{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:05:48Z","timestamp":1789981548016,"version":"4.0.1"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373496","type":"print"},{"value":"9783032373502","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\/978-3-032-37350-2_14","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:39:11Z","timestamp":1789979951000},"page":"241-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ECHO: Efficient Chest X-Ray Report Generation with\u00a0One-Step Block Diffusion"],"prefix":"10.1007","author":[{"given":"Lifeng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianqi","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhimin","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jile","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicai","family":"Ou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Mou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojie","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"14_CR1","unstructured":"Arriola, M., et al.: Block diffusion: interpolating between autoregressive and diffusion language models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"14_CR2","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den, Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: Advances in Neural Information Processing Systems (2021)"},{"key":"14_CR3","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., van den Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: Advances in Neural Information Processing Systems (2021)"},{"key":"14_CR4","unstructured":"Bie, T., et\u00a0al.: LLaDA2.0: Scaling Up Diffusion Language Models to 100B. arXiv preprint arXiv:2512.15745 (2025)"},{"key":"14_CR5","unstructured":"Chandrasegaran, K., et al.: Rnd1: simple, scalable ar-to-diffusion conversion (2025)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., et\u00a0al.: Towards injecting medical visual knowledge into multimodal llms at scale. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.418"},{"key":"14_CR7","unstructured":"Chen, Z., et al.: A vision-language foundation model to enhance efficiency of chest x-ray interpretation. arXiv preprint arXiv:2401.12208 (2024)"},{"key":"14_CR8","unstructured":"Chen, Z., Fang, G., Ma, X., Yu, R., Wang, X.: dparallel: learnable parallel decoding for dllms. arXiv preprint arXiv:2509.26488 (2025)"},{"key":"14_CR9","unstructured":"Cheng, S., et al.: Sdar-vl: stable and efficient block-wise diffusion for vision-language understanding. arXiv preprint arXiv:2512.14068 (2025)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Christopher, J.K., Bartoldson, B.R., Ben-Nun, T., Cardei, M., Kailkhura, B., Fioretto, F.: Speculative diffusion decoding: accelerating language generation through diffusion. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (2025)","DOI":"10.18653\/v1\/2025.naacl-long.601"},{"key":"14_CR11","unstructured":"Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inf. Assoc. (2016)"},{"key":"14_CR12","unstructured":"Deschenaux, J., Gulcehre, C.: Beyond autoregression: fast llms via self-distillation through time (2025)"},{"key":"14_CR13","unstructured":"Dong, X., et al.: Llada-medv: exploring large language diffusion models for biomedical image understanding. arXiv preprint arXiv:2508.01617 (2025)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Du, S., et al.: Pansharpening for thin-cloud contaminated remote sensing images: a unified framework and benchmark dataset. In: Proceedings of the AAAI Conference on Artificial Intelligence (2026)","DOI":"10.1609\/aaai.v40i5.37369"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Du, S., et al.: Unsupervised hyperspectral image super-resolution via self-supervised modality decoupling. Int. J. Comput. Vis. (2026)","DOI":"10.1007\/s11263-026-02757-8"},{"key":"14_CR16","unstructured":"Fathi, N., Scholak, T., Noel, P.A.: Unifying autoregressive and diffusion-based sequence generation. In: ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy (2025)"},{"key":"14_CR17","unstructured":"Gong, S., et al.: Scaling diffusion language models via adaptation from autoregressive models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"14_CR18","unstructured":"Google DeepMind: Gemini 3 pro model card (2025)"},{"key":"14_CR19","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. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.acl-long.647"},{"key":"14_CR20","unstructured":"Hu, Z., et al.: Accelerating diffusion language model inference via efficient kv caching and guided diffusion. arXiv e-prints (2025)"},{"key":"14_CR21","unstructured":"Hurst, A., et al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"14_CR23","unstructured":"Jiang, S., et\u00a0al.: Hulu-med: a transparent generalist model towards holistic medical vision-language understanding. arXiv preprint arXiv:2510.08668 (2025)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Lee, S., Youn, J., Kim, H., Kim, M., Yoon, S.H.: Cxr-llava: a multimodal large language model for interpreting chest x-ray images. Eur. Radiol. (2025)","DOI":"10.1007\/s00330-024-11339-6"},{"key":"14_CR26","unstructured":"Li, B., et\u00a0al.: Llava-onevision: easy visual task transfer. Trans. Mach. Learn. Res. (2024)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1240"},{"key":"14_CR28","unstructured":"Li, F., et al.: Llava-next-interleave: tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Li, G., et al.: Diffuspec: unlocking diffusion language models for speculative decoding. arXiv preprint arXiv:2510.02358 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.1048"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: Lavida: a large diffusion language model for multimodal understanding. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3511"},{"key":"14_CR31","unstructured":"Liang, Y., et al.: Cd4lm: consistency distillation and adaptive decoding for diffusion language models. arXiv preprint arXiv:2601.02236 (2026)"},{"key":"14_CR32","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1516"},{"key":"14_CR34","unstructured":"Liu, Z., et al.: dllm-cache: accelerating diffusion large language models with adaptive caching. arXiv preprint arXiv:2506.06295 (2025)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Nie, S., et al.: Large language diffusion models. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-1689"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Medvlm-r1: incentivizing medical reasoning capability of vision-language models (vlms) via reinforcement learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2025)","DOI":"10.1007\/978-3-032-04981-0_32"},{"key":"14_CR37","unstructured":"Pellegrini, C., \u00d6zsoy, E., Busam, B., Navab, N., Keicher, M.: Radialog: a large vision-language model for radiology report generation and conversational assistance. arXiv preprint arXiv:2311.18681 (2023)"},{"key":"14_CR38","unstructured":"Qian, Y.Y., et al.: d3llm: ultra-fast diffusion llm using pseudo-trajectory distillation. arXiv preprint arXiv:2601.07568 (2026)"},{"key":"14_CR39","unstructured":"Saab, K., et al.: Capabilities of gemini models in medicine. arXiv preprint arXiv:2404.18416 (2024)"},{"key":"14_CR40","doi-asserted-by":"crossref","unstructured":"Sahoo, S., et al.: Simple and effective masked diffusion language models. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-4135"},{"key":"14_CR41","unstructured":"Sellergren, A., et al.: Medgemma technical report. arXiv preprint arXiv:2507.05201 (2025)"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Shi, J., Han, K., Wang, Z., Doucet, A., Titsias, M.: Simplified and generalized masked diffusion for discrete data. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-3277"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Smit, A., Jain, S., Rajpurkar, P., Pareek, A., Ng, A.Y., Lungren, M.: Combining automatic labelers and expert annotations for accurate radiology report labeling using bert. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1500\u20131519 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"14_CR44","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Thawakar, O.C., et al.: Xraygpt: chest radiographs summarization using large medical vision-language models. In: Proceedings of the 23rd Workshop on Biomedical Natural Language Processing (2024)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Tu, T., et\u00a0al.: Towards generalist biomedical ai. Nejm Ai (2024)","DOI":"10.1056\/AIoa2300138"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"14_CR48","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":"14_CR49","unstructured":"Wang, X., Xu, C., Jin, Y., Jin, J., Zhang, H., Deng, Z.: Diffusion llms can do faster-than-ar inference via discrete diffusion forcing. arXiv preprint arXiv:2508.09192 (2025)"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Hui, H., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data. Nat. Commun. (2025)","DOI":"10.1038\/s41467-025-62385-7"},{"key":"14_CR51","unstructured":"Wu, C., et al.: Fast-dllm v2: Efficient block-diffusion llm. arXiv preprint arXiv:2509.26328 (2025)"},{"key":"14_CR52","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":"14_CR53","unstructured":"Xu, M., et al.: Energy-based diffusion language models for text generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Xu, W., et\u00a0al.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv:2506.07044 (2025)","DOI":"10.1109\/TPAMI.2026.3730310"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Yang, L., Wang, Z., Chen, Z., Liang, X., Zhou, L.: Medxchat: a unified multimodal large language model framework towards cxrs understanding and generation. In: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI) (2025)","DOI":"10.1109\/ISBI60581.2025.10981215"},{"key":"14_CR56","unstructured":"Ye, J., et al.: Dream 7b: diffusion large language models. arXiv preprint arXiv:2508.15487 (2025)"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Yoo, J., Kim, W., Hong, S.: Redi: Rectified discrete flow. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-2727"},{"key":"14_CR58","unstructured":"You, Z., et al.: Llada-v: large language diffusion models with visual instruction tuning. arXiv preprint arXiv:2505.16933 (2025)"},{"key":"14_CR59","unstructured":"Yu, R., Ma, X., Wang, X.: Dimple: discrete diffusion multimodal large language model with parallel decoding. arXiv preprint arXiv:2505.16990 (2025)"},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: A generalist vision\u2013language foundation model for diverse biomedical tasks. Nat. Med. (2024)","DOI":"10.1038\/s41591-024-03185-2"},{"key":"14_CR61","unstructured":"Zhang, T., et\u00a0al.: T3d: few-step diffusion language models via trajectory self-distillation with direct discriminative optimization. arXiv preprint arXiv:2602.12262 (2026)"},{"key":"14_CR62","unstructured":"Zhang, X., Acosta, J.N., Miller, J., Huang, O., Rajpurkar, P.: Rexgradient-160k: a large-scale publicly available dataset of chest radiographs with free-text reports. arXiv preprint arXiv:2505.00228 (2025)"},{"key":"14_CR63","unstructured":"Zhang, Y., Schwing, A., Zhao, Z.: Variational masked diffusion models. arXiv preprint arXiv:2510.23606 (2025)"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, C., Cai, W., Dong, C., Hu, C.: Wavelet-based fourier information interaction with frequency diffusion adjustment for underwater image restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00791"},{"key":"14_CR65","unstructured":"Zhao, C., et al.: LUVE\u202f: latent-cascaded ultra-high-resolution video generation with dual frequency experts. In: Forty-third International Conference on Machine Learning (2026)"},{"key":"14_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Ultrahr-100k: enhancing uhr image synthesis with a large-scale high-quality dataset. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0118"},{"key":"14_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: RaTEScore: a metric for radiology report generation. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (2024)","DOI":"10.1101\/2024.06.24.24309405"}],"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\/978-3-032-37350-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:39:47Z","timestamp":1789979987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37350-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373496","9783032373502"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37350-2_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":"22 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"}}]}}