The paper investigates whether the stable GAN architecture R3GAN can improve time‑series imputation when adapted to 1‑D temporal data. Using a coarse‑to‑fine refinement framework and a frequency‑domain discriminator, the authors evaluate 14 saved configurations across three datasets and find a negative result: most configurations either show negligible improvement or degrade performance compared to baseline methods. The study highlights that the usual argument—GANs optimize distributional objectives rather than point‑wise ones—does not fully explain the lack of benefit, and it poses an open problem regarding why a learned discriminator fails to provide useful refinement gradients while diffusion denoisers succeed, offering practical guidance on when adversarial refinement may be worthwhile.
arXiv:2608. 10096v1 Announce Type: cross Abstract: Modern data science increasingly gives rise to hypothesis-testing problems that are not naturally formulated in terms of parameters within prespecified statistical models.
NextGAN introduces a new training approach for GANs that regresses the critic’s input gradient onto displacements between paired reference and generated features in frozen representation spaces, effectively adding a gradient‑energy penalty while keeping the generator’s standard update. This method scales to very large pre‑trained image and video generators (up to 14 B parameters) without extra losses or teacher signals, achieving state‑of‑the‑art one‑step FIDs on ImageNet and superior VBench scores for text‑to‑video generation with a single 1.3 B model.
arXiv:2509. 24935v3 Announce Type: replace-cross Abstract: Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning.
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...
EmbeddGAN introduces a new GAN framework that replaces the traditional discriminator with an embedding network trained to maximize statistical dependence between embeddings and real/fake labels using Gini distance correlation (gCor). The generator simultaneously minimizes this dependence, encouraging real and generated samples to become indistinguishable in the learned low‑dimensional embedding space. Experiments on MNIST, CIFAR‑10, and CelebA show competitive performance and notably more stable training dynamics compared to established baselines.
arXiv:2404. 06294v2 Announce Type: replace-cross Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart.
The paper reexamines GAN training by replacing the traditional cross‑entropy discriminator with an upper bound on the Bayes error rate, using the Bayes optimal learning threshold (BOLT) loss. It shows that, with balanced class priors, the resulting adversarial game is equivalent to minimizing total variation between data and generator distributions, and introduces BOLT‑GAN when the discriminator is constrained to be 1‑Lipschitz. Experiments on four image‑generation benchmarks demonstrate that BOLT‑GAN achieves better sample quality and coverage than WGAN‑GP, reducing FID scores on CIFAR‑10 and LSUN Bedroom‑64 within a 20‑epoch budget.
arXiv:2608. 19540v1 Announce Type: new Abstract: Training fast generators on new domains with limited data remains challenging for two reasons.
arXiv:2508. 01725v5 Announce Type: replace Abstract: Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM), estimate high-dimensional data distributions conditioned on scalar regression labels such as angles, ages, or temperatures.
Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costly multi-step sampling unaddressed, and existing acceleration methods are tied to the source parameterization--$ε$, $x$, $v$, or $u$--leaving heterogeneous pretrained models with no common acceleration target.
arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.
arXiv:2608.19540v4 Announce Type: replace Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model...