{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:22:07Z","timestamp":1789122127730,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374349","type":"print"},{"value":"9783032374356","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\/978-3-032-37435-6_29","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:17:57Z","timestamp":1789118277000},"page":"536-553","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GRADE: Benchmarking Discipline-Informed Reasoning in\u00a0Image Editing"],"prefix":"10.1007","author":[{"given":"Mingxin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaokai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leyao","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zirun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiguo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changyao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qibing","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihang","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanhe","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"29_CR1","unstructured":"Analysis, A.: Image editing leaderboard. https:\/\/artificialanalysis.ai\/image\/leaderboard\/editing\/ (2026)"},{"key":"29_CR2","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"29_CR3","unstructured":"Balaji, Y., et al.: eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers arXiv preprint (2022). arXiv:2211.01324"},{"key":"29_CR4","unstructured":"Chang, Y., Feng, Y., Sun, J., Ai, J., Li, C., Zhou, S.K., Zhang, K.: Sridbench: Benchmark of scientific research illustration drawing of image generation model. arXiv preprint arXiv:2505.22126 (2025)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: European Conference on Computer Vision, pp. 88\u2013105. Springer (2022)","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"29_CR6","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"29_CR7","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Ghosh, D., Hajishirzi, H., Schmidt, L.: Geneval: An object-focused framework for evaluating text-to-image alignment (2023). https:\/\/arxiv.org\/abs\/2310.11513","DOI":"10.52202\/075280-2270"},{"key":"29_CR9","unstructured":"Google: Gemini 3 flash: frontier intelligence built for speed (2025). https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3-flash\/"},{"key":"29_CR10","unstructured":"Google: Introducing nano banana pro (2025). https:\/\/blog.google\/innovation-and-ai\/products\/nano-banana-pro\/"},{"key":"29_CR11","unstructured":"Google: Nano banana 2: Combining pro capabilities with lightning-fast speed (2025). https:\/\/blog.google\/innovation-and-ai\/technology\/ai\/nano-banana-2\/"},{"key":"29_CR12","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 (2018). https:\/\/arxiv.org\/abs\/1706.08500"},{"key":"29_CR13","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":"29_CR14","unstructured":"Hu, X., Wang, R., Fang, Y., Fu, B., Cheng, P., Yu, G.: Ella: equip diffusion models with LLM for enhanced semantic alignment (2024). https:\/\/arxiv.org\/abs\/2403.05135"},{"key":"29_CR15","unstructured":"Huang, Y., et al.: SmartEdit: exploring complex instruction-based image editing with multimodal large language models. https:\/\/arxiv.org\/abs\/2312.06739 (2023)"},{"key":"29_CR16","unstructured":"Labs, B.F.: FLUX.2: Frontier Visual Intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Li, H., et\u00a0al.: SynerGen-VL: towards synergistic image understanding and generation with vision experts and token folding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29767\u201329779 (2025)","DOI":"10.1109\/CVPR52734.2025.02771"},{"key":"29_CR18","unstructured":"Li, S., Huang, F., Zhang, L.: A survey of multimodal composite editing and retrieval https:\/\/arxiv.org\/abs\/2409.05405 (2024)"},{"key":"29_CR19","unstructured":"Liu, S., et\u00a0al.: Step1x-edit: A practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: MMMG: a massive, multidisciplinary, multi-tier generation benchmark for text-to-image reasoning. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-3193"},{"key":"29_CR21","unstructured":"Niu, Y., et al.: WISE: a world knowledge-informed semantic evaluation for text-to-image generation (2025). https:\/\/arxiv.org\/abs\/2503.07265"},{"key":"29_CR22","unstructured":"OpenAI: Gpt-image-1 (2025). https:\/\/openai.com\/index\/image-generation-api\/"},{"key":"29_CR23","unstructured":"OpenAI: Gpt-image-1.5 (2025). https:\/\/openai.com\/zh-Hans-CN\/index\/new-chatgpt-images-is-here\/"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Phan, L., et\u00a0al.: Humanity\u2019s last exam. arXiv preprint arXiv:2501.14249 (2025)","DOI":"10.21203\/rs.3.rs-6615297\/v1"},{"key":"29_CR25","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR26","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. https:\/\/arxiv.org\/abs\/1606.03498 (2016)"},{"key":"29_CR27","unstructured":"Seedream: Seedream 4.5 (2025). https:\/\/seed.bytedance.com\/en\/seedream4_5\/"},{"key":"29_CR28","unstructured":"Seedream: Seedream 5.0 (2026). https:\/\/seed.bytedance.com\/en\/seedream5_0_lite\/"},{"key":"29_CR29","unstructured":"Seedream, T., et\u00a0al.: Seedream 4.0: toward next-generation multimodal image generation. arXiv preprint arXiv:2509.20427 (2025)"},{"key":"29_CR30","unstructured":"Singh, A., et\u00a0al.: Openai GPT-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Sun, K., Fang, R., Duan, C., Liu, X., Liu, X.: T2I-reasonbench: Benchmarking reasoning-informed text-to-image generation. https:\/\/arxiv.org\/abs\/2508.17472 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.433"},{"key":"29_CR32","unstructured":"Team, C.: Chameleon: Mixed-modal early-fusion foundation models, 2024. URL https:\/\/arxiv.org\/abs\/2405.098189(8) (2024)"},{"key":"29_CR33","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models arXiv preprint. arXiv:2312.11805 (2023)"},{"key":"29_CR34","unstructured":"Wang, Z., et al.: GenExam: A multidisciplinary text-to-image exam. arXiv preprint arXiv:2509.14232 (2025)"},{"key":"29_CR35","unstructured":"Wu, C., et al.: Qwen-image technical report https:\/\/arxiv.org\/abs\/2508.02324 (2025)"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Wu, Y., Li, Z., Hu, X., Ye, X., Zeng, X., Yu, G., Zhu, W., Schiele, B., Yang, M.H., Yang, X.: Kris-bench: Benchmarking next-level intelligent image editing models. arXiv preprint arXiv:2505.16707 (2025)","DOI":"10.52202\/085713-5242"},{"key":"29_CR37","unstructured":"Xia, B., et al.: DreamOmni: Unified image generation and editing (2025). https:\/\/arxiv.org\/abs\/2412.17098"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: OmniGen: unified image generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13294\u201313304 (2025)","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: ImgEdit: A unified image editing dataset and benchmark. arXiv preprint arXiv:2505.20275 (2025)","DOI":"10.52202\/085713-4387"},{"key":"29_CR40","unstructured":"Yu, J., et al: Scaling autoregressive models for content-rich text-to-image generation (2022). https:\/\/arxiv.org\/abs\/2206.10789"},{"key":"29_CR41","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":"29_CR42","unstructured":"Zhang, C., et al.: UniModel: A visual-only framework for unified multimodal understanding and generation. arXiv preprint arXiv:2511.16917 (2025)"},{"key":"29_CR43","unstructured":"Zhang, D., et al.: Worldgenbench: A world-knowledge-integrated benchmark for reasoning-driven text-to-image generation. arXiv preprint arXiv:2505.01490 (2025)"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, J., Lu, Y., Yang, Z., Yang, Y.: In-context edit: Enabling instructional image editing with in-context generation in large-scale diffusion transformers. In: Advances in Neural Information Processing Systems (NeurIPS). arXiv:2504.20690 (2025)","DOI":"10.52202\/085713-4646"},{"issue":"12","key":"29_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-025-4676-4","volume":"68","author":"Z Zhang","year":"2025","unstructured":"Zhang, Z., et al.: Large multimodal models evaluation: a survey. Sci. China Inf. Sci. 68(12), 221301 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, X., et\u00a0al.: Envisioning beyond the pixels: Benchmarking reasoning-informed visual editing. arXiv preprint arXiv:2504.02826 (2025)","DOI":"10.52202\/085713-5791"}],"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\/978-3-032-37435-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:18:19Z","timestamp":1789118299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37435-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374349","9783032374356"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37435-6_29","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":"12 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"}}]}}