{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:24:41Z","timestamp":1783095881037,"version":"3.54.6"},"reference-count":92,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271312,62401365,62225112,62132006,U24A20220"],"award-info":[{"award-number":["62271312,62401365,62225112,62132006,U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411,2025M773473"],"award-info":[{"award-number":["BX20250411,2025M773473"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01608","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17312-17323","source":"Crossref","is-referenced-by-count":6,"title":["LMM4LMM: Benchmarking and Evaluating Large-Multimodal Image Generation With LMMs"],"prefix":"10.1109","author":[{"given":"Jiarui","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juntong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Kandinsky 3: Text-to-image synthesis for multifunctional generative framework","author":"Arkhipkin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Consistency-diversity-realism pareto fronts of conditional image generative models","author":"Astolfi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"issue":"3","key":"ref4","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1267"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation","author":"Cho","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Autoregressive video generation without vector quantization","author":"Deng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Esser","year":"2024"},{"key":"ref12","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref15","article-title":"Improved training of wasserstein gans","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Gulrajani","year":"2017"},{"key":"ref16","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Evalmuse-40k: A reliable and fine-grained benchmark with comprehensive human annotations for text-to-image generation model evaluation","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Heusel","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Edward","year":"2022"},{"key":"ref23","article-title":"Ella: Equip diffusion models with 11 m for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref30","article-title":"Imagenhub: Standardizing the evaluation of conditional image generation models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ku","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713945"},{"key":"ref32","volume-title":"Flux","author":"Labs","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3067"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"ref38","article-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Li","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref44","article-title":"World model on million-length video and language with blockwise ringattention","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Deepseek-vl: Towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","year":"2024","journal-title":"Meta AI Blog"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902097"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref52","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref55","first-page":"500","article-title":"Methodology for the subjective assessment of the quality of television pictures","year":"2012","journal-title":"Recommendation ITU-R BT"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref57","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref59","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref61","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3651009"},{"key":"ref64","article-title":"Love: Benchmarking and evaluating text-to-video generation and video-to-text interpretation","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758204"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"ref67","article-title":"Tdve-assessor: Benchmarking and evaluating the quality of text-driven video editing with 1 mms","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","article-title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Q-align: Teaching $l \\text{mms}$ for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref73","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_22"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref77","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758206"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2585880"},{"key":"ref80","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Xu","year":"2023"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209987"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755700"},{"key":"ref84","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref85","article-title":"mplugowl3: Towards long image-sequence understanding in multimodal large language models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ye","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref87","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01352"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref91","first-page":"70","article-title":"Bridging different language models and generative vision models for text-to-image generation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Zhao","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758207"}],"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\/11445370.pdf?arnumber=11445370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:06Z","timestamp":1777613526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01608","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}