{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:03:24Z","timestamp":1789686204201,"version":"4.0.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","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\/978-3-032-37032-7_29","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:17:46Z","timestamp":1789683466000},"page":"535-552","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Illuminating Unified Multimodal Model for\u00a0Free-Form Interleaved Text-Image Generation"],"prefix":"10.1007","author":[{"given":"Chonghuinan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yecong","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renjing","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohe","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Ainslie, J., Lee-Thorp, J., de\u00a0Jong, M., Zemlyanskiy, Y., Lebron, F., Sanghai, S.: GQA: training generalized multi-query transformer models from multi-head checkpoints. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"29_CR2","unstructured":"Bai, S., et al.: Qwen3-VL Technical Report. arXiv:2511.21631 (2025)"},{"key":"29_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL Technical report. arXiv:2502.13923 (2025)"},{"key":"29_CR4","unstructured":"Cao, S., et\u00a0al.: Hunyuanimage 3.0 Technical report. arXiv preprint arXiv:2509.23951 (2025)"},{"key":"29_CR5","unstructured":"Chen, D., et\u00a0al.: Interleaved scene graphs for interleaved text-and-image generation assessment. arXiv preprint arXiv:2411.17188 (2024)"},{"key":"29_CR6","unstructured":"Chen, J., et\u00a0al.: BLIP3-o: a family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv:2505.09568 (2025)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: CoMM: a coherent interleaved image-text dataset for multimodal understanding and generation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00756"},{"key":"29_CR8","unstructured":"Chen, X., et al.: Janus-Pro: unified multimodal understanding and generation with data and model scaling. arXiv:2501.17811 (2025)"},{"key":"29_CR9","unstructured":"Chern, E., Su, J., Ma, Y., Liu, P.: Anole: an open, autoregressive, native large multimodal models for interleaved image-text generation. arXiv preprint arXiv:2407.06135 (2024)"},{"key":"29_CR10","unstructured":"Chow, W., et\u00a0al.: WEAVE: Unleashing and benchmarking the in-context interleaved comprehension and generation. arXiv preprint arXiv:2511.11434 (2025)"},{"key":"29_CR11","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"29_CR12","unstructured":"Cui, Y., et al.: Emu3.5: native multimodal models are world learners. arXiv:2510.26583 (2025)"},{"key":"29_CR13","unstructured":"Dehghani, M., et al.: Scaling Vision Transformers to 22 Billion Parameters. In: ICML. (2023)"},{"key":"29_CR14","unstructured":"Deng, C., et al.: Emerging properties in unified multimodal pretraining. arXiv:2505.14683 (2025)"},{"key":"29_CR15","unstructured":"Dong, R., et al.: DreamLLM: synergistic multimodal comprehension and creation. In: ICLR (2024)"},{"key":"29_CR16","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"29_CR17","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: ICML (2024)"},{"key":"29_CR18","unstructured":"Ge, Y., et al.: Making LLaMA see and draw with seed tokenizer. arXiv preprint arXiv:2310.01218 (2023)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: GenEval: an object-focused framework for evaluating text-to-image alignment. In: NeurIPS (2023)","DOI":"10.52202\/075280-2270"},{"key":"29_CR20","unstructured":"He, X., Wei, L., Ouyang, J., Liao, M., Xie, L., Tian, Q.: EMMA: efficient multimodal understanding, generation, and editing with a unified architecture. arXiv:2512.04810 (2025)"},{"key":"29_CR21","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: ELLA: equip diffusion models with LLM for enhanced semantic alignment (2024)"},{"key":"29_CR22","unstructured":"Huang, R., et al.: ILLUME+: illuminating unified mllm with dual visual tokenization and diffusion refinement. arXiv:2504.01934 (2025)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Jiao, Y., et al.: UniToken: harmonizing multimodal understanding and generation through unified visual encoding. In: CVPR (2025)","DOI":"10.1109\/CVPRW67362.2025.00345"},{"key":"29_CR24","unstructured":"Kou, S., et al.: Orthus: autoregressive interleaved image-text generation with modality-specific heads. In: ICML (2025)"},{"key":"29_CR25","unstructured":"Labs, B.F., et al.: Flux.1 Kontext: flow matching for in-context image generation and editing in latent space (2025)"},{"key":"29_CR26","unstructured":"Li, A., et\u00a0al.: Zebra-CoT: a dataset for interleaved vision language reasoning. arXiv preprint arXiv:2507.16746 (2025)"},{"key":"29_CR27","unstructured":"Li, B., et al.: ColorFLUX: a structure-color decoupling framework for old photo colorization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)"},{"key":"29_CR28","unstructured":"Li, S., et al.: Lavida-O: elastic large masked diffusion models for unified multimodal understanding and generation. arXiv preprint arXiv:2509.19244 (2025)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Dual diffusion for unified image generation and understanding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00265"},{"key":"29_CR30","unstructured":"Liao, C., et al.: Mogao: an omni foundation model for interleaved multi-modal generation. arXiv:2505.05472 (2025)"},{"key":"29_CR31","unstructured":"Lightman, H., et al.: Let\u2019s verify step by step. In: ICLR (2024)"},{"key":"29_CR32","unstructured":"Lin, B., et al.: UniWorld: high-resolution semantic encoders for unified visual understanding and generation. arXiv preprint arXiv:2506.03147 (2025)"},{"key":"29_CR33","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR (2023)"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: SmartControl: enhancing controlnet for handling rough visual conditions. In: European Conference on Computer Vision, pp. 1\u201317. Springer (2024)","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: JanusFlow: harmonizing autoregression and rectified flow for unified multimodal understanding and generation. arXiv:2411.07975 (2025)","DOI":"10.1109\/CVPR52734.2025.00725"},{"key":"29_CR36","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024)"},{"key":"29_CR37","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: ICLR (2024)"},{"key":"29_CR38","unstructured":"Qu, L., et al.: VINCIE: unlocking in-context image editing from video. In: ICLR (2026)"},{"key":"29_CR39","unstructured":"Shazeer, N.: GLU variants improve transformer. arXiv:2002.05202 (2020)"},{"key":"29_CR40","unstructured":"Shi, Q., et\u00a0al.: Muddit: liberating generation beyond text-to-image with a unified discrete diffusion model. arXiv preprint arXiv:2505.23606 (2025)"},{"key":"29_CR41","unstructured":"Singh, A., et\u00a0al.: OpenAI GPT-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position Embedding. Neurocomputing (2024)","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"29_CR43","unstructured":"Team, C.: Chameleon: mixed-modal early-fusion foundation models. arXiv:2405.09818 (2025)"},{"key":"29_CR44","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2024)"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"29_CR46","unstructured":"Tian, C., et al.: MM-Interleaved: interleaved image-text generative modeling via multi-modal feature synchronizer. arXiv (2024)"},{"key":"29_CR47","unstructured":"Wang, C., et al.: CREval: an automated interpretable evaluation for creative image manipulation under complex instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)"},{"key":"29_CR48","unstructured":"Wang, X., et\u00a0al.: Hbridge: H-shape bridging of heterogeneous experts for unified multimodal understanding and generation. arXiv preprint arXiv:2511.20520 (2025)"},{"key":"29_CR49","unstructured":"Wang, X., et\u00a0al.: Emu3: next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Wu, C., et al.: Janus: decoupling visual encoding for unified multimodal understanding and generation. arXiv:2410.13848 (2024)","DOI":"10.1109\/CVPR52734.2025.01210"},{"key":"29_CR51","unstructured":"Wu, C., et al.: YOSE: You only select essential tokens for efficient DiT-based video object removal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)"},{"key":"29_CR52","unstructured":"Wu, C., et al.: OmniGen2: exploration to advanced multimodal generation. arXiv:2506.18871 (2025)"},{"key":"29_CR53","unstructured":"Xie, J., et al.: Show-o: one single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528 (2024)"},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Xie, J., Yang, Z., Shou, M.Z.: Show-o2: improved native unified multimodal models. arXiv preprint arXiv:2506.15564 (2025)","DOI":"10.52202\/085713-1584"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: MmaDA: multimodal large diffusion language models. arXiv preprint arXiv:2505.15809 (2025)","DOI":"10.52202\/085713-4636"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: SEED-Story: multimodal long story generation with large language model. In: ICCV Workshops, pp. 1850\u20131860 (2025)","DOI":"10.1109\/ICCVW69036.2025.00197"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: MANIQA: multi-dimension attention network for no-reference image quality assessment. In: CVPR (2022)","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"29_CR58","unstructured":"Zhang, B., Sennrich, R.: Root mean square layer normalization. In: NeurIPS (2019)"},{"key":"29_CR59","unstructured":"Zhang, C., et al.: UniModel: a visual-only framework for unified multimodal understanding and generation. arXiv preprint arXiv:2511.16917 (2025)"},{"key":"29_CR60","unstructured":"Zhang, H., et al.: NextFlow: unified sequential modeling activates multimodal understanding and generation. arXiv:2601.02204 (2026)"},{"key":"29_CR61","unstructured":"Zheng, K., He, X., Wang, X.E.: MiniGPT-5: interleaved vision-and-language generation via generative vokens. arXiv preprint arXiv:2310.02239 (2023)"},{"key":"29_CR62","unstructured":"Zhou, C., et al.: Transfusion: predict the next token and diffuse images with one multi-modal model, In: ICLR (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\/978-3-032-37032-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:18:01Z","timestamp":1789683481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_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":"18 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"}}]}}