{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:07:35Z","timestamp":1789380455404,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370280","type":"print"},{"value":"9783032370297","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\/978-3-032-37029-7_5","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:45:28Z","timestamp":1789379128000},"page":"59-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SpecV: Specification Verification for\u00a0Robust Unified Multimodal Evaluation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1718-1859","authenticated-orcid":false,"given":"Weihao","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8010-4808","authenticated-orcid":false,"given":"Rongyao","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9701-6487","authenticated-orcid":false,"given":"Linjiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4392-6126","authenticated-orcid":false,"given":"Xianwei","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9863-1887","authenticated-orcid":false,"given":"Junyang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0853-6948","authenticated-orcid":false,"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"5_CR1","unstructured":"Anthropic: Opus-4.5 (2025). https:\/\/www.anthropic.com\/news\/claude-opus-4-5"},{"key":"5_CR2","unstructured":"ByteDance: seedream5.0 (2026). https:\/\/seed.bytedance.com\/en\/seedream5_0_lite"},{"key":"5_CR3","unstructured":"Cai, H., et al.: Z-image: an efficient image generation foundation model with single-stream diffusion transformer. arXiv preprint arXiv:2511.22699 (2025)"},{"key":"5_CR4","unstructured":"Chen, D., et al.: MLLM-as-a-judge: assessing multimodal LLM-as-a-judge with vision-language benchmark. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"5_CR5","unstructured":"Chen, J., et\u00a0al.: Blip3o-next: next frontier of native image generation. arXiv preprint arXiv:2510.15857 (2025)"},{"key":"5_CR6","unstructured":"Chen, X., et al.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"5_CR7","unstructured":"Cho, J., et al.: Davidsonian scene graph: improving reliability in finegrained evaluation for text-to-image generation. arXiv preprint arXiv:2310.18235 (2023)"},{"key":"5_CR8","unstructured":"Cui, Y., et\u00a0al.: Emu3. 5: native multimodal models are world learners. arXiv preprint arXiv:2510.26583 (2025)"},{"key":"5_CR9","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Fang, R., et al.: Got: unleashing reasoning capability of multimodal large language model for visual generation and editing. arXiv preprint arXiv:2503.10639 (2025)","DOI":"10.52202\/085713-2270"},{"key":"5_CR11","unstructured":"Fang, R., et al.: Flux-reason-6m & prism-bench: a million-scale text-to-image reasoning dataset and comprehensive benchmark. arXiv preprint arXiv:2509.09680 (2025)"},{"key":"5_CR12","unstructured":"GLM: GLM-image (2026). https:\/\/z.ai\/blog\/glm-image"},{"key":"5_CR13","unstructured":"Google: Gemini2.5-flash-image (2025). https:\/\/ai.google.dev\/gemini-api\/docs\/models\/gemini-2.5-flash-image"},{"key":"5_CR14","unstructured":"Google: Gemini3-flash (2025). https:\/\/deepmind.google\/models\/gemini\/flash\/"},{"key":"5_CR15","unstructured":"Google: Gemini3-pro (2025). https:\/\/ai.google.dev\/gemini-api\/docs\/gemini-3"},{"key":"5_CR16","unstructured":"Google: Gemini3-pro-image (2025). https:\/\/deepmind.google\/models\/gemini-image\/pro\/"},{"key":"5_CR17","unstructured":"Google: Gemini3.1-flash-image (2026). https:\/\/gemini.google\/overview\/image-generation\/"},{"key":"5_CR18","unstructured":"Google: Gemini3.1-pro (2026). https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Guan, T., et\u00a0al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14375\u201314385 (2024)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a referencefree evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"5_CR21","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: TIFA: accurate and interpretable text-to-image faithfulness evaluation with question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20406\u201320417 (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"5_CR23","unstructured":"Li, Y., et al.: Unieval: unified holistic evaluation for unified multimodal understanding and generation. arXiv preprint arXiv:2505.10483 (2025)"},{"key":"5_CR24","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":"5_CR25","unstructured":"OpenAI: GPT-5.2 (2025). https:\/\/openai.com\/zh-Hans-CN\/index\/introducing-gpt-5-2\/"},{"key":"5_CR26","unstructured":"OpenAI: Gpt-image-1 (2025). https:\/\/developers.openai.com\/api\/docs\/models\/gpt-image-1"},{"key":"5_CR27","unstructured":"OpenAI: GPT-image-1.5 (2025). https:\/\/developers.openai.com\/api\/docs\/models\/gpt-image-1.5"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Paiss, R., et al.: Teaching clip to count to ten. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3170\u20133180 (2023)","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"5_CR29","unstructured":"Qwen: Qwen-3.5 (2026). https:\/\/qwen.ai\/blog?id=qwen3.5"},{"key":"5_CR30","unstructured":"Qwen: Qwen-image-2.0 (2026). https:\/\/qwen.ai\/blog?id=qwen-image-2.0"},{"key":"5_CR31","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":"5_CR32","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":"5_CR33","unstructured":"Shi, W., et al.: Mathcanvas: intrinsic visual chain-of-thought for multimodal mathematical reasoning. arXiv preprint arXiv:2510.14958 (2025)"},{"key":"5_CR34","unstructured":"Shi, Y., et\u00a0al.: Realunify: do unified models truly benefit from unification? a comprehensive benchmark. arXiv preprint arXiv:2509.24897 (2025)"},{"key":"5_CR35","doi-asserted-by":"publisher","first-page":"113569","DOI":"10.52202\/079017-3609","volume":"37","author":"Z Wang","year":"2024","unstructured":"Wang, Z., et al.: Charxiv: charting gaps in realistic chart understanding in multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 113569\u2013113697 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR36","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"5_CR37","unstructured":"Wu, X., et al.: Human preference score v2: a solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"5_CR38","unstructured":"Xie, W., et al.: MME-unify: a comprehensive benchmark for unified multimodal understanding and generation models. arXiv preprint arXiv:2504.03641 (2025)"},{"key":"5_CR39","doi-asserted-by":"publisher","first-page":"15903","DOI":"10.52202\/075280-0700","volume":"36","author":"J Xu","year":"2023","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 15903\u201315935 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR40","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":"5_CR41","doi-asserted-by":"publisher","first-page":"46595","DOI":"10.52202\/075280-2020","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, P., et\u00a0al.: Opening: a comprehensive benchmark for judging open-ended interleaved image-text generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 56\u201366 (2025)","DOI":"10.1109\/CVPR52734.2025.00015"},{"key":"5_CR43","unstructured":"Zou, K., et al.: Uni-mmmu: a massive multi-discipline multimodal unified benchmark. arXiv preprint arXiv:2510.13759 (2025)"}],"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\/978-3-032-37029-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:45:46Z","timestamp":1789379146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37029-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370280","9783032370297"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37029-7_5","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":"15 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"}}]}}