EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling Paper • 2502.09509 • Published Feb 13 • 7
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20 • 138
ObjectMover: Generative Object Movement with Video Prior Paper • 2503.08037 • Published 16 days ago • 4
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models Paper • 2503.09573 • Published 14 days ago • 62
RWKV-7 "Goose" with Expressive Dynamic State Evolution Paper • 2503.14456 • Published 8 days ago • 131