{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:04:06Z","timestamp":1789319046922,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375919","type":"print"},{"value":"9783032375926","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\/978-3-032-37592-6_14","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:46:09Z","timestamp":1789317969000},"page":"240-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FlowInOne: Unifying Multimodal Generation as\u00a0Image-in, Image-Out Flow Matching"],"prefix":"10.1007","author":[{"given":"Junchao","family":"Yi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weixian","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qisheng","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex Jinpeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Aizman, A., Maltby, G., Breuel, T.: High performance I\/O for large scale deep learning. arXiv preprint arXiv:2001.01858 (2020)","DOI":"10.1109\/BigData47090.2019.9005703"},{"key":"14_CR2","unstructured":"Bai, J., et al.: Meissonic: revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis. In: International Conference on Learning Representations, vol.\u00a02025, pp. 74103\u201374160 (2025)"},{"key":"14_CR3","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"14_CR4","unstructured":"Bai, S., et al: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"14_CR6","unstructured":"Chang, Y., Chen, J., Cheng, A., Bogdan, P.: MaskAttn-SDXL: controllable region-level text-to-image generation. arXiv preprint arXiv:2509.15357 (2025)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: TextDiffuser: diffusion models as text painters. arXiv preprint arXiv:2305.10855 (2023)","DOI":"10.52202\/075280-0410"},{"key":"14_CR8","unstructured":"Chen, J., et al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. In: International Conference on Learning Representations, vol.\u00a02024, pp. 57611\u201357640 (2024)"},{"key":"14_CR9","unstructured":"Chen, X., et a.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z.K., Jiang, J.P., Ye, H.J., Zhan, D.C.: Hawk: leveraging spatial context for faster autoregressive text-to-image generation. arXiv preprint (2025). arXiv:2510.25739","DOI":"10.52202\/085713-4649"},{"issue":"70","key":"14_CR11","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. 25(70), 1\u201353 (2024)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR12","unstructured":"Dong, Z., et al.: Seeing is not reasoning: MVPBench for graph-based evaluation of multi-path visual physical cot. arXiv preprint arXiv:2505.24182 (2025)"},{"key":"14_CR13","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Proceedings of the 41st International Conference on Machine Learning, vol. 235, pp. 12606\u201312633 (2024)"},{"key":"14_CR14","unstructured":"Fan, L., et al.: Fluid: scaling autoregressive text-to-image generative models with continuous tokens. arXiv preprint arXiv:2410.13863 (2024)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Bermano, A.H., Chechik, G., Cohen-Or, D.: StyleGAN-NADA: CLIP-guided domain adaptation of image generators. ACM Trans. Graph 41(4) (2022)","DOI":"10.1145\/3528223.3530164"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Gat, I., et al.: Discrete flow matching. In: Advances in Neural Information Processing Systems, vol. 37, pp. 133345\u2013133385 (2024)","DOI":"10.52202\/079017-4239"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Geng, Z., Deng, M., Bai, X., Kolter, J.Z., He, K.: Mean flows for one-step generative modeling. arXiv preprint arXiv:2505.13447 (2025)","DOI":"10.52202\/085713-2534"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Gillman, N., et al.: Force prompting: video generation models can learn and generalize physics-based control signals. arXiv preprint arXiv:2505.19386 (2025)","DOI":"10.52202\/085713-3448"},{"key":"14_CR19","unstructured":"Google: Gemini (2025). https:\/\/deepmind.google\/models\/gemini\/. Accessed 07 Jan 2026"},{"key":"14_CR20","unstructured":"Google: Nano banana (2025). https:\/\/aistudio.google.com\/models\/gemini-2-5-flash-image. Accessed 22 Jan 2026"},{"key":"14_CR21","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"14_CR22","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. arXiv preprint arXiv:1706.08500 (2018)"},{"key":"14_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851. Curran Associates, Inc. (2020)"},{"key":"14_CR24","unstructured":"Jia, J., et al.: From principles to applications: a comprehensive survey of discrete tokenizers in generation, comprehension, recommendation, and information retrieval. arXiv preprint arXiv:2502.12448 (2025)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Kim, D., et al.: Democratizing text-to-image masked generative models with compact text-aware one-dimensional tokens. arXiv preprint arXiv:2501.07730 (2025)","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"14_CR26","unstructured":"Labs, B.F., et al.: FLUX.1 kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GliGen: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"14_CR28","unstructured":"Lin, W., et al.: PixWizard: versatile image-to-image visual assistant with open-language instructions. arXiv preprint arXiv:2409.15278 (2024)"},{"key":"14_CR29","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"14_CR30","unstructured":"Liu, G.H., Vahdat, A., Huang, D.A., Theodorou, E.A., Nie, W., Anandkumar, A.: I2SB: image-to-image schr\u00f6dinger bridge. In: International Conference on Machine Learning (2023)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Q., Yin, X., Yuille, A., Brown, A., Singh, M.: Flowing from words to pixels: a noise-free framework for cross-modality evolution. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2755\u20132765 (2025)","DOI":"10.1109\/CVPR52734.2025.00263"},{"key":"14_CR32","unstructured":"Liu, S., et al.: Step1X-edit: a practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)"},{"key":"14_CR33","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"14_CR34","unstructured":"Liu, X., Zhang, X., Ma, J., Peng, J., Liu, Q.: InstaFlow: one step is enough for high-quality diffusion-based text-to-image generation. arXiv preprint arXiv:2309.06380 (2024)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al: Latent harmony: synergistic unified UHD image restoration via latent space regularization and controllable refinement. arXiv preprint arXiv:2510.07961 (2025)","DOI":"10.52202\/085713-1481"},{"key":"14_CR36","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022)"},{"key":"14_CR37","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Nobis, G., et al.: Fractional diffusion bridge models. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/085713-3819"},{"key":"14_CR39","unstructured":"OpenAI: ChatGPT (2025). https:\/\/chatgpt.com\/. Accessed 16 Jan 2026"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Pan, X., Tewari, A., Leimk\u00fchler, T., Liu, L., Meka, A., Theobalt, C.: Drag your GAN: interactive point-based manipulation on the generative image manifold. In: ACM SIGGRAPH 2023 Conference Proceedings (2023)","DOI":"10.1145\/3588432.3591500"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Peebles, W.S., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4172\u20134182 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"14_CR42","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"14_CR43","unstructured":"Polyak, A.: Movie gen: a cast of media foundation models. arXiv preprint arXiv:2410.13720 (2025)"},{"key":"14_CR44","unstructured":"Qian, Y., et al.: Pico-banana-400K: a large-scale dataset for text-guided image editing. arXiv preprint arXiv:2510.19808 (2025)"},{"key":"14_CR45","unstructured":"Qwen Team: Qwen3.5: Towards native multimodal agents (2026). https:\/\/qwen.ai\/blog?id=qwen3.5. Accessed 01 Mar 2026"},{"key":"14_CR46","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 8821\u20138831 (2021)"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR48","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2014)","journal-title":"Int. J. Comput. Vision"},{"key":"14_CR49","unstructured":"Rust, P., Lotz, J.F., Bugliarello, E., Salesky, E., de\u00a0Lhoneux, M., Elliott, D.: Language modelling with pixels. arXiv preprint arXiv:2207.06991 (2022)"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Salesky, E., Etter, D., Post, M.: Robust open-vocabulary translation from visual text representations. arXiv preprint arXiv:2104.08211 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.576"},{"key":"14_CR51","unstructured":"Sim\u00e9oni, O., et al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"14_CR52","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"14_CR53","unstructured":"Sucheng, R., Qihang, Y., Ju, H., Xiaohui, S., Alan, Y., Liang-Chieh, C.: Beyond next-token: next-X prediction for autoregressive visual generation. arXiv preprint arXiv:2502.20388 (2025)"},{"key":"14_CR54","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: LLaMA for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"14_CR55","unstructured":"Wang, H., et al.: Residual diffusion bridge model for image restoration. arXiv preprint arXiv:2510.23116 (2025)"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C.K., Loy, C.C.: Exploring CLIP for assessing the look and feel of images. In: AAAI Conference on Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"14_CR57","unstructured":"Wang, J., Chan, K.C.K., Loy, C.C.: Exploring CLIP for assessing the look and feel of images. arXiv preprint arXiv:2207.12396 (2022)"},{"key":"14_CR58","unstructured":"Wang, Y., et al.: GPT-image-edit-1.5m: a million-scale, GPT-generated image dataset. arXiv preprint arXiv:2507.21033 (2025)"},{"key":"14_CR59","unstructured":"Weber, M., et al.: MaskBit: embedding-free image generation via bit tokens. arXiv preprint arXiv:2409.16211 (2024)"},{"key":"14_CR60","unstructured":"Wu, C., et al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"14_CR61","unstructured":"Wu, C., et al.: OmniGen2: exploration to advanced multimodal generation. arXiv preprint arXiv:2506.18871 (2025)"},{"key":"14_CR62","unstructured":"Xiao, C., et al.: Pixel sentence representation learning. arXiv preprint arXiv:2402.08183 (2024)"},{"key":"14_CR63","doi-asserted-by":"crossref","unstructured":"Xiao, J., Nayak, R., Zhang, N., Toertei, D., Loianno, G.: ThermalGen: style-disentangled flow-based generative models for RGB-to-thermal image translation. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-1112"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Xing, L., Wang, A.J., Yan, R., Shu, X., Tang, J.: Vision-centric token compression in large language model. In: Advances in Neural Information Processing Systems, vol. 38, pp. 33080\u201333110 (2025)","DOI":"10.52202\/085713-1111"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: GlyphControl: glyph conditional control for visual text generation. Adv. Neural. Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1912"},{"key":"14_CR66","unstructured":"Ye, K., et al.: UnicEdit-10M: a dataset and benchmark breaking the scale-quality barrier via unified verification for reasoning-enriched edits. arXiv preprint arXiv:2512.02790 (2025)"},{"key":"14_CR67","doi-asserted-by":"crossref","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Randomized autoregressive visual generation. arXiv preprint arXiv:2411.00776 (2024)","DOI":"10.1109\/ICCV51701.2025.01713"},{"key":"14_CR68","unstructured":"Zhang, H., et al.: AlphaFlow: understanding and improving meanflow models. arXiv preprint arXiv:2510.20771 (2025)"},{"key":"14_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3813\u20133824 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"14_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Ren, Y., Xia, X., Xiao, X., Xie, X.: Dense2MoE: restructuring diffusion transformer to MoE for efficient text-to-image generation. arXiv preprint arXiv:2510.09094 (2025)","DOI":"10.1109\/ICCV51701.2025.01734"},{"key":"14_CR71","unstructured":"Zhou, L., Lou, A., Khanna, S., Ermon, S.: Denoising diffusion bridge models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, B., Zhu, Y., Yang, X., Chen, C., Xu, J.: Shifted diffusion for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10157\u201310166 (2023)","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"14_CR73","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593 (2020)"},{"key":"14_CR74","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/s11263-026-02862-8","volume":"134","author":"K Zou","year":"2026","unstructured":"Zou, K., Zhao, Z., Liu, B., Yu, N.: Advancing aesthetic image generation via composition transfer. Int. J. Comput. Vision 134, 252 (2026)","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\/978-3-032-37592-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:46:22Z","timestamp":1789317982000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37592-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375919","9783032375926"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37592-6_14","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":"14 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"}}]}}