Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Paper • 2505.18875 • Published • 42
Attention
-
-
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
Paper • 2506.16054 • Published • 60 -
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Paper • 2410.02367 • Published • 50 -
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 42 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 126 -
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60 -
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
Paper • 2509.24006 • Published • 119 -
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Paper • 2509.24695 • Published • 47 -
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
Paper • 2510.04212 • Published • 26 -
Native Hybrid Attention for Efficient Sequence Modeling
Paper • 2510.07019 • Published • 17 -
Sparser Block-Sparse Attention via Token Permutation
Paper • 2510.21270 • Published • 25 -
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Paper • 2511.11062 • Published • 32 -
Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
Paper • 2602.01801 • Published • 28 -
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Paper • 2602.13515 • Published • 44 -
SLA2: Sparse-Linear Attention with Learnable Routing and QAT
Paper • 2602.12675 • Published • 57