{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:06:55Z","timestamp":1788991615050,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370259","type":"print"},{"value":"9783032370266","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\/978-3-032-37026-6_29","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:12:20Z","timestamp":1788988340000},"page":"523-541","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LlamaSeg: Image Segmentation via\u00a0Autoregressive Mask Generation"],"prefix":"10.1007","author":[{"given":"Jiru","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengjin","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"29_CR2","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"29_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":"29_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Lu, J., Zhu, X., Zhang, L.: Generative semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7111\u20137120 (2023)","DOI":"10.1109\/CVPR52729.2023.00687"},{"key":"29_CR6","unstructured":"Chen, X., et al.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"29_CR7","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR8","unstructured":"Chowdhery, A., et al.: PALM: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=vvoWPYqZJA","DOI":"10.52202\/075280-2142"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"29_CR12","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":"29_CR13","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"29_CR14","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR, vol. 1, no. 2, p. 3 (2022)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"29_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2013)"},{"key":"29_CR17","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., Jia, J.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"29_CR19","unstructured":"Lan, M., et al.: Text4Seg: reimagining image segmentation as text generation. arXiv preprint arXiv:2410.09855 (2024)"},{"key":"29_CR20","unstructured":"Li, B., et\u00a0al.: LLaVA-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"29_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"29_CR23","unstructured":"Liu, H., et al.: LLaVA-next: improved reasoning, OCR, and world knowledge (2024)"},{"key":"29_CR24","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"29_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Lu, J., et al.: Unified-IO 2: Scaling autoregressive multimodal models with vision language audio and action. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26439\u201326455 (2024)","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"29_CR28","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. arXiv preprint arXiv:2206.08916 (2022)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Pramanick, S., et al.: Jack of all tasks master of many: designing general-purpose coarse-to-fine vision-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14076\u201314088 (2024)","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"29_CR30","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"29_CR31","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International conference on machine learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"29_CR32","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":"29_CR33","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: PixelLM: pixel reasoning with large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26374\u201326383 (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"29_CR34","unstructured":"Singh, A., Rozeboom, J., Ray, N.: Tokenizing semantic segmentation with run length encoding. arXiv preprint arXiv:2602.21627 (2026)"},{"key":"29_CR35","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: LLaMA for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"29_CR36","unstructured":"Team, C.: Chameleon: mixed-modal early-fusion foundation models, vol. 9 (2024). https:\/\/arxiv.org\/abs\/2405.09818"},{"key":"29_CR37","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":"29_CR38","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"29_CR39","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"29_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":"29_CR41","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"29_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: GiT: towards generalist vision transformer through universal language interface. In: European Conference on Computer Vision, pp. 55\u201373. Springer (2024)","DOI":"10.1007\/978-3-031-73397-0_4"},{"key":"29_CR44","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Wang, T., Cheng, C., Wang, L., Chen, S., Zhao, W.: HiMTok: learning hierarchical mask tokens for image segmentation with large multimodal model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23267\u201323278 (2025)","DOI":"10.1109\/ICCV51701.2025.02160"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. Adv. Neural. Inf. Process. Syst. 36, 61501\u201361513 (2023)","DOI":"10.52202\/075280-2688"},{"key":"29_CR47","first-page":"28312","volume":"38","author":"X Wang","year":"2026","unstructured":"Wang, X., et al.: ArgenSeg: image segmentation with autoregressive image generation model. Adv. Neural. Inf. Process. Syst. 38, 28312\u201328336 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: CLIP-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"29_CR49","unstructured":"Wei, C., Tan, H., Zhong, Y., Yang, Y., Lasagna, L.M.: Language-based segmentation assistant for complex queries. arXiv preprint arXiv:2404.08506, vol. 2, no. 3, p. 6 (2024)"},{"key":"29_CR50","unstructured":"Weng, T., Jiang, W., Wang, J., Li, M., Ma, L., Ming, Z.: OddGridBench: exposing the lack of fine-grained visual discrepancy sensitivity in multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1575\u20131584 (2026)"},{"key":"29_CR51","doi-asserted-by":"crossref","unstructured":"Weng, T., Wang, J., Jiang, W., Ming, Z.: VisNumBench: evaluating number sense of multimodal large language models. arXiv preprint arXiv:2503.14939 (2025)","DOI":"10.1109\/ICCV51701.2025.00365"},{"key":"29_CR52","doi-asserted-by":"publisher","first-page":"69925","DOI":"10.52202\/079017-2235","volume":"37","author":"J Wu","year":"2024","unstructured":"Wu, J., et al.: VisionLLM v2: an end-to-end generalist multimodal large language model for hundreds of vision-language tasks. Adv. Neural. Inf. Process. Syst. 37, 69925\u201369975 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR53","doi-asserted-by":"crossref","unstructured":"Xia, Z., Han, D., Han, Y., Pan, X., Song, S., Huang, G.: GSVA: generalized segmentation via multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3858\u20133869 (2024)","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"29_CR54","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: u-LLaVA: unifying multi-modal tasks via large language model. In: ECAI 2024, pp. 618\u2013625. IOS Press (2024)","DOI":"10.3233\/FAIA240541"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"29_CR57","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. arXiv preprint (2021). arXiv:2110.04627"},{"key":"29_CR58","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, vol. 2, no. 3, p.\u00a05 (2022)"},{"key":"29_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"29_CR60","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"29_CR61","doi-asserted-by":"publisher","first-page":"71737","DOI":"10.52202\/079017-2291","volume":"37","author":"T Zhang","year":"2024","unstructured":"Zhang, T., et al.: OMG-LLaVA: bridging image-level, object-level, pixel-level reasoning and understanding. Adv. Neural. Inf. Process. Syst. 37, 71737\u201371767 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR62","doi-asserted-by":"publisher","first-page":"23412","DOI":"10.52202\/068431-1701","volume":"35","author":"C Zheng","year":"2022","unstructured":"Zheng, C., Vuong, T.L., Cai, J., Phung, D.: MoVQ: modulating quantized vectors for high-fidelity image generation. Adv. Neural. Inf. Process. Syst. 35, 23412\u201323425 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR63","first-page":"165921","volume":"38","author":"R Zheng","year":"2026","unstructured":"Zheng, R., Qi, L., Chen, X., Wang, Y., Wang, K., Zhao, H.: Seg-var: image segmentation with visual autoregressive modeling. Adv. Neural. Inf. Process. Syst. 38, 165921\u2013165942 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR64","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"}],"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\/978-3-032-37026-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:12:29Z","timestamp":1788988349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37026-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370259","9783032370266"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37026-6_29","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"}}]}}