{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:35Z","timestamp":1778048315840,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00799","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8282-8291","source":"Crossref","is-referenced-by-count":0,"title":["Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Zhang","sequence":"first","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Animesh","family":"Sinha","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Juefei-Xu","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Ma","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunpeng","family":"Li","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Fan","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Dai","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingbo","family":"Hou","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peizhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zecheng","family":"He","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33607-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref3","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt17t74vv.65"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","article-title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref7","article-title":"Subject-driven text-to-image generation via apprenticeship learning","volume":"36","author":"Chen","year":"2024","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref11","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023"},{"key":"ref12","article-title":"SEED-X: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024"},{"key":"ref13","article-title":"Imagine yourself: Tuning-free personalized image generation","author":"He","year":"2024"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NIPS"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"SBER-MoVQGAN","author":"Maltseva","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref24","article-title":"Chatgpt-3.5: Optimizing language models for dialogue","year":"2022"},{"key":"ref25","article-title":"Chatgpt","year":"2023"},{"key":"ref26","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref28","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref29","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref30","article-title":"Movie Gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"issue":"2","key":"ref31","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref34","article-title":"EVA-CLIP: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref36","article-title":"Generative pretraining in multimodality","author":"Sun","year":"2024","journal-title":"ICLR"},{"key":"ref37","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024"},{"key":"ref38","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref39","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref40","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref41","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref44","article-title":"Show-O: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024"},{"key":"ref45","article-title":"Reference-based painterly inpainting via diffusion: Crossing the wild reference domain gap","author":"Xu","year":"2023"},{"key":"ref46","article-title":"Lateralization lora: Interleaved instruction tuning with modality-specialized adaptations","author":"Xu","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"ref48","article-title":"Ip-adapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023"},{"key":"ref49","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023"},{"key":"ref50","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","author":"Zhang","year":"2023","journal-title":"NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","article-title":"LLaVaR: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"key":"ref53","article-title":"SVIT: Scaling up visual instruction tuning","author":"Zhao","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref55","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024"},{"key":"ref56","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref57","article-title":"Multimodal c4: An open, billion-scale corpus of images interleaved with text","volume":"36","author":"Zhu","year":"2024","journal-title":"NIPS"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492382.pdf?arnumber=11492382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:25Z","timestamp":1778046985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00799","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}