{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:24Z","timestamp":1780949124758,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NTU SUG-NAP"},{"name":"Funding Initiative"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3663759","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:55:51Z","timestamp":1770843351000},"page":"7692-7706","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7976-8439","authenticated-orcid":false,"given":"Tianyi","family":"Wei","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4642-4373","authenticated-orcid":false,"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft GenAI, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Zhou","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5825-9467","authenticated-orcid":false,"given":"Xingang","family":"Pan","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref2","article-title":"SD3.5: Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2025"},{"key":"ref3","article-title":"Flux","author":"Labs","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref6","first-page":"1","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"issue":"140","key":"ref9","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02156"},{"key":"ref15","first-page":"1","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562237"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3547889"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref20","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3522305"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3541625"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3510752"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref27","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref28","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generat. Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref29","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"ref31","article-title":"Investigating prompt engineering in diffusion models","author":"Witteveen","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2923"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref35","first-page":"1","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Feng","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3101"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref42","first-page":"3536","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rassin","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00826"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01715"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00097"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref50","first-page":"1","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","volume":"2024","author":"Lian","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657527"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00241"},{"key":"ref58","article-title":"GPT-4o mini: Advancing cost-efficient intelligence","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref60","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref61","article-title":"ChatGPT","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref66","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11391567.pdf?arnumber=11391567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:00Z","timestamp":1780948320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":66,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3663759","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}