The GAN is dead; long live the GAN! A Modern GAN Baseline
Paper • 2501.05441 • Published • 98
cv gen
-
-
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Paper • 2503.07677 • Published • 86 -
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
Paper • 2503.08677 • Published • 29 -
Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space
Paper • 2503.09419 • Published • 6 -
EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering
Paper • 2505.24417 • Published • 13 -
Fine-Grained Perturbation Guidance via Attention Head Selection
Paper • 2506.10978 • Published • 25 -
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 43 -
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
Paper • 2507.22058 • Published • 40 -
Vision Transformers Don't Need Trained Registers
Paper • 2506.08010 • Published • 22 -
Vision Transformers Need Registers
Paper • 2309.16588 • Published • 86