{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:42:24Z","timestamp":1776883344614,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890562","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Image Editing with Chain-of-Thought Reasoning and Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Mengxue","family":"Kang","sequence":"first","affiliation":[{"name":"AMAP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wei","sequence":"additional","affiliation":[{"name":"AMAP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhe","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref2","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","article-title":"Hq-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024"},{"key":"ref5","article-title":"Generative pretraining in multimodality","author":"Sun","year":"2023"},{"key":"ref6","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024"},{"key":"ref7","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1515\/9780773588165-061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","article-title":"Stable diffusion v1.5 model card"},{"issue":"2","key":"ref11","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"issue":"3","key":"ref12","article-title":"Scaling autoregressive multi-modal models: Pretraining and instruction tuning","volume":"2","author":"Yu","year":"2023"},{"key":"ref13","article-title":"Unified language-vision pretraining with dynamic discrete visual tokenization","author":"Jin","year":"2023"},{"key":"ref14","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02497"},{"key":"ref16","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023"},{"key":"ref17","article-title":"Vl-gpt: A generative pre-trained transformer for vision and language understanding and generation","author":"Zhu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01365"},{"key":"ref19","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024"},{"key":"ref20","article-title":"An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","first-page":"31 428","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref25","article-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer","author":"Tian","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890562.pdf?arnumber=10890562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:15Z","timestamp":1774416315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890562","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}