AIBullisharXiv – CS AI · 10h ago7/10
🧠
ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers
Researchers introduce ScalingAttention, a training-free framework that optimizes video diffusion transformers by discovering stable, sparse attention patterns encoded in model weights rather than computing them dynamically. The method achieves up to 1.90X speedup while maintaining superior video generation fidelity, addressing a critical computational bottleneck in AI-generated video production.