Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention Paper • 2602.04789 • Published 6 days ago • 3
Rethinking Video Generation Model for the Embodied World Paper • 2601.15282 • Published 20 days ago • 43
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published 29 days ago • 52