Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19, 2025 • 236
nablaNABLA: Neighborhood Adaptive Block-Level Attention Paper • 2507.13546 • Published Jul 17, 2025 • 126
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published Mar 20, 2025 • 73