arXiv AI
FisherDistill: Diffusion Distribution Distillation via Closed-Form Fisher Critics
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
2d ago
NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers
arXiv:2611.05648v1 Announce Type: new Abstract: Adversarial diffusion distillation has conventionally relied on image features for discrimination. We revisit this choice for multimodal diffusion tran...
arXiv Computer Vision
Oct 1
Enhancing Autoregressive Video Generation via Representation Adversarial Distillation
arXiv:2609.40037v1 Announce Type: new Abstract: Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context an...
Hugging Face Trending Papers
5d ago
Latent Diffusion-GAN: Adversarial Learning in the Autoencoded Latent Space
Latent Diffusion-GAN (LD‑GAN) integrates adversarial learning into diffusion models by using the pretrained VAE as an energy‑based discriminator, avoiding extra parameters and preserving the latent priors. It introduces a structural consistency energy to align encoder and decoder features, improving perceptual quality. Experiments show LD‑GAN enhances sample fidelity, sharpness, and diversity across generation tasks while maintaining efficient training dynamics.
arXiv Computer Vision
Sep 30
Adversarial Training for Pixel Diffusion
Pixel diffusion models generate RGB images directly but tend to miss fine‑scale natural‑image statistics. The authors introduce an adversarial post‑training step that adds an adversarial loss to the model’s output at non‑high‑noise timesteps, without changing the architecture or sampling procedure. This approach improves distribution fidelity, coverage, prompt alignment, and perceptual quality across two pixel backbones, and restores missing high‑frequency spectral power while avoiding memorization or mode dropping.
arXiv Machine Learning
Sep 22
EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation
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 Computer Vision
Sep 7
PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization
PAPT++ is a risk‑aware adversarial generation‑training framework designed to improve single domain generalization. It learns diverse semantic reference images per class and uses them as denoising targets in classifier‑guided diffusion synthesis, thereby generating challenging yet semantically consistent samples. These samples are iteratively combined with source data to update the classifier, progressively exposing it to difficult variations and enhancing generalization performance on standard benchmarks.