{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:53Z","timestamp":1777865393785,"version":"3.51.4"},"reference-count":60,"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\/iccv51701.2025.01619","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17432-17442","source":"Crossref","is-referenced-by-count":0,"title":["Imbalance in Balance: Online Concept Balancing in Generation Models"],"prefix":"10.1109","author":[{"given":"Yukai","family":"Shi","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiarong","family":"Ou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_25"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","article-title":"Pixart- \\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref10","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Esser","year":"2024"},{"key":"ref13","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"arXiv preprint","author":"Feng","year":"2022"},{"key":"ref14","volume-title":"Flux. Flux [Text-to-Image Model]","year":"2024"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref20","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00487"},{"key":"ref22","volume-title":"Kuaishou. Kling","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-018-0151-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1797"},{"key":"ref26","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref28","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref30","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Improving text-to-image consistency via automatic prompt optimization","author":"Ma\u00f1as","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref33","volume-title":"Midjourney. Midjourney (V5.2) [Text-to-Image Model]","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2182"},{"key":"ref35","year":"2023","journal-title":"OpenAI. Gpt-4v(ision) system card"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01768"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref41","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":"Journal of machine learning research"},{"key":"ref42","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume":"33","author":"Ren","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref45","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"ref47","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_24"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00789"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0304"},{"key":"ref54","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Training class-imbalanced diffusion model via overlap optimization","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"128940128966","article-title":"An image is worth 32 tokens for reconstruction and generation","volume":"37","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref58","article-title":"Long-tailed diffusion models with oriented calibration","volume-title":"The twelfth international conference on learning representations","author":"Zhang","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_19"}],"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\/11446147.pdf?arnumber=11446147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:24:22Z","timestamp":1777530262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01619","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}