{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:05:27Z","timestamp":1789578327794,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375162","type":"print"},{"value":"9783032375179","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\/978-3-032-37517-9_30","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:49:23Z","timestamp":1789577363000},"page":"539-555","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Test-Time Registers as\u00a0Global Priors for\u00a0Tokenized Image Generation"],"prefix":"10.1007","author":[{"given":"Cheng-Yao","family":"Hong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1567-2787","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1429-4543","authenticated-orcid":false,"given":"Yuewei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-7822","authenticated-orcid":false,"given":"Chenyu","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"30_CR1","unstructured":"Beyer, L.L., Li, T., Chen, X., Karaman, S., He, K.: Highly compressed tokenizer can generate without training. In: ICML (2025)"},{"key":"30_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) NeurIPS (2020)"},{"key":"30_CR3","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":"30_CR4","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"30_CR5","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. In: ICLR (2024)"},{"key":"30_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Erel, Y., D\u00fcnkel, O., Dabral, R., Golyanik, V., Theobalt, C., Bermano, A.H.: Attention (as discrete-time markov) chains. CoRR (2025)","DOI":"10.52202\/085713-1828"},{"key":"30_CR8","unstructured":"Gao, W., Wang, Y., Ma, Y., Yang, C., Li, W., You, C.: Neurosonic: Conditional flow matching for eeg-to-speech reconstruction. CoRR (2026)"},{"key":"30_CR9","unstructured":"Gu, X., et al.: When attention sink emerges in language models: An empirical view. In: ICLR (2025)"},{"key":"30_CR10","unstructured":"Guo, L., et al.: Csrv2: unlocking ultra-sparse embeddings. CoRR (2026)"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: Hybrid neural diffeomorphic flow for shape representation and generation via triplane. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00753"},{"key":"30_CR12","unstructured":"Hayou, S., Ghosh, N., Yu, B.: Plop: Precise lora placement for efficient finetuning of large models. CoRR (2025)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, H., Cao, M., Chen, L., You, C., An, D.: Cross-modal conditioned reconstruction for language-guided medical image segmentation. IEEE TMI (2024)","DOI":"10.1109\/TMI.2024.3523333"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, N., Dravid, A., Efros, A.A., Gandelsman, Y.: Vision transformers don\u2019t need trained registers. NeurIPS (2025)","DOI":"10.52202\/085713-1891"},{"key":"30_CR15","unstructured":"Kang, S., Kim, J., Kim, J., Hwang, S.J.: See what you are told: Visual attention sink in large multimodal models. In: ICLR (2025)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Kim, D., et al.: Democratizing text-to-image masked generative models with compact text-aware one-dimensional tokens. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., You, C., Ge, S., Zou, Y., Sun, X.: Aligning source visual and target language domains for unpaired video captioning. IEEE TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3132229"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Liu, F., Yang, B., You, C., Wu, X., Ge, S., Liu, Z., Sun, X., Yang, Y., Clifton, D.: Retrieve, reason, and refine: Generating accurate and faithful patient instructions. NeurIPS (2022)","DOI":"10.52202\/068431-1370"},{"key":"30_CR19","unstructured":"Liu, F., You, C., Wu, X., Ge, S., Sun, X., et\u00a0al.: Auto-encoding knowledge graph for unsupervised medical report generation. NeurIPS (2021)"},{"key":"30_CR20","unstructured":"Lu, J., et al.: Atoken: A unified tokenizer for vision. CoRR (2025)"},{"key":"30_CR21","unstructured":"Luo, J., et al.: To sink or not to sink: Visual information pathways in large vision-language models. In: ICLR (2026)"},{"key":"30_CR22","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. TMLR (2024)"},{"key":"30_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) ICML (2021)"},{"key":"30_CR24","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. CoRR (2025)"},{"key":"30_CR25","unstructured":"Sun, M., Chen, X., Kolter, J.Z., Liu, Z.: Massive activations in large language models. CoRR (2024)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Sun, S., et al.: Coma: Compositional human motion generation with multi-modal agents. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i11.37878"},{"key":"30_CR27","unstructured":"Wang, H., et al.: Fourier-vlm: Compressing vision tokens in the frequency domain for large vision-language models. CoRR (2025)"},{"key":"30_CR28","unstructured":"Wang, Y., Ma, Y., Li, W., You, C.: Let eeg models learn eeg. CoRR (2026)"},{"key":"30_CR29","unstructured":"Wen, T., et al.: Beyond matryoshka: Revisiting sparse coding for adaptive representation. CoRR (2025)"},{"key":"30_CR30","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. In: ICLR (2024)"},{"key":"30_CR31","unstructured":"Yang, L., et al.: Less is more: Training-free sparse attention with global locality for efficient reasoning. CoRR (2025)"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"You, C., Dai, H., Min, Y., Sekhon, J.S., Joshi, S., Duncan, J.S.: Uncovering memorization effect in the presence of spurious correlations. Nature Communications (2025)","DOI":"10.1038\/s41467-025-61531-5"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"You, C., Mint, Y., Dai, W., Sekhon, J.S., Staib, L., Duncan, J.S.: Calibrating multi-modal representations: a pursuit of group robustness without annotations. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02470"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Yu, Q., Weber, M., Deng, X., Shen, X., Cremers, D., Chen, L.: An image is worth 32 tokens for reconstruction and generation. In: NeurIPS (2024)","DOI":"10.52202\/079017-4096"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Zha, K., Yu, L., Fathi, A., Ross, D.A., Schmid, C., Katabi, D., Gu, X.: Language-guided image tokenization for generation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01465"},{"key":"30_CR36","volume-title":"Lora land: 310 fine-tuned llms that rival gpt-4","author":"J Zhao","year":"2024","unstructured":"Zhao, J.: Lora land: 310 fine-tuned llms that rival gpt-4. A technical report, CoRR (2024)"}],"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\/978-3-032-37517-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:49:35Z","timestamp":1789577375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37517-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375162","9783032375179"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37517-9_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":"17 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"}}]}}