{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:29Z","timestamp":1777888769422,"version":"3.51.4"},"reference-count":47,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01627","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17516-17525","source":"Crossref","is-referenced-by-count":0,"title":["Discovering Divergent Representations Between Text-To-Image Models"],"prefix":"10.1109","author":[{"given":"Lisa","family":"Dunlap","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph E.","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian Caba","family":"Heilbron","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Russell","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Introducing stable diffusion 3.5"},{"key":"ref2","year":"2024","journal-title":"Llama 3 model card"},{"key":"ref3","article-title":"Anthropic","year":"2024","journal-title":"Claude 3.5 sonnet"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594095"},{"key":"ref6","volume-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_25"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_11"},{"key":"ref10","article-title":"Dall-eval: Probing the reasoning skills and social biases of text-to-image generative transformers","author":"Cho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/h0026256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3592901\/mm1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00185"},{"key":"ref16","volume-title":"Dreamlike photoreal 2.0","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02284"},{"key":"ref18","article-title":"Fair diffusion: Instructing text-to-image generation models on fairness","author":"Friedrich","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","author":"Gandelsman","year":"2023","journal-title":"Interpreting clip\u2019s image representation via text-based decomposition"},{"key":"ref20","author":"Gandelsman","year":"2024","journal-title":"Interpreting the second-order effects of neurons in clip"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.465"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00287"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31657"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref25","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref27","article-title":"The platonic representation hypothesis","volume-title":"ICML","author":"Huh","year":"2024"},{"key":"ref28","article-title":"Openclip, 2021","author":"Ilharco","journal-title":"If you use this software, please cite it as below"},{"key":"ref29","author":"Lauren\u00e7on","year":"2024","journal-title":"Building and better understanding visionlanguage models: insights and future directions"},{"key":"ref30","article-title":"Holistic evaluation of text-to-image models","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS)","author":"Lee"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23161-2_300919"},{"key":"ref32","author":"Lin","year":"2024","journal-title":"Sdxllightning: Progressive adversarial diffusion distillation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","article-title":"Organizing unstructured image collections using natural language","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Stable bias: Analyzing societal representations in diffusion models","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS)","author":"Sasha Luccioni"},{"key":"ref36","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref37","article-title":"Benchmark for compositional text-to-image synthesis","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)","author":"Park"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref39","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"2234","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","article-title":"LAION-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Schuhmann"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref43","article-title":"One embedder","author":"Su","year":"2022","journal-title":"any task: Instruction-finetuned text embeddings"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1275"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.160"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00894"},{"key":"ref47","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv preprint"}],"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\/11446216.pdf?arnumber=11446216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:46Z","timestamp":1777611466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01627","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}