{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:28Z","timestamp":1778048308261,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00080","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"751-761","source":"Crossref","is-referenced-by-count":0,"title":["Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis"],"prefix":"10.1109","author":[{"given":"Imanol G.","family":"Estepa","sequence":"first","affiliation":[{"name":"Universitat de Barcelona,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jes\u00fas M.","family":"Rodr\u00edguez-de-Vera","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignacio","family":"Saras\u00faa","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhalaji","family":"Nagarajan","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petia","family":"Radeva","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref3","author":"Bao","year":"2021","journal-title":"BEiT: BERT Pre-Training of Image Transformers"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref5","author":"Brock","year":"2018","journal-title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","first-page":"27517","article-title":"Instance-Conditioned GAN","volume-title":"Advances in Neural Information Processing Systems","author":"Casanova","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref10","first-page":"1597","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref12","author":"Chen","year":"2020","journal-title":"Improved Baselines with Momentum Contrastive Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref15","author":"Chen","year":"2024","journal-title":"Deconstructing Denoising Diffusion Models for Self-Supervised Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3443885"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref18","author":"Dao","year":"2023","journal-title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning"},{"key":"ref19","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Dhariwal"},{"key":"ref20","article-title":"Large Scale Adversarial Representation Learning","volume-title":"Advances in Neural Information Processing Systems","author":"Donahue","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00029"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01488"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_25"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02524-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1285"},{"key":"ref31","author":"Huang","year":"2024","journal-title":"Learning Mask Invariant Mutual Information for Masked Image Modeling"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref33","first-page":"5034","article-title":"Characterizing Structural Regularities of Labeled Data in Overparameterized Models","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Jiang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_11"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02771"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01836"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01429"},{"key":"ref40","first-page":"4183","article-title":"High-Fidelity Image Generation With Fewer Labels","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Lu\u010di\u0107"},{"key":"ref41","article-title":"Unitok: A unified tokenizer for visual generation and understanding","author":"Ma","year":"2025"},{"key":"ref42","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3686"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref45","author":"van den Oord","year":"2019","journal-title":"Representation Learning with Contrastive Predictive Coding"},{"key":"ref46","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref47","article-title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","author":"Ozbulak","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01582"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref53","author":"Tian","year":"2024","journal-title":"ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process"},{"key":"ref54","article-title":"Attention is All you Need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref58","author":"Yu","year":"2021","journal-title":"Vector-quantized Image Modeling with Improved VQGAN"},{"key":"ref59","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024"},{"key":"ref60","first-page":"12310","article-title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Zbontar"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1967"},{"key":"ref62","author":"Zhang","year":"2024","journal-title":"EDT: Improving Large Language Models\u2019 Generation by Entropy-based Dynamic Temperature Sampling"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/865"},{"key":"ref64","first-page":"18367","article-title":"Improved Transformer for High-Resolution GANs","author":"Zhao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref65","author":"Zhou","year":"2021","journal-title":"Image BERT Pre-training with Online Tokenizer"},{"key":"ref66","author":"Zhou","year":"2022","journal-title":"iBOT: Image BERT Pre-Training with Online Tokenizer"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref68","article-title":"Stabilize the latent space for image autoregressive modeling: A unified perspective","author":"Zhu","year":"2024"},{"key":"ref69","author":"Zhu","year":"2024","journal-title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492140.pdf?arnumber=11492140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:21Z","timestamp":1778046861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00080","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}