{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:47:25Z","timestamp":1792025245292,"version":"4.4.0"},"publisher-location":"Cham","reference-count":91,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370976","type":"print"},{"value":"9783032370983","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\/978-3-032-37098-3_22","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:07:02Z","timestamp":1788944822000},"page":"398-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cheers: Decoupling Patch Details from\u00a0Semantic Representations Enables Unified Multimodal Comprehension and\u00a0Generation"],"prefix":"10.1007","author":[{"given":"Yichen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shichu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanghao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"22_CR1","unstructured":"An, X., et al.: Llava-onevision-1.5: Fully open framework for democratized multimodal training (2025). https:\/\/arxiv.org\/abs\/2509.23661"},{"key":"22_CR2","unstructured":"Baade, A., et al.: Latent forcing: Reordering the diffusion trajectory for pixel-space image generation. arXiv preprint arXiv:2602.11401 (2026)"},{"key":"22_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"22_CR4","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), \u00a08 (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"22_CR5","unstructured":"Chen, F., Jing, M., Lu, W., Feng, Y., Li, X., Cao, X.: Unihetero: Could generation enhance understanding for vision-language-model at large data scale? arXiv preprint arXiv:2512.23512 (2025)"},{"key":"22_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":"22_CR7","unstructured":"Chen, J., et al.: Sharegpt-4o-image: Aligning multimodal models with gpt-4o-level image generation. arXiv preprint arXiv:2506.18095 (2025)"},{"key":"22_CR8","doi-asserted-by":"publisher","first-page":"27056","DOI":"10.52202\/079017-0850","volume":"37","author":"L Chen","year":"2024","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? Adv. Neural. Inf. Process. Syst. 37, 27056\u201327087 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR9","unstructured":"Chen, X., et al.: Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"22_CR10","unstructured":"Chu, X., et\u00a0al.: Mobilevlm v2: Faster and stronger baseline for vision language model. arXiv preprint arXiv:2402.03766 (2024)"},{"key":"22_CR11","unstructured":"Cui, Y., et\u00a0al.: Emu3. 5: Native multimodal models are world learners. arXiv preprint arXiv:2510.26583 (2025)"},{"key":"22_CR12","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"22_CR13","unstructured":"Du, S., et al.: Vqrae: Representation quantization autoencoders for multimodal understanding, generation and reconstruction. arXiv preprint arXiv:2511.23386 (2025)"},{"key":"22_CR14","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Fan, W., Diao, H., Wang, Q., Lin, D., Liu, Z.: The prism hypothesis: Harmonizing semantic and pixel representations via unified autoencoding. arXiv preprint arXiv:2512.19693 (2025)","DOI":"10.1007\/978-3-032-37138-6_23"},{"key":"22_CR16","unstructured":"Ge, Y., et al.: Seed-x: Multimodal models with unified multi-granularity comprehension and generation. arXiv preprint arXiv:2404.14396 (2024)"},{"key":"22_CR17","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":"22_CR18","unstructured":"Gu, S., et\u00a0al.: Infinity-mm: Scaling multimodal performance with large-scale and high-quality instruction data. arXiv preprint arXiv:2410.18558 (2024)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Vision as a dialect: Unifying visual understanding and generation via text-aligned representations. arXiv preprint arXiv:2506.18898 (2025)","DOI":"10.52202\/085713-5294"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Vision as a dialect: Unifying visual understanding and generation via text-aligned representations. arXiv preprint arXiv:2506.18898 (2025)","DOI":"10.52202\/085713-5294"},{"key":"22_CR21","unstructured":"Han, S., Kim, J.: Clip-vqdiffusion: Langauge free training of text to image generation using clip and vector quantized diffusion model. arXiv preprint arXiv:2403.14944 (2024)"},{"key":"22_CR22","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: Ella: Equip diffusion models with llm for enhanced semantic alignment. arXiv preprint arXiv:2403.05135 (2024)"},{"key":"22_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A Diagram is Worth a Dozen Images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"22_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"22_CR25","unstructured":"Labs, B.F.: FLUX.2: Frontier Visual Intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2"},{"key":"22_CR26","unstructured":"Labs, B.F., et al.: Flux.1 kontext: Flow matching for in-context image generation and editing in latent space (2025). https:\/\/arxiv.org\/abs\/2506.15742"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: Benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"22_CR28","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":"22_CR29","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":"22_CR30","unstructured":"Liao, C., et al.: Mogao: An omni foundation model for interleaved multi-modal generation. arXiv preprint arXiv:2505.05472 (2025)"},{"key":"22_CR31","unstructured":"Lin, H., et al.: Toklip: Marry visual tokens to clip for multimodal comprehension and generation. arXiv preprint arXiv:2505.05422 (2025)"},{"key":"22_CR32","unstructured":"Lin, S., Wang, A., Yang, X.: Sdxl-lightning: Progressive adversarial diffusion distillation. arXiv preprint arXiv:2402.13929 (2024)"},{"key":"22_CR33","unstructured":"Liu, H., Yan, W., Zaharia, M., Abbeel, P.: World model on million-length video and language with blockwise ringattention. arXiv preprint arXiv:2402.08268 (2024)"},{"key":"22_CR34","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: Mmbench: Is your multi-modal model an all-around player? In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 216\u2013233. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"issue":"12","key":"22_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6","volume":"67","author":"Y Liu","year":"2024","unstructured":"Liu, Y., et al.: Ocrbench: on the hidden mystery of ocr in large multimodal models. SCIENCE CHINA Inf. Sci. 67(12), 220102 (2024)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"22_CR36","unstructured":"Liu, Z., et\u00a0al.: Tuna: Taming unified visual representations for native unified multimodal models. arXiv preprint arXiv:2512.02014 (2025)"},{"key":"22_CR37","unstructured":"Lu, H., et\u00a0al.: Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)"},{"key":"22_CR38","unstructured":"Lu, P., et al.: Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Unitok: A unified tokenizer for visual generation and understanding. arXiv preprint arXiv:2502.20321 (2025)","DOI":"10.52202\/085713-4306"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Ma, Y., et\u00a0al.: Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7739\u20137751 (2025)","DOI":"10.1109\/CVPR52734.2025.00725"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Masry, A., Do, X.L., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: A benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR43","unstructured":"Peng, D., et al.: Flexivideo: Variation-aware temporal dynamics modeling for efficient video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9804\u20139814 (2026)"},{"key":"22_CR44","unstructured":"Podell, D., et al.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Qu, L., et al.: Tokenflow: Unified image tokenizer for multimodal understanding and generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2545\u20132555 (2025)","DOI":"10.1109\/CVPR52734.2025.00243"},{"key":"22_CR46","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":"22_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: A large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"22_CR49","unstructured":"Shi, M., et al.: Latent diffusion model without variational autoencoder. arXiv preprint arXiv:2510.15301 (2025)"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"22_CR51","unstructured":"skvarre: movie-posters-100k (2023). https:\/\/huggingface.co\/datasets\/skvarre\/movie_posters-100k"},{"key":"22_CR52","unstructured":"Song, W., et al.: Dualtoken: Towards unifying visual understanding and generation with dual visual vocabularies. arXiv preprint arXiv:2503.14324 (2025)"},{"key":"22_CR53","unstructured":"Su, Z., et al.: Generation enhances understanding in unified multimodal models via multi-representation generation. arXiv preprint arXiv:2601.21406 (2026)"},{"key":"22_CR54","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Sun, Q., et al.: Generative multimodal models are in-context learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14398\u201314409 (2024)","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"22_CR56","unstructured":"Sun, Q., et al.: Emu: Generative pretraining in multimodality. arXiv preprint arXiv:2307.05222 (2023)"},{"key":"22_CR57","unstructured":"Sun, S., et al.: Llava-uhd v3: Progressive visual compression for efficient native-resolution encoding in mllms. arXiv preprint arXiv:2511.21150 (2025)"},{"key":"22_CR58","unstructured":"Swerdlow, A., Prabhudesai, M., Gandhi, S., Pathak, D., Fragkiadaki, K.: Unified multimodal discrete diffusion. arXiv preprint arXiv:2503.20853 (2025)"},{"key":"22_CR59","doi-asserted-by":"publisher","unstructured":"Team, C.: Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818 (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.09818, https:\/\/github.com\/facebookresearch\/chameleon","DOI":"10.48550\/arXiv.2405.09818"},{"key":"22_CR60","unstructured":"Team, K., et\u00a0al.: Kimi k2. 5: Visual agentic intelligence. arXiv preprint arXiv:2602.02276 (2026)"},{"key":"22_CR61","unstructured":"Team, N., et al.: Nextstep-1: Toward autoregressive image generation with continuous tokens at scale. arXiv preprint arXiv:2508.10711 (2025)"},{"key":"22_CR62","unstructured":"Team, Q.: Qwen2.5: A party of foundation models (2024). https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"22_CR63","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":"22_CR64","unstructured":"Tong, S., et al.: Scaling text-to-image diffusion transformers with representation autoencoders. arXiv preprint arXiv:2601.16208 (2026)"},{"key":"22_CR65","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":"22_CR66","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR67","unstructured":"Wang, A.J., et\u00a0al.: Textatlas5m: A large-scale dataset for dense text image generation. arXiv preprint arXiv:2502.07870 (2025)"},{"key":"22_CR68","unstructured":"Wang, B., et\u00a0al.: Nemotron-cascade: Scaling cascaded reinforcement learning for general-purpose reasoning models. arXiv preprint arXiv:2512.13607 (2025)"},{"key":"22_CR69","unstructured":"Wang, H., et al.: Reconstructive visual instruction tuning. arXiv preprint arXiv:2410.09575 (2024)"},{"key":"22_CR70","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":"22_CR71","unstructured":"Wang, W., et al.: Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"22_CR72","unstructured":"Wang, X., et\u00a0al.: Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)"},{"key":"22_CR73","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: DiffusionDB: A large-scale prompt gallery dataset for text-to-image generative models. arXiv:2210.14896 [cs] (2022). https:\/\/arxiv.org\/abs\/2210.14896"},{"key":"22_CR74","doi-asserted-by":"crossref","unstructured":"Wu, C., et\u00a0al.: Janus: Decoupling visual encoding for unified multimodal understanding and generation. arXiv preprint arXiv:2410.13848 (2024)","DOI":"10.1109\/CVPR52734.2025.01210"},{"key":"22_CR75","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":"22_CR76","unstructured":"Wu, Y., et al.: Vila-u: a unified foundation model integrating visual understanding and generation. arXiv preprint arXiv:2409.04429 (2024)"},{"key":"22_CR77","unstructured":"X.AI: Grok-1.5 vision preview (2024). https:\/\/x.ai\/blog\/grok-1.5v"},{"key":"22_CR78","unstructured":"Xie, E., et al.: Sana: Efficient high-resolution image synthesis with linear diffusion transformer (2024). https:\/\/arxiv.org\/abs\/2410.10629"},{"key":"22_CR79","unstructured":"Xie, J., et al.: Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528 (2024)"},{"key":"22_CR80","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":"22_CR81","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":"22_CR82","doi-asserted-by":"crossref","unstructured":"Yao, J., Song, Y., Zhou, Y., Wang, X.: Towards scalable pre-training of visual tokenizers for generation. arXiv preprint arXiv:2512.13687 (2025)","DOI":"10.1007\/978-3-032-37627-5_36"},{"key":"22_CR83","doi-asserted-by":"crossref","unstructured":"Yao, J., Yang, B., Wang, X.: Reconstruction vs. generation: Taming optimization dilemma in latent diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15703\u201315712 (2025)","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"22_CR84","unstructured":"Ye, J., et\u00a0al.: Echo-4o: Harnessing the power of gpt-4o synthetic images for improved image generation. arXiv preprint arXiv:2508.09987 (2025)"},{"key":"22_CR85","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13040\u201313051 (2024)","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"22_CR86","unstructured":"Yu, S., et al.: Representation alignment for generation: Training diffusion transformers is easier than you think. arXiv preprint arXiv:2410.06940 (2024)"},{"key":"22_CR87","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":"22_CR88","unstructured":"Zhang, B., et\u00a0al.: Videollama 3: Frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)"},{"key":"22_CR89","first-page":"170934","volume":"38","author":"J Zhang","year":"2026","unstructured":"Zhang, J., Shen, Y., Chen, G., Song, L., Xing, E.: Dimensional collapse in vqvaes: Evidence and remedies. Adv. Neural. Inf. Process. Syst. 38, 170934\u2013170966 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR90","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. arXiv preprint arXiv:2510.11690 (2025)"},{"key":"22_CR91","unstructured":"Zhou, C., et al.: Transfusion: Predict the next token and diffuse images with one multi-modal model. arXiv preprint arXiv:2408.11039 (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\/978-3-032-37098-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:16:32Z","timestamp":1792023392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37098-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370976","9783032370983"],"references-count":91,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37098-3_22","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"}}]}}