{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T12:07:26Z","timestamp":1768910846296,"version":"3.49.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3651887","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:28Z","timestamp":1768255348000},"page":"6566-6582","source":"Crossref","is-referenced-by-count":0,"title":["UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6198-7906","authenticated-orcid":false,"given":"Wonjun","family":"Kang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8517-6177","authenticated-orcid":false,"given":"Byeongkeun","family":"Ahn","sequence":"additional","affiliation":[{"name":"Independent Researcher, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjae","family":"Lee","sequence":"additional","affiliation":[{"name":"FuriosaAI, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Galim","sequence":"additional","affiliation":[{"name":"FuriosaAI, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seunghyuk","family":"Oh","sequence":"additional","affiliation":[{"name":"FuriosaAI, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6955-8083","authenticated-orcid":false,"given":"Hyung","family":"Il Koo","sequence":"additional","affiliation":[{"name":"FuriosaAI, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-4649","authenticated-orcid":false,"given":"Nam","family":"Ik Cho","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref2","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv:2406.06525"},{"key":"ref6","first-page":"84839","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref8","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref9","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref10","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref13","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref14","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref15","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref16","article-title":"Lumina-mGPT: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv:2408.02657"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref18","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref19","first-page":"1","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Bai"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref21","first-page":"3536","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rassin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00826"},{"key":"ref23","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"1","author":"Chen"},{"key":"ref24","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref25","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Podell"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02125"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"ref29","first-page":"1","article-title":"Halton scheduler for masked generative image transformer","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Besnier"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref31","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02191"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref34","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref35","first-page":"12268","article-title":"VIEScore: Towards explainable metrics for conditional image synthesis evaluation","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","author":"Ku"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00097"},{"key":"ref38","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11339498.pdf?arnumber=11339498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:55:46Z","timestamp":1768856146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3651887","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}