Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation

Documenti analoghi

• Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
  di: Luo, Jiayi, et al.
  Pubblicazione: (2026)
• Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
  di: Yang, Shuo, et al.
  Pubblicazione: (2025)
• OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
  di: Chen, Feng, et al.
  Pubblicazione: (2025)
• Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
  di: Mutlu, Sinan, et al.
  Pubblicazione: (2025)
• Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
  di: Xu, Boxun, et al.
  Pubblicazione: (2026)