{"slug": "scalable-gans-with-transformers", "title": "Scalable GANs with Transformers", "summary": "Researchers introduced GAT, a purely transformer-based Generative Adversarial Network trained in a compact Variational Autoencoder latent space, achieving state-of-the-art single-step class-conditional generation on ImageNet-256 with an FID of 2.18 in just 60 epochs. The model scales from S to XL sizes by addressing failure modes like early-layer underutilization and optimization instability through lightweight intermediate supervision and width-aware learning-rate adjustment.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n[Submitted on 29 Sep 2025 (\n\n[v1](https://arxiv.org/abs/2509.24935v1)), last revised 5 Jun 2026 (this version, v3)]# Title:Scalable GANs with Transformers\n\n[View PDF](/pdf/2509.24935)\n\n[HTML (experimental)](https://arxiv.org/html/2509.24935v3)\n\nAbstract:Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigate the scalability of Generative Adversarial Networks (GANs) through two design choices that have proven to be effective in other types of generative models: training in a compact Variational Autoencoder latent space and adopting purely transformer-based generators and discriminators. Training in latent space enables efficient computation while preserving perceptual fidelity, and this efficiency pairs naturally with plain transformers, whose performance scales with computational budget. Building on these choices, we analyze failure modes that emerge when naively scaling GANs. Specifically, we find issues as underutilization of early layers in the generator and optimization instability as the network scales. Accordingly, we provide simple and scale-friendly solutions as lightweight intermediate supervision and width-aware learning-rate adjustment. Our experiments show that GAT, a purely transformer-based and latent-space GANs, can be easily trained reliably across a wide range of capacities (S through XL). Moreover, GAT-XL/2 achieves state-of-the-art single-step, class-conditional generation performance (FID of 2.18) on ImageNet-256 in just 60 epochs, 4x fewer epochs than strong baselines. Project page:[this https URL].\n\n## Submission history\n\nFrom: Sangeek Hyun [[view email](/show-email/6304dfc3/2509.24935)]\n\n**Mon, 29 Sep 2025 15:36:15 UTC (41,481 KB)**\n\n[[v1]](/abs/2509.24935v1)**Tue, 26 May 2026 03:14:03 UTC (16,766 KB)**\n\n[[v2]](/abs/2509.24935v2)**[v3]** Fri, 5 Jun 2026 02:15:59 UTC (16,766 KB)\n\n### Current browse context:\n\ncs.CV\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/scalable-gans-with-transformers", "canonical_source": "https://arxiv.org/abs/2509.24935", "published_at": "2026-06-30 22:41:55+00:00", "updated_at": "2026-06-30 23:20:10.829324+00:00", "lang": "en", "topics": ["generative-ai", "computer-vision", "machine-learning", "neural-networks", "artificial-intelligence"], "entities": ["GAT", "ImageNet", "Variational Autoencoder", "Sangeek Hyun"], "alternates": {"html": "https://wpnews.pro/news/scalable-gans-with-transformers", "markdown": "https://wpnews.pro/news/scalable-gans-with-transformers.md", "text": "https://wpnews.pro/news/scalable-gans-with-transformers.txt", "jsonld": "https://wpnews.pro/news/scalable-gans-with-transformers.jsonld"}}