Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
This work introduces SparsePR, which combines Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction and consistently reduces attention-reconstruction error across four heterogeneous video generation and world models.
P. Taghavi, Reza Langari, Gaurav Pandey
· 0 citations