org\/abs\/2603.27538"},{"key":"30_CR39","unstructured":"Team, Q.: Qwen2.5-VL (2025). https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"30_CR40","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"30_CR41","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"30_CR42","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"30_CR43","unstructured":"Wu, C., et\u00a0al.: Qwen-image Technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"30_CR44","unstructured":"Xie, J., et al.: Show-o: one single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528 (2024)"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Xie, R., Du, C., Song, P., Liu, C.: Muse-VL: modeling unified VLM through semantic discrete encoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 24135\u201324146 (2025)","DOI":"10.1109\/ICCV51701.2025.02237"},{"key":"30_CR46","unstructured":"Yin, W., et alet\u00a0al.: Sail-vl2 Technical report. arXiv preprint arXiv:2509.14033 (2025)"},{"key":"30_CR47","unstructured":"Yu, L., et al.: Language model beats diffusion tokenizer is key to visual generation. In: The Twelfth International Conference on Learning Representations"},{"key":"30_CR48","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: Mmmu: a massive multi-discipline multimodal understanding and reasoning benchmark for expert Agi. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pretraining. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"30_CR50","unstructured":"Zhao, Y., Xiong, Y., Kraehenbuehl, P.: Image and video tokenization with binary spherical quantization. In: The Thirteenth International Conference on Learning Representations"},{"key":"30_CR51","unstructured":"Zhao, Y., et al.: Qlip: text-aligned visual tokenization unifies auto-regressive multimodal understanding and generation. CoRR (2025)"},{"key":"30_CR52","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"30_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, B., Xin, Y., Xia, Z., Xu, L.: Addressing representation collapse in vector quantized models with one linear layer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22968\u201322977 (2025)","DOI":"10.1109\/ICCV51701.2025.02132"}],"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\/978-3-032-37356-4_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:28:31Z","timestamp":1788985711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_30","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":"10 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"}}]}}