mlsanityData to 7 Oct 2026

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

arXiv 2501.05441 ↗First posted 9 Jan 2025cs.LG cs.CVcited by 57

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

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 Second, our new loss allows us to discard all ad-hoc tricks and replace outdated backbones used in common GANs with modern architectures.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.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 34; 2026: 23.

57 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  2. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  3. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  4. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 81
  5. 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?cited by 49
  6. 2025StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatarscited by 24
  7. 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminatorcited by 22
  8. 2025Temporal Difference Flowscited by 20
  9. 2025Towards One-step Causal Video Generation via Adversarial Self-Distillationcited by 15
  10. 2025Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detectioncited by 10
  11. 2025Adversarial Flow Modelscited by 10
  12. 2025NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detectioncited by 7
38 more
  1. 2025One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolutioncited by 7
  2. 2025Scalable GANs with Transformerscited by 5
  3. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  4. 2026PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detectioncited by 5
  5. 2025So-Fake: Benchmarking and Explaining Social Media Image Forgery Detectioncited by 4
  6. 2025DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detectioncited by 4
  7. 2025SAIDO: Generalizable Detection of AI-Generated Images via Scene-Aware and Importance-Guided Dynamic Optimization in Continual Learningcited by 4
  8. 2026Continuous Adversarial Flow Modelscited by 4
  9. 2025Guidance Free Image Editing via Explicit Conditioningcited by 3
  10. 2025Learned Lightweight Smartphone ISP with Unpaired Datacited by 3
  11. 2025LLMs Are Not Yet Ready for Deepfake Image Detectioncited by 3
  12. 2026Grounding Synthetic Data Generation With Vision and Language Modelscited by 3
  13. 2026IncreFA: Breaking the Static Wall of Generative Model Attributioncited by 3
  14. 2025Multi-Marginal Flow Matching with Adversarially Learnt Interpolantscited by 2
  15. 2026LiveBand: Live Accompaniment Generation in the Audio Domaincited by 2
  16. 2025Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasetscited by 1
  17. 2025StyleQoRA: Quality-Aware Low-Rank Adaptation for Few-Shot Multi-Style Editingcited by 1
  18. 2026RelA-Diffusion: Relativistic Adversarial Diffusion for Multi-Tracer PET Synthesis from Multi-Sequence MRIcited by 1
  19. 2026TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generationcited by 1
  20. 2026Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detectioncited by 1
  21. 2026DiFA: Inference-Time Forward-Process Alignment for Diffusion Modelscited by 1
  22. 2025Auxiliary Discrminator Sequence Generative Adversarial Networks (ADSeqGAN) for Few Sample Molecule Generationcited by 0
  23. 2025MODIS: Multi-Omics Data Integration for Small and unpaired datasetscited by 0
  24. 2025CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metricscited by 0
  25. 2025Bridging GANs and Bayesian Neural Networks via Partial Stochasticitycited by 0
  26. 2025Noise-Guided Transport for Imitation Learningcited by 0
  27. 2025UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANscited by 0
  28. 2025SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminatorcited by 0
  29. 2025GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solvercited by 0
  30. 2025Revisiting GAN with Bayes-Optimal Discriminationcited by 0
  31. 2025Recovering Sub-threshold S-wave Arrivals in Deep Learning Phase Pickers via Shape-Aware Losscited by 0
  32. 2025How Noise Benefits AI-generated Image Detectioncited by 0
  33. 2026ATATA: One Algorithm to Align Them Allcited by 0
  34. 2026SpooFL: Spoofing Federated Learningcited by 0
  35. 2026Consistency-Regularized GAN for Few-Shot SAR Target Recognitioncited by 0
  36. 2026Controllable Image Generation with Composed Parallel Token Predictioncited by 0
  37. 2026Pairing Regularization for Mitigating Many-to-One Collapse in GANscited by 0
  38. 2026Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detectioncited by 0

50 most cited of 57 All 57 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
  2. 2025Generative Adversarial Networks Bridging Art and Machine Intelligence
  3. 2023SMaRt: Improving GANs with Score Matching Regularity
  4. 2023Scaling up GANs for Text-to-Image Synthesis
  5. 2024E2GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
  6. 2025BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs
  7. 2024Towards Practical Single-shot Motion Synthesis
  8. 2024Distilling Diffusion Models into Conditional GANs