{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T21:05:02Z","timestamp":1772053502593,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/vcip67698.2025.11396865","type":"proceedings-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:55:27Z","timestamp":1771966527000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["MGM-DPO: Multi-Generative-Model Guided Preference Optimization for Advanced Text-to-Image Models"],"prefix":"10.1109","author":[{"given":"Yu","family":"Zhao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiarui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"World model on million-length video and language with blockwise ringattention","author":"Liu","year":"2024"},{"key":"ref2","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref3","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024"},{"key":"ref4","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"ref7","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning (ICML)","author":"Esser"},{"key":"ref8","article-title":"Playground v2. 5: Three insights towards enhancing aesthetic quality in textto-image generation","author":"Li","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref11","first-page":"16083","article-title":"Any-to-any generation via composable diffusion","volume":"36","author":"Tang","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref12","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024"},{"key":"ref13","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","author":"Team","year":"2024"},{"issue":"3","key":"ref14","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref15","article-title":"Flux","year":"2024"},{"key":"ref16","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","article-title":"Improving video generation with human feedback","author":"Liu","year":"2025"},{"key":"ref18","article-title":"Visionreward: Fine-grained multi-dimensional human preference learning for image and video generation","author":"Xu","year":"2024"},{"key":"ref19","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref20","article-title":"Improving dynamic object interactions in text-to-video generation with ai feedback","author":"Furuta","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref22","article-title":"Lmm4lmm: Benchmarking and evaluating large-multimodal image generation with lmms","author":"Wang","year":"2025"},{"key":"ref23","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref27","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446282"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref30","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"}],"event":{"name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","location":"Klagenfurt, Austria","start":{"date-parts":[[2025,12,1]]},"end":{"date-parts":[[2025,12,4]]}},"container-title":["2025 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11396756\/11396790\/11396865.pdf?arnumber=11396865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:54:00Z","timestamp":1772052840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396865\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396865","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}