{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:40Z","timestamp":1777889260661,"version":"3.51.4"},"reference-count":73,"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"}],"funder":[{"DOI":"10.13039\/100017567","name":"Apple","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01594","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17160-17170","source":"Crossref","is-referenced-by-count":0,"title":["UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing"],"prefix":"10.1109","author":[{"given":"Tsu-Jui","family":"Fu","sequence":"first","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusu","family":"Qian","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenze","family":"Hu","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Gan","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinfei","family":"Yang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Building Normalizing Flows with Stochastic Interpolants","volume-title":"International Conference on Learning Representations (ICLR)","author":"Albergo","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02074"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","article-title":"PixArt-alpha: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2024"},{"key":"ref6","article-title":"Neural Ordinary Differential Equations","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Chen","year":"2018"},{"key":"ref7","article-title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Cho","year":"2024"},{"key":"ref8","article-title":"Diffusion Models Beat GANs on Image Synthesis","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Dhariwal","year":"2021"},{"key":"ref9","volume-title":"Dalle3 1 Million+ High Quality Captions","author":"Egan","year":"2024"},{"key":"ref10","article-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","author":"Esser","year":"2024","journal-title":"arXiv:2403.03206"},{"key":"ref11","article-title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_19"},{"key":"ref13","article-title":"SEED- Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","author":"Ge","year":"2024","journal-title":"arXiv:2405.04007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref16","article-title":"Imagen Team Google","year":"2024","journal-title":"Imagen 3"},{"key":"ref17","article-title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Guo","year":"2024"},{"key":"ref18","article-title":"StyleBooth: Image Style Editing with Multimodal Instruction","author":"Han","year":"2024","journal-title":"arXiv:2404.12154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_3"},{"key":"ref20","article-title":"Prompt-to-Prompt Image Editing with Cross Attention Control","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hertz","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref22","article-title":"Classifier-Free Diffusion Guidance","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2022"},{"key":"ref23","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref26","article-title":"Black Forest Labs","year":"2024","journal-title":"FLUX"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref28","article-title":"One Diffusion to Generate Them All","author":"Le","year":"2024","journal-title":"arXiv:2411.16318"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref31","article-title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","author":"Li","year":"2023","journal-title":"arXiv:2312.04461"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref33","article-title":"Flow Matching for Generative Modeling","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lipman","year":"2023"},{"key":"ref34","article-title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref35","article-title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref40","article-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","volume-title":"International Conference on Machine Learning (ICML)","author":"Nichol","year":"2022"},{"key":"ref41","article-title":"Im2Text: Describing Images Using 1 Million Captioned Photographs","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ordonez","year":"2021"},{"key":"ref42","article-title":"Scalable Diffusion Models with Transformers","author":"Peebles","year":"2022","journal-title":"arXiv:2212.09748"},{"key":"ref43","article-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref44","article-title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Qin","year":"2023"},{"key":"ref45","article-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","article-title":"UNet: Convolutional Networks for Biomedical Image Segmentation","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"Ronneberger","year":"2015"},{"key":"ref49","article-title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","volume-title":"International Conference on Machine Learning (ICML)","author":"Shazeer","year":"2018"},{"key":"ref50","article-title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","author":"Sheynin","year":"2023","journal-title":"arXiv:2311.10089"},{"key":"ref51","article-title":"Denoising Diffusion Implicit Models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song","year":"2021"},{"key":"ref52","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Song","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2161"},{"key":"ref54","article-title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","author":"Team","year":"2024","journal-title":"arXiv:2405.09818"},{"key":"ref55","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2023","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref56","article-title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","author":"Wang","year":"2024","journal-title":"arXiv:2401.07519"},{"key":"ref57","article-title":"OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision","author":"Wei","year":"2024","journal-title":"arXiv:2411.07199"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref59","article-title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref60","article-title":"OmniGen: Unified Image Generation","author":"Xiao","year":"2024","journal-title":"arXiv:2409.11340"},{"key":"ref61","article-title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xie","year":"2025"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01369"},{"key":"ref65","article-title":"IPAdapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","author":"Ye","year":"2024","journal-title":"arXiv:2308.06721"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0100"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref72","article-title":"Places: An Image Database for Deep Scene Understanding","author":"Zhou","year":"2016","journal-title":"arXiv:1610.02055"},{"key":"ref73","article-title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2025"}],"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\/11444856.pdf?arnumber=11444856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:19Z","timestamp":1777612219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01594","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}