DIP: Unsupervised Dense In-Context Post-training of Visual Representations Paper • 2506.18463 • Published 3 days ago • 17
Boosting Generative Image Modeling via Joint Image-Feature Synthesis Paper • 2504.16064 • Published Apr 22 • 14
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling Paper • 2502.09509 • Published Feb 13 • 7