# The GAN is dead; long live the GAN! A Modern GAN Baseline

arXiv: https://arxiv.org/abs/2501.05441 · HTML: https://mlsanity.com/paper/2501.05441/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2025.

## Built on by (most cited first, 30 of 59)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Diffusion Adversarial Post-Training for One-Step Video Generation](https://mlsanity.com/paper/2501.08316/) (2025)
- [Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2506.09350/) (2025)
- [Align Your Flow: Scaling Continuous-Time Flow Map Distillation](https://mlsanity.com/paper/2506.14603/) (2025)
- [Is Artificial Intelligence Generated Image Detection a Solved Problem?](https://mlsanity.com/paper/2505.12335/) (2025)
- [StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars](https://mlsanity.com/paper/2512.22065/) (2025)
- [Temporal Difference Flows](https://mlsanity.com/paper/2503.09817/) (2025)
- [Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator](https://mlsanity.com/paper/2503.01103/) (2025)
- [Towards One-step Causal Video Generation via Adversarial Self-Distillation](https://mlsanity.com/paper/2511.01419/) (2025)
- [Adversarial Flow Models](https://mlsanity.com/paper/2511.22475/) (2025)
- [Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection](https://mlsanity.com/paper/2501.15253/) (2025)
- [NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2508.01248/) (2025)
- [One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution](https://mlsanity.com/paper/2511.17138/) (2025)
- [PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.21207/) (2026)
- [So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection](https://mlsanity.com/paper/2505.18660/) (2025)
- [Scalable GANs with Transformers](https://mlsanity.com/paper/2509.24935/) (2025)
- [DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection](https://mlsanity.com/paper/2511.13108/) (2025)
- [SAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learning](https://mlsanity.com/paper/2512.00539/) (2025)
- [Continuous Adversarial Flow Models](https://mlsanity.com/paper/2604.11521/) (2026)
- [Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling](https://mlsanity.com/paper/2604.28185/) (2026)
- [LLMs Are Not Yet Ready for Deepfake Image Detection](https://mlsanity.com/paper/2506.10474/) (2025)
- [Multi-Marginal Flow Matching with Adversarially Learnt Interpolants](https://mlsanity.com/paper/2510.01159/) (2025)
- [Guidance Free Image Editing via Explicit Conditioning](https://mlsanity.com/paper/2503.17593/) (2025)
- [Learned Lightweight Smartphone ISP with Unpaired Data](https://mlsanity.com/paper/2505.10420/) (2025)
- [Grounding Synthetic Data Generation With Vision and Language Models](https://mlsanity.com/paper/2603.09625/) (2026)
- [IncreFA: Breaking the Static Wall of Generative Model Attribution](https://mlsanity.com/paper/2604.17736/) (2026)
- [StyleQoRA: Quality-Aware Low-Rank Adaptation for Few-Shot Multi-Style Editing](https://mlsanity.com/paper/2511.11236/) (2025)
- [LiveBand: Live Accompaniment Generation in the Audio Domain](https://mlsanity.com/paper/2606.03803/) (2026)
- [MODIS: Multi-Omics Data Integration for Small and unpaired datasets](https://mlsanity.com/paper/2503.18856/) (2025)
- [CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics](https://mlsanity.com/paper/2504.05945/) (2025)

## Abstract (arXiv)

There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks. We provide evidence against this claim and build a modern GAN baseline in a more principled manner. First, we derive a well-behaved regularized relativistic GAN loss that addresses issues of mode dropping and non-convergence that were previously tackled via a bag of ad-hoc tricks. We analyze our loss mathematically and prove that it admits local convergence guarantees, unlike most existing relativistic losses. Second, our new loss allows us to discard all ad-hoc tricks and replace outdated backbones used in common GANs with modern architectures. Using StyleGAN2 as an example, we present a roadmap of simplification and modernization that results in a new minimalist baseline -- R3GAN. Despite being simple, our approach surpasses StyleGAN2 on FFHQ, ImageNet, CIFAR, and Stacked MNIST datasets, and compares favorably against state-of-the-art GANs and diffusion models.