{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:21:03Z","timestamp":1780057263550,"version":"3.54.0"},"reference-count":43,"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\/iccv51701.2025.01525","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16431-16440","source":"Crossref","is-referenced-by-count":1,"title":["DIMCIM: A Quantitative Evaluation Framework for Default-Mode Diversity and Generalization in Text-to-Image Generative Models"],"prefix":"10.1109","author":[{"given":"Revant","family":"Teotia","sequence":"first","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Candace","family":"Ross","sequence":"additional","affiliation":[{"name":"FAIR at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Ullrich","sequence":"additional","affiliation":[{"name":"FAIR at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumit","family":"Chopra","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriana","family":"Romero-Soriano","sequence":"additional","affiliation":[{"name":"FAIR at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Hall","sequence":"additional","affiliation":[{"name":"FAIR at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Muckley","sequence":"additional","affiliation":[{"name":"FAIR at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"arXiv-2310","article-title":"Feedback-guided data synthesis for imbalanced classification","author":"Askari Hemmat","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref2","author":"Astolfi","year":"2024","journal-title":"Consistency-diversity-realism pareto fronts of conditional image generative models"},{"key":"ref3","article-title":"Boosting latent diffusion with perceptual objectives","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Berrada"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref5","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation","author":"Cho","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0265"},{"key":"ref7","author":"Cho","year":"2024","journal-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation"},{"key":"ref8","author":"Won Chung","year":"2022","journal-title":"Scaling instruction-finetuned language models"},{"key":"ref9","author":"Conwell","year":"2024","journal-title":"Relations, negations, and numbers: Looking for logic in generative text-to-image models"},{"key":"ref10","article-title":"Particle guidance: noniid diverse sampling with diffusion models","author":"Corso","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01162"},{"key":"ref14","author":"Esser","year":"2024","journal-title":"Scaling rectified flow transformers for high-resolution image synthesis"},{"key":"ref15","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","author":"Friedman","year":"2023","journal-title":"The vendi score: A diversity evaluation metric for machine learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58292-0_40250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref20","author":"Heusel","year":"2018","journal-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium"},{"key":"ref21","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref22","author":"Honnibal","year":"2020","journal-title":"spaCy: Industrial-strength Natural Language Processing in Python"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref24","author":"Hu","year":"2023","journal-title":"Smith. Tifa: Accurate and interpretable text-to-image faithfulness evaluation with question answering"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref26","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Improved precision and recall metric for assessing generative models"},{"key":"ref27","volume-title":"Flux","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","article-title":"Evaluating text-to-visual generation with image-to-text generation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","author":"Lipman","year":"2023","journal-title":"Flow matching for generative modeling"},{"key":"ref31","author":"Ferjad Naeem","year":"2020","journal-title":"Reliable fidelity and diversity metrics for generative models"},{"key":"ref32","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.30965\/9783657786411_20311"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","article-title":"What makes a good metric? evaluating automatic metrics for text-to-image consistency","author":"Ross","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Cads: Unleashing the diversity of diffusion models through condition-annealed sampling","author":"Sadat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01120"},{"key":"ref38","article-title":"Evalalign: Supervised finetuning multimodal 11 ms with human-aligned data for evaluating text-to-image models","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","year":"2024","journal-title":"Llama 3 herd of models"},{"key":"ref40","article-title":"The new data and new challenges in multimedia research","volume":"abs\/1503.01817","author":"Thomee","year":"2015","journal-title":"CoRR"},{"key":"ref41","article-title":"Conceptmix: A compositional image generation benchmark with controllable difficulty","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Diverse diffusion: Enhancing image diversity in text-toimage generation","author":"Zameshina","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"A contrastive compositional benchmark for text-to-image synthesis: A study with unified text-to-image fidelity metrics","author":"Zhu","year":"2023","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\/11445044.pdf?arnumber=11445044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:14Z","timestamp":1777613474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01525","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}