{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:14Z","timestamp":1777889834247,"version":"3.51.4"},"reference-count":75,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2427478"],"award-info":[{"award-number":["2427478"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000138","name":"U.S. Department of Education","doi-asserted-by":"publisher","award":["2229873"],"award-info":[{"award-number":["2229873"]}],"id":[{"id":"10.13039\/100000138","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009523","name":"College of Computing at the Georgia Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009523","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\/iccv51701.2025.01492","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16079-16089","source":"Crossref","is-referenced-by-count":0,"title":["IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance"],"prefix":"10.1109","author":[{"given":"Jiayi","family":"Guo","sequence":"first","affiliation":[{"name":"SHI Labs @ Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanhao","family":"Yan","sequence":"additional","affiliation":[{"name":"SHI Labs @ Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingqian","family":"Xu","sequence":"additional","affiliation":[{"name":"SHI Labs @ Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"SHI Labs @ Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[{"name":"SHI Labs @ Georgia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","volume-title":"Stable diffusion 3.5 large.","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref8","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01201"},{"key":"ref10","volume-title":"Directly fine-tuning diffusion models on differentiable rewards","author":"Clark","year":"2023"},{"key":"ref11","volume-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023"},{"key":"ref12","volume-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref13","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","author":"Fan","year":"2024","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","author":"Feng","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2024","journal-title":"ICLR"},{"key":"ref16","article-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00822"},{"key":"ref18","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19956"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00721"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02840"},{"key":"ref23","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","volume-title":"Ella: Equip diffusion models with 11 m for enhanced semantic alignment","author":"Hu","year":"2024"},{"key":"ref25","article-title":"Classdiffusion: More aligned personalization tuning with explicit class guidance","author":"Huang","year":"2025","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref27","volume-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref29","article-title":"Social reward: Evaluating and enhancing generative AI through million-user feedback from an online creative community","author":"Isajanyan","year":"2024","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref33","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref36","volume-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01368"},{"key":"ref38","article-title":"Unimog: Unified image generation through multimodal conditional diffusion","author":"Li","year":"2021","journal-title":"ACL"},{"key":"ref39","article-title":"Llmgrounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2024","journal-title":"TMLR"},{"key":"ref40","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"CVPR"},{"key":"ref41","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01757"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref44","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"CVPR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"ref46","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2023","journal-title":"CVPR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687656"},{"key":"ref51","article-title":"Kosmos-g: Generating images in context with multimodal large language models","author":"Pan","year":"2024","journal-title":"ICLR"},{"key":"ref52","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"ICLR"},{"key":"ref53","volume-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref55","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"CVPR"},{"key":"ref56","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref57","volume-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00777"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref60","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref61","article-title":"Moma: Multimodal 11 m adapter for fast personalized image generation","author":"Song","year":"2024","journal-title":"ECCV"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref63","volume-title":"Instantstyle: Free lunch towards stylepreserving in text-to-image generation","author":"Wang","year":"2024"},{"key":"ref64","article-title":"Cove: Unleashing the diffusion feature correspondence for consistent video editing","author":"Wang","year":"2024","journal-title":"CVPR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref68","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00713"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref72","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal 11 ms","author":"Yang","year":"2024","journal-title":"ICML"},{"key":"ref73","volume-title":"IPAdapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023"},{"key":"ref74","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"TMLR"},{"key":"ref75","volume-title":"Self-play fine-tuning of diffusion models for text-to-image generation","author":"Yuan","year":"2024"},{"key":"ref76","article-title":"Finestyle: Fine-grained controllable style personalization for text-to-image models","author":"Zhang","year":"2024","journal-title":"CVPR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref78","article-title":"UniControlNet: All-in-one control to text-to-image diffusion models","author":"Zhao","year":"2023","journal-title":"CVPR"},{"key":"ref79","article-title":"Easyref: Omni-generalized group image reference for diffusion models via multimodal llm","author":"Zong","year":"2024","journal-title":"ICML"}],"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\/11446320.pdf?arnumber=11446320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:25Z","timestamp":1777612885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01492","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}