{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:09Z","timestamp":1788937629720,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":110,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371317","type":"print"},{"value":"9783032371324","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\/978-3-032-37132-4_35","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:41:23Z","timestamp":1788936083000},"page":"626-647","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transferability Between Understanding and\u00a0Generation in\u00a0Unified Multimodal Models"],"prefix":"10.1007","author":[{"given":"Jiwon","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heeji","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaewoo","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaewon","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minkyeong","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biyeon","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangwon","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"35_CR1","unstructured":"AI, Z.: Glm-ocr (2026). https:\/\/github.com\/zai-org\/GLM-OCR. Accessed 01 July 2026"},{"key":"35_CR2","unstructured":"Albergo, M.S., Vanden-Eijnden, E.: Building normalizing flows with stochastic interpolants. arXiv preprint arXiv:2209.15571 (2022)"},{"key":"35_CR3","unstructured":"Anthropic: introducing the next generation of claude (2024). https:\/\/www.anthropic.com\/news\/claude-3-family. Accessed 01 July 2026"},{"key":"35_CR4","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den Berg, R.: Structured denoising diffusion models in discrete state-spaces. Adv. Neural. Inf. Process. Syst. 34, 17981\u201317993 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"35_CR6","unstructured":"Ballard, D.H.: Modular learning in neural networks. In: Proceedings of the sixth National Conference on Artificial Intelligence-Volume 1, pp. 279\u2013284 (1987)"},{"key":"35_CR7","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Binyamin, L., Tewel, Y., Segev, H., Hirsch, E., Rassin, R., Chechik, G.: Make it count: text-to-image generation with an accurate number of objects. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13242\u201313251 (2025)","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"35_CR9","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. In: International Conference on Learning Representations, vol. 2024, pp. 4965\u20134987 (2024)"},{"key":"35_CR10","unstructured":"Black Forest Labs: FLUX.2: analyzing and enhancing the latent space of FLUX \u2013 representation comparison (2025).https:\/\/bfl.ai\/research\/representation-comparison. Accessed 01 July 2026"},{"key":"35_CR11","unstructured":"Boo, H., et al.: Countsteer: steering attention for object counting in diffusion models. arXiv preprint arXiv:2511.11253 (2025)"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Chae, J., Kim, J., Choi, J., Kim, K., Hwang, S.: Apt: adaptive personalized training for diffusion models with limited data. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28619\u201328628 (2025)","DOI":"10.1109\/CVPR52734.2025.02665"},{"key":"35_CR13","unstructured":"Chen, J., et\u00a0al.: Blip3-o: a family of fully open unified multimodal models-architecture, training and dataset (2025). https:\/\/arxiv.org\/abs\/2505.09568"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5343\u20135353 (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"35_CR15","unstructured":"Chen, X., et al.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"35_CR18","unstructured":"Cui, Y., et\u00a0al.: Emu3. 5: native multimodal models are world learners. arXiv preprint arXiv:2510.26583 (2025)"},{"key":"35_CR19","unstructured":"Dai, X., et\u00a0al.: Emu: enhancing image generation models using photogenic needles in a haystack. arXiv preprint arXiv:2309.15807 (2023)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: MOLMO and PIXMO: open weights and open data for state-of-the-art vision-language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 91\u2013104 (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"35_CR21","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"35_CR23","unstructured":"Deng, N., et al.: Internspatial: a comprehensive dataset for spatial reasoning in vision-language models. arXiv:2506.18385 arXiv preprint (2025)"},{"key":"35_CR24","unstructured":"Dong, R., et al.: Dreamllm: synergistic multimodal comprehension and creation. In: International Conference on Learning Representations, vol. 2024, pp. 6666\u20136702 (2024)"},{"key":"35_CR25","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"35_CR26","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":"35_CR27","doi-asserted-by":"publisher","first-page":"79858","DOI":"10.52202\/075280-3497","volume":"36","author":"Y Fan","year":"2023","unstructured":"Fan, Y., et al.: Dpok: reinforcement learning for fine-tuning text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 79858\u201379885 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR28","unstructured":"Fan, Y., et al.: Grit: teaching MLLMs to think with images (2025). https:\/\/arxiv.org\/abs\/2505.15879. Accessed 01 July 2026"},{"key":"35_CR29","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)"},{"key":"35_CR30","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv:2306.13394 arXiv preprint (2023)"},{"key":"35_CR31","unstructured":"Fu, S., et al.: Counting hallucinations in diffusion models. arXiv:2510.13080 arXiv preprint (2025)"},{"key":"35_CR32","unstructured":"Ge, Y., et al.: Seed-x: multimodal models with unified multi-granularity comprehension and generation. arXiv preprint arXiv:2404.14396 (2024)"},{"key":"35_CR33","unstructured":"Gemini Team Google: Gemini: A family of highly capable multimodal models. arXiv:2312.11805 arXiv preprint (2023)"},{"key":"35_CR34","doi-asserted-by":"publisher","first-page":"52132","DOI":"10.52202\/075280-2270","volume":"36","author":"D Ghosh","year":"2023","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: an object-focused framework for evaluating text-to-image alignment. Adv. Neural. Inf. Process. Syst. 36, 52132\u201352152 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR35","unstructured":"Ghosh, D., Zhang, Y., Schmidt, L.: Understanding the fine-grained knowledge capabilities of vision-language models. arXiv:2602.17871 arXiv preprint (2026)"},{"key":"35_CR36","unstructured":"Gokhale, T., et al.: Benchmarking spatial relationships in text-to-image generation. arXiv:2212.10015 arXiv preprint (2022)"},{"key":"35_CR37","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"35_CR38","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. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"35_CR39","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"35_CR41","unstructured":"Jung, W., Go, J., Jeon, M., Yoon, S., Kim, J.: Visual funnel: resolving contextual blindness in multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8962\u20138971 (2026)"},{"key":"35_CR42","unstructured":"Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: training-free perception of small visual details with multimodal LLMs. In: International Conference on Learning Representations, vol. 2025, pp. 68194\u201368213 (2025)"},{"key":"35_CR43","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 arXiv preprint (2013)"},{"key":"35_CR44","unstructured":"Kou, S., et al.: Orthus: autoregressive interleaved image-text generation with modality-specific heads. In: International Conference on Machine Learning, pp. 31619\u201331633. PMLR (2025)"},{"key":"35_CR45","unstructured":"Labs, B.F., et\u00a0al.: Flux. 1 kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"35_CR46","unstructured":"Lee, K., et al.: Aligning text-to-image models using human feedback. arXiv:2302.12192 arXiv preprint (2023)"},{"key":"35_CR47","doi-asserted-by":"publisher","first-page":"103269","DOI":"10.52202\/079017-3281","volume":"37","author":"K Lee","year":"2024","unstructured":"Lee, K., Kwak, S., Sohn, K., Shin, J.: Direct consistency optimization for robust customization of text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 37, 103269\u2013103304 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR48","doi-asserted-by":"publisher","first-page":"24897","DOI":"10.52202\/079017-0785","volume":"37","author":"S Li","year":"2024","unstructured":"Li, S., Kallidromitis, K., Gokul, A., Kato, Y., Kozuka, K.: Aligning diffusion models by optimizing human utility. Adv. Neural. Inf. Process. Syst. 37, 24897\u201324925 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR49","unstructured":"Li, T., et al.: Unifork: exploring modality alignment for unified multimodal understanding and generation. arXiv preprint arXiv:2506.17202 (2025)"},{"key":"35_CR50","unstructured":"Li, Y., Wan, P., Han, L., Wang, Y., Nie, L., Zhang, M.: Countdiffusion: text-to-image synthesis with training-free counting-guidance diffusion. arXiv preprint arXiv:2505.04347 (2025)"},{"key":"35_CR51","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"35_CR52","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Dual diffusion for unified image generation and understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2779\u20132790 (2025)","DOI":"10.1109\/CVPR52734.2025.00265"},{"key":"35_CR53","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv:2210.02747 arXiv preprint (2022)"},{"key":"35_CR54","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":"35_CR55","doi-asserted-by":"crossref","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: European Conference on Computer Vision, pp. 423\u2013439. Springer (2022)","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"35_CR56","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"35_CR57","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Mmbench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"35_CR58","unstructured":"Lou, A., Meng, C., Ermon, S.: Discrete diffusion modeling by estimating the ratios of the data distribution. arXiv:2310.16834 arXiv preprint (2023)"},{"key":"35_CR59","doi-asserted-by":"crossref","unstructured":"Lv, H., Xiao, J., Li, L.: Pick-and-draw: training-free semantic guidance for text-to-image personalization. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 10535\u201310543 (2024)","DOI":"10.1145\/3664647.3680658"},{"key":"35_CR60","unstructured":"Marsili, D., Mehta, A., Lin, R.Y., Gkioxari, G.: Same or not? enhancing visual perception in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17303\u201317315 (2026)"},{"key":"35_CR61","unstructured":"NVIDIA: Llama-nemotron-vlm-dataset-v1 (2025). https:\/\/huggingface.co\/datasets\/nvidia\/Llama-Nemotron-VLM-Dataset-v1. Accessed 01 July 2026"},{"key":"35_CR62","unstructured":"OpenAI: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"35_CR63","unstructured":"Pan, X., et\u00a0al.: Transfer between modalities with metaqueries. arXiv preprint arXiv:2504.06256 (2025)"},{"key":"35_CR64","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., Huang, J.B.: Grounded text-to-image synthesis with attention refocusing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7932\u20137942 (2024)","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"35_CR65","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations, vol. 2024, pp. 1862\u20131874 (2024)"},{"key":"35_CR66","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"35_CR67","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":"35_CR68","doi-asserted-by":"crossref","unstructured":"Sahoo, S.S., et al.: Simple and effective masked diffusion language models. Adv. Neural. Inf. Process. Syst. 37, 130136\u2013130184 (2024)","DOI":"10.52202\/079017-4135"},{"key":"35_CR69","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"35_CR70","unstructured":"Shi, Q., et al.: Muddit: liberating generation beyond text-to-image with a unified discrete diffusion model. arXiv preprint arXiv:2505.23606 (2025)"},{"key":"35_CR71","doi-asserted-by":"crossref","unstructured":"Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: Textocr: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8802\u20138812 (2021)","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"35_CR72","doi-asserted-by":"crossref","unstructured":"Song, C.H., Blukis, V., Tremblay, J., Tyree, S., Su, Y., Birchfield, S.: Robospatial: teaching spatial understanding to 2d and 3d vision-language models for robotics. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15768\u201315780 (2025)","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"35_CR73","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 arXiv preprint (2020)"},{"key":"35_CR74","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, p. 32 (2019)"},{"key":"35_CR75","unstructured":"Sun, Q., et al.: Emu: generative pretraining in multimodality. In: International Conference on Learning Representations. vol.\u00a02024, pp. 12352\u201312380 (2024)"},{"key":"35_CR76","unstructured":"Team, C.: Chameleon: mixed-modal early-fusion foundation models. arXiv:2405.09818 arXiv preprint (2024)"},{"key":"35_CR77","doi-asserted-by":"crossref","unstructured":"Tong, P., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 87310\u201387356 (2024)","DOI":"10.52202\/079017-2771"},{"key":"35_CR78","doi-asserted-by":"crossref","unstructured":"Tong, S., et al.: Metamorph: multimodal understanding and generation via instruction tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17001\u201317012 (2025)","DOI":"10.1109\/ICCV51701.2025.01579"},{"key":"35_CR79","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv:2302.13971 arXiv preprint (2023)"},{"key":"35_CR80","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv:2502.14786 arXiv preprint (2025)"},{"key":"35_CR81","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"35_CR82","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv:1601.07140 arXiv preprint (2016)"},{"key":"35_CR83","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8228\u20138238 (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"35_CR84","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":"35_CR85","unstructured":"Wang, X., et\u00a0al.: Emu3: next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)"},{"key":"35_CR86","unstructured":"Wang, Z., Hu, X., Wang, Y., Xiong, F., Zhang, M., Chu, X.: Everything in its place: benchmarking spatial intelligence of text-to-image models. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=ddFN3lWpIr"},{"key":"35_CR87","unstructured":"Wang, Z., et\u00a0al.: Lightfusion: a light-weighted, double fusion framework for unified multimodal understanding and generation. arXiv preprint arXiv:2510.22946 (2025)"},{"key":"35_CR88","doi-asserted-by":"crossref","unstructured":"Wu, C., et\u00a0al.: Janus: decoupling visual encoding for unified multimodal understanding and generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12966\u201312977 (2025)","DOI":"10.1109\/CVPR52734.2025.01210"},{"issue":"1","key":"35_CR89","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s11263-025-02639-5","volume":"134","author":"J Wu","year":"2026","unstructured":"Wu, J., et al.: Liquid: language models are scalable and unified multi-modal generators. Int. J. Comput. Vision 134(1), 39 (2026)","journal-title":"Int. J. Comput. Vision"},{"key":"35_CR90","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Harmonizing visual representations for unified multimodal understanding and generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17739\u201317750 (2025)","DOI":"10.1109\/ICCV51701.2025.01648"},{"key":"35_CR91","unstructured":"Xiao, J., Lv, H., Li, L., Wang, S., Huang, Q.: R&b: region and boundary aware zero-shot grounded text-to-image generation. In: International Conference on Learning Representations. vol.\u00a02024, pp. 26088\u201326116 (2024)"},{"key":"35_CR92","unstructured":"Xie, J., et al.: Show-o: one single transformer to unify multimodal understanding and generation. In: International Conference on Learning Representations, vol. 2025, pp. 28240\u201328264 (2025)"},{"key":"35_CR93","unstructured":"Xin, Y., et\u00a0al.: Lumina-dimoo: an omni diffusion large language model for multi-modal generation and understanding. arXiv preprint arXiv:2510.06308 (2025)"},{"key":"35_CR94","unstructured":"Xu, J., et\u00a0al.: Qwen3-omni technical report. arXiv preprint arXiv:2509.17765 (2025)"},{"key":"35_CR95","unstructured":"Xu, Z., et al.: Pisces: an auto-regressive foundation model for image understanding and generation. arXiv:2506.10395 arXiv preprint (2025)"},{"key":"35_CR96","unstructured":"Xue, L., et al.: XGEN-mm(blip-3): a family of open large multimodal models. arXiv preprint (2024)"},{"key":"35_CR97","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Mmar: towards lossless multi-modal auto-regressive probabilistic modeling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 7974\u20137985 (2025)","DOI":"10.1109\/CVPR52734.2025.00747"},{"key":"35_CR98","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: Using human feedback to fine-tune diffusion models without any reward model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8941\u20138951 (2024)","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"35_CR99","doi-asserted-by":"crossref","unstructured":"Yang, K., Russakovsky, O., Deng, J.: Spatialsense: an adversarially crowdsourced benchmark for spatial relation recognition. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00214"},{"key":"35_CR100","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Mmada: multimodal large diffusion language models. arXiv:2505.15809 arXiv preprint (2025)","DOI":"10.52202\/085713-4636"},{"key":"35_CR101","unstructured":"Yoon, H., et\u00a0al.: Visual representation alignment for multimodal large language models. arXiv preprint arXiv:2509.07979 (2025)"},{"key":"35_CR102","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":"35_CR103","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":"35_CR104","unstructured":"Zhang, J., Hu, J., Khayatkhoei, M., Ilievski, F., Sun, M.: Exploring perceptual limitation of multimodal large language models. arXiv:2402.07384 arXiv preprint (2024)"},{"key":"35_CR105","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: Visual cropping improves zero-shot question answering of multimodal large language models. In: R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models (2023)"},{"key":"35_CR106","unstructured":"Zhang, J., Li, T., Li, L., Yang, Z., Cheng, Y.: Are unified vision-language models necessary: generalization across understanding and generation. arXiv preprint arXiv:2505.23043 (2025)"},{"key":"35_CR107","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VSR: a unified framework for document layout analysis combining vision, semantics and relations. In: International Conference on Document Analysis and Recognition, pp. 115\u2013130. Springer (2021)","DOI":"10.1007\/978-3-030-86549-8_8"},{"key":"35_CR108","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop - CVPR 2017. Hawaii, U.S.A. (2017)"},{"key":"35_CR109","unstructured":"Zhao, S., et al.: Unified multimodal understanding and generation models: advances, challenges, and opportunities. arXiv:2505.02567 arXiv preprint (2025)"},{"key":"35_CR110","unstructured":"Zhou, C., et al.: Transfusion: predict the next token and diffuse images with one multi-modal model. arXiv:2408.11039 arXiv preprint (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\/978-3-032-37132-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:41:44Z","timestamp":1788936104000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37132-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371317","9783032371324"],"references-count":110,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37132-4_35","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"}}]}}