SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding Paper • 2512.14068 • Published 15 days ago • 1
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation Paper • 2510.06303 • Published Oct 7 • 15
SDAR Collection The models without suffixes use the default block size = 4. • 21 items • Updated Sep 9 • 7