← Search

Yulin Qiao

1 accepted papers

2026

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

CVPR 2026

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity, or fail to adapt to heterogeneous token distributions across layers, leading to model performance degradation. W

Cited by 0SourcecodeScholar