{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:17Z","timestamp":1777865477656,"version":"3.51.4"},"reference-count":67,"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\/iccv51701.2025.02262","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24402-24412","source":"Crossref","is-referenced-by-count":1,"title":["GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers"],"prefix":"10.1109","author":[{"given":"Shijie","family":"Ma","sequence":"first","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuying","family":"Ge","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Guo","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixiao","family":"Ge","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks","year":"2024","journal-title":"OpenAI Blog"},{"key":"ref4","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Deconstructing denoising diffusion models for self-supervised learning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref10","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3658965"},{"key":"ref12","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02523"},{"key":"ref15","article-title":"Aligned better, listen better for audio-visual large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Guo"},{"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":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"ref19","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_7"},{"key":"ref21","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref23","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref24","volume-title":"Flux","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0542"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref28","article-title":"Toklip: Marry visual tokens to clip for multimodal comprehension and generation","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref32","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref34","article-title":"DEEM: Diffusion models serve as the eyes of large language models for image perception","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Luo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1609"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01598"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110875"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3557502"},{"key":"ref39","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0803"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02583"},{"key":"ref48","article-title":"Data pruning by information maximization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tan"},{"key":"ref49","author":"Tan","year":"2025","journal-title":"Diff-in: Data influence estimation with differential approximation"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2098"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2771"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref54","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref55","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","article-title":"Reconstructive visual instruction tuning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref58","article-title":"Diffusion feedback helps CLIP see better","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref61","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xie"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref65","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Yu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/11445399.pdf?arnumber=11445399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:38:44Z","timestamp":1777531124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02262","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}