{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:22Z","timestamp":1777888822517,"version":"3.51.4"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01705","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18345-18356","source":"Crossref","is-referenced-by-count":0,"title":["ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation"],"prefix":"10.1109","author":[{"given":"Sherry X.","family":"Chen","sequence":"first","affiliation":[{"name":"University of California,Santa Barbara"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wei","sequence":"additional","affiliation":[{"name":"AI Center-Mountain View, Samsung Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"AI Center-Mountain View, Samsung Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suren","family":"Kumar","sequence":"additional","affiliation":[{"name":"AI Center-Mountain View, Samsung Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","year":"2024","journal-title":"Anthropic. Claude 3.5 sonnet model card addendum. Technical report"},{"key":"ref3","author":"Awadalla","year":"2023","journal-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models"},{"key":"ref4","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref6","author":"Bavishi","year":"2023","journal-title":"Introducing our multimodal models"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI62980.2024.10859215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","author":"Chen","year":"2024","journal-title":"Mega-bench: Scaling multimodal evaluation to over 500 real-world tasks"},{"key":"ref12","author":"Chen","year":"2024","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","author":"Couairon","year":"2022","journal-title":"Diffedit: Diffusion-based semantic image editing with mask guidance"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","first-page":"8780","volume-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref17","year":"2023","journal-title":"Dreamlike.art. Dreamlike photoreal 2.5"},{"key":"ref18","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref19","author":"Fu","year":"2023","journal-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data"},{"key":"ref20","author":"Ge","year":"2024","journal-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing"},{"key":"ref21","author":"Ge","year":"2024","journal-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation"},{"key":"ref22","author":"Gu","year":"2024","journal-title":"Multi-reward as condition for instruction-based image editing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref24","author":"Hertz","year":"2022","journal-title":"Prompt-to-Prompt image editing with cross attention control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"issue":"2","key":"ref26","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref27","author":"Jiang","year":"2024","journal-title":"Genai arena: An open evaluation platform for generative models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref29","article-title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","author":"Krojer","year":"2024","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref31","article-title":"Imagenhub: Standardizing the evaluation of conditional image generation models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ku","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref33","article-title":"Introducing idefics2: A powerful 8b vision-language model for the community","author":"Lauren\u00e7on","year":"2024","journal-title":"Hugging Face Blog"},{"key":"ref34","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref35","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref39","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","author":"Luo","year":"2023","journal-title":"Latent Consistency Models: Synthesizing highresolution images with few-step inference"},{"key":"ref43","author":"Ma","year":"2024","journal-title":"I2ebench: A comprehensive benchmark for instructionbased image editing"},{"key":"ref44","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref47","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref49","volume-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref51","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref54","author":"Smith","year":"2023","journal-title":"Aria: Advancing multimodal ai"},{"key":"ref55","author":"Song","journal-title":"Denoising diffusion implicit models"},{"key":"ref56","author":"Sun","year":"2025","journal-title":"Ie-bench: Advancing the measurement of textdriven image editing for human perception alignment"},{"key":"ref57","author":"Team","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02158"},{"key":"ref60","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref61","author":"Wang","year":"2023","journal-title":"Cogvlm: Visual expert for pretrained language models"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref63","author":"Wei","year":"2024","journal-title":"Omniedit: Building image editing generalist models through specialist supervision"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref67","first-page":"81287","article-title":"Multimodal large language models make text-toimage generative models align better","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref68","author":"Wu","year":"2024","journal-title":"Multimodal large language model is a human-aligned annotator for text-toimage generation"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref70","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref71","author":"Yao","year":"2024","journal-title":"Minicpm-v: A gpt-4v level mllm on your phone"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref73","author":"Yuksekgonul","year":"2022","journal-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0100"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444440.pdf?arnumber=11444440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:59Z","timestamp":1777611539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01705","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}