{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T20:40:58Z","timestamp":1789245658620,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373687","type":"print"},{"value":"9783032373694","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\/978-3-032-37369-4_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:46:39Z","timestamp":1788932799000},"page":"331-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models"],"prefix":"10.1007","author":[{"given":"Lunbin","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingfeng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bencheng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyuan","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","first-page":"6155","DOI":"10.1109\/ACCESS.2024.3514079","volume":"13","author":"MA Ahmad","year":"2024","unstructured":"Ahmad, M.A., et al.: Mathvision: an accessible intelligent agent for visually impaired people to understand mathematical equations. IEEE Access 13, 6155\u20136165 (2024)","journal-title":"IEEE Access"},{"key":"18_CR2","unstructured":"Arriola, M., et al.: Block diffusion: Interpolating between autoregressive and diffusion language models. arXiv preprint arXiv:2503.09573 (2025)"},{"key":"18_CR3","unstructured":"Arriola, M., Venkat, N., Granskog, J., Germanidis, A.: Adapting autoregressive vision language models for parallel diffusion decoding (2025). https:\/\/runwayml.com\/research\/autoregressive-to-diffusion-vlms. Accessed 30 June 2026"},{"key":"18_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":"18_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"18_CR6","unstructured":"Bie, T., et al.: Llada2.0: scaling up diffusion language models to 100b (2025)"},{"key":"18_CR7","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":"18_CR8","unstructured":"Chen, M., et al.: Evaluating large language models trained on code (2021)"},{"key":"18_CR9","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":"18_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Sdar: a synergistic diffusion\u2013autoregression paradigm for scalable sequence generation (2025)","DOI":"10.18653\/v1\/2026.findings-acl.1110"},{"key":"18_CR11","unstructured":"Dong, H., Li, J., Wu, B., Wang, J., Zhang, Y., Guo, H.: Benchmarking and improving detail image caption. arXiv preprint arXiv:2405.19092 (2024)"},{"key":"18_CR12","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: Mme: a comprehensive evaluation benchmark for multimodal large language models (2025)","DOI":"10.52202\/085713-4899"},{"key":"18_CR14","unstructured":"Gong, S., et al.: Scaling diffusion language models via adaptation from autoregressive models. arXiv preprint arXiv:2410.17891 (2024)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Han, X., Kumar, S., Tsvetkov, Y.: Ssd-lm: semi-autoregressive simplex-based diffusion language model for text generation and modular control. arXiv preprint arXiv:2210.17432 (2022)","DOI":"10.18653\/v1\/2023.acl-long.647"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: European Conference on Computer Vision, pp. 235\u2013251. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"18_CR17","unstructured":"Li, B., et al.: Llava-next: stronger llms supercharge multimodal capabilities in the wild (2024)"},{"key":"18_CR18","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":"18_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Lavida-o: elastic large masked diffusion models for unified multimodal understanding and generation (2025)","DOI":"10.52202\/085713-3511"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Lavida: a large diffusion language model for multimodal understanding. arXiv preprint arXiv:2505.16839 (2025)","DOI":"10.52202\/085713-3511"},{"key":"18_CR21","unstructured":"Li, Y., et\u00a0al.: Recogdrive: a reinforced cognitive framework for end-to-end autonomous driving. arXiv preprint arXiv:2506.08052 (2025)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Liao, B., et\u00a0al.: Diffusiondrive: truncated diffusion model for end-to-end autonomous driving. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12037\u201312047 (2025)","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"18_CR23","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":"18_CR24","unstructured":"Liu, Y., et\u00a0al.: Sequential diffusion language models. arXiv preprint arXiv:2509.24007 (2025)"},{"key":"18_CR25","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":"18_CR26","unstructured":"Lou, A., Meng, C., Ermon, S.: Discrete diffusion modeling by estimating the ratios of the data distribution. arXiv preprint arXiv:2310.16834 (2023)"},{"key":"18_CR27","unstructured":"Lu, P., et al.: Mathvista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: Chartqa: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"18_CR29","unstructured":"Nie, S., et al.: Large language diffusion models. arXiv preprint arXiv:2502.09992 (2025)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"18_CR31","unstructured":"Qwen et al.: Qwen2.5 technical report (2025)"},{"key":"18_CR32","unstructured":"Tao, H., et al.: Infinitevl: synergizing linear and sparse attention for highly-efficient, unlimited-input vision-language models (2025)"},{"key":"18_CR33","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":"18_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural Information Processing Systems, vol. 30 (2017)"},{"key":"18_CR35","unstructured":"Wang, F., et\u00a0al.: Muirbench: a comprehensive benchmark for robust multi-image understanding. arXiv preprint arXiv:2406.09411 (2024)"},{"key":"18_CR36","unstructured":"Wu, C., et al.: Fast-dllm v2: efficient block-diffusion llm. arXiv preprint arXiv:2509.26328 (2025)"},{"key":"18_CR37","unstructured":"Wu, C., et al.: Fast-dllm: training-free acceleration of diffusion llm by enabling kv cache and parallel decoding. arXiv preprint arXiv:2505.22618 (2025)"},{"key":"18_CR38","doi-asserted-by":"publisher","first-page":"39957","DOI":"10.52202\/075280-1737","volume":"36","author":"T Wu","year":"2023","unstructured":"Wu, T., et al.: Ar-diffusion: auto-regressive diffusion model for text generation. Adv. Neural. Inf. Process. Syst. 36, 39957\u201339974 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR39","unstructured":"xAI: Grok-1.5 vision preview: connecting the digital and physical worlds with our first multimodal model (2024)"},{"key":"18_CR40","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":"18_CR41","doi-asserted-by":"publisher","first-page":"56166","DOI":"10.52202\/079017-1787","volume":"37","author":"J Yao","year":"2024","unstructured":"Yao, J., Wang, C., Liu, W., Wang, X.: Fasterdit: towards faster diffusion transformers training without architecture modification. Adv. Neural. Inf. Process. Syst. 37, 56166\u201356189 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR42","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":"18_CR43","unstructured":"Ye, J., et al.: Dream 7b: Diffusion large language models. arXiv preprint arXiv:2508.15487 (2025)"},{"key":"18_CR44","unstructured":"You, Z., et al.: Llada-v: large language diffusion models with visual instruction tuning. arXiv preprint arXiv:2505.16933 (2025)"},{"key":"18_CR45","unstructured":"Yu, R., Ma, X., Wang, X.: Dimple: discrete diffusion multimodal large language model with parallel decoding. arXiv preprint arXiv:2505.16990 (2025)"},{"key":"18_CR46","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":"18_CR47","unstructured":"Yue, X., et\u00a0al.: Mmmu-pro: a more robust multi-discipline multimodal understanding benchmark. arXiv preprint arXiv:2409.02813 (2024)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: Lmms-eval: reality check on the evaluation of large multimodal models (2024)","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"18_CR49","unstructured":"Zhang, K., et al.: Openmmreasoner: pushing the frontiers for multimodal reasoning with an open and general recipe. arXiv preprint arXiv:2511.16334 (2025)"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, R., et\u00a0al.: Mathverse: does your multi-modal llm truly see the diagrams in visual math problems? In: European Conference on Computer Vision, pp. 169\u2013186. Springer (2024)","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"18_CR51","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. In: International Conference on Learning Representations (2020)"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: Dig: Scalable and efficient diffusion models with gated linear attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7664\u20137674 (2025)","DOI":"10.1109\/CVPR52734.2025.00718"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yao, J., Yu, S., Zhang, S., Liu, W., Wang, X.: Turbo-vaed: fast and stable transfer of video-vaes to mobile devices. arXiv preprint arXiv:2508.09136 (2025)","DOI":"10.1609\/aaai.v40i16.38420"}],"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\/978-3-032-37369-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:46:48Z","timestamp":1788932808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37369-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373687","9783032373694"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37369-4_18","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"}}]}}